yujia/ieemoo-ai-detecttracking
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

回传数据解析，兼容v5和v10

Browse Source
This commit is contained in:
jiajie555
2025-04-18 14:41:53 +08:00
commit 010f5c445a
888 changed files with 93632 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
ultralytics/__init__.py Normal file
View File

@ -0,0 +1,27 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
__version__ = "8.1.34"
from ultralytics.data.explorer.explorer import Explorer
from ultralytics.models import RTDETR, SAM, YOLO, YOLOWorld, YOLOv10
from ultralytics.models.fastsam import FastSAM
from ultralytics.models.nas import NAS
from ultralytics.utils import ASSETS, SETTINGS as settings
from ultralytics.utils.checks import check_yolo as checks
from ultralytics.utils.downloads import download
__all__ = (
"__version__",
"ASSETS",
"YOLO",
"YOLOWorld",
"NAS",
"SAM",
"FastSAM",
"RTDETR",
"checks",
"download",
"settings",
"Explorer",
"YOLOv10"
)

BIN
ultralytics/__pycache__/__init__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/__pycache__/__init__.cpython-39.pyc Normal file
View File

Binary file not shown.

613
ultralytics/cfg/__init__.py Normal file
View File

@ -0,0 +1,613 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
import contextlib
import os
import shutil
import subprocess
import sys
from pathlib import Path
from types import SimpleNamespace
from typing import Dict, List, Union
import re
from ultralytics.utils import (
ASSETS,
DEFAULT_CFG,
DEFAULT_CFG_DICT,
DEFAULT_CFG_PATH,
LOGGER,
RANK,
ROOT,
RUNS_DIR,
SETTINGS,
SETTINGS_YAML,
TESTS_RUNNING,
IterableSimpleNamespace,
__version__,
checks,
colorstr,
deprecation_warn,
yaml_load,
yaml_print,
)
# Define valid tasks and modes
MODES = {"train", "val", "predict", "export", "track", "benchmark"}
TASKS = {"detect", "segment", "classify", "pose", "obb"}
TASK2DATA = {
"detect": "coco8.yaml",
"segment": "coco8-seg.yaml",
"classify": "imagenet10",
"pose": "coco8-pose.yaml",
"obb": "dota8.yaml",
}
TASK2MODEL = {
"detect": "yolov8n.pt",
"segment": "yolov8n-seg.pt",
"classify": "yolov8n-cls.pt",
"pose": "yolov8n-pose.pt",
"obb": "yolov8n-obb.pt",
}
TASK2METRIC = {
"detect": "metrics/mAP50-95(B)",
"segment": "metrics/mAP50-95(M)",
"classify": "metrics/accuracy_top1",
"pose": "metrics/mAP50-95(P)",
"obb": "metrics/mAP50-95(B)",
}
CLI_HELP_MSG = f"""
Arguments received: {str(['yolo'] + sys.argv[1:])}. Ultralytics 'yolo' commands use the following syntax:
yolo TASK MODE ARGS
Where TASK (optional) is one of {TASKS}
MODE (required) is one of {MODES}
ARGS (optional) are any number of custom 'arg=value' pairs like 'imgsz=320' that override defaults.
See all ARGS at https://docs.ultralytics.com/usage/cfg or with 'yolo cfg'
1. Train a detection model for 10 epochs with an initial learning_rate of 0.01
yolo train data=coco128.yaml model=yolov8n.pt epochs=10 lr0=0.01
2. Predict a YouTube video using a pretrained segmentation model at image size 320:
yolo predict model=yolov8n-seg.pt source='https://youtu.be/LNwODJXcvt4' imgsz=320
3. Val a pretrained detection model at batch-size 1 and image size 640:
yolo val model=yolov8n.pt data=coco128.yaml batch=1 imgsz=640
4. Export a YOLOv8n classification model to ONNX format at image size 224 by 128 (no TASK required)
yolo export model=yolov8n-cls.pt format=onnx imgsz=224,128
6. Explore your datasets using semantic search and SQL with a simple GUI powered by Ultralytics Explorer API
yolo explorer
5. Run special commands:
yolo help
yolo checks
yolo version
yolo settings
yolo copy-cfg
yolo cfg
Docs: https://docs.ultralytics.com
Community: https://community.ultralytics.com
GitHub: https://github.com/ultralytics/ultralytics
"""
# Define keys for arg type checks
CFG_FLOAT_KEYS = {"warmup_epochs", "box", "cls", "dfl", "degrees", "shear", "time"}
CFG_FRACTION_KEYS = {
"dropout",
"iou",
"lr0",
"lrf",
"momentum",
"weight_decay",
"warmup_momentum",
"warmup_bias_lr",
"label_smoothing",
"hsv_h",
"hsv_s",
"hsv_v",
"translate",
"scale",
"perspective",
"flipud",
"fliplr",
"bgr",
"mosaic",
"mixup",
"copy_paste",
"conf",
"iou",
"fraction",
} # fraction floats 0.0 - 1.0
CFG_INT_KEYS = {
"epochs",
"patience",
"batch",
"workers",
"seed",
"close_mosaic",
"mask_ratio",
"max_det",
"vid_stride",
"line_width",
"workspace",
"nbs",
"save_period",
}
CFG_BOOL_KEYS = {
"save",
"exist_ok",
"verbose",
"deterministic",
"single_cls",
"rect",
"cos_lr",
"overlap_mask",
"val",
"save_json",
"save_hybrid",
"half",
"dnn",
"plots",
"show",
"save_txt",
"save_conf",
"save_crop",
"save_frames",
"show_labels",
"show_conf",
"visualize",
"augment",
"agnostic_nms",
"retina_masks",
"show_boxes",
"keras",
"optimize",
"int8",
"dynamic",
"simplify",
"nms",
"profile",
"multi_scale",
}
def cfg2dict(cfg):
"""
Convert a configuration object to a dictionary, whether it is a file path, a string, or a SimpleNamespace object.
Args:
cfg (str | Path | dict | SimpleNamespace): Configuration object to be converted to a dictionary.
Returns:
cfg (dict): Configuration object in dictionary format.
"""
if isinstance(cfg, (str, Path)):
cfg = yaml_load(cfg) # load dict
elif isinstance(cfg, SimpleNamespace):
cfg = vars(cfg) # convert to dict
return cfg
def get_cfg(cfg: Union[str, Path, Dict, SimpleNamespace] = DEFAULT_CFG_DICT, overrides: Dict = None):
"""
Load and merge configuration data from a file or dictionary.
Args:
cfg (str | Path | Dict | SimpleNamespace): Configuration data.
overrides (str | Dict | optional): Overrides in the form of a file name or a dictionary. Default is None.
Returns:
(SimpleNamespace): Training arguments namespace.
"""
cfg = cfg2dict(cfg)
# Merge overrides
if overrides:
overrides = cfg2dict(overrides)
if "save_dir" not in cfg:
overrides.pop("save_dir", None) # special override keys to ignore
check_dict_alignment(cfg, overrides)
cfg = {**cfg, **overrides} # merge cfg and overrides dicts (prefer overrides)
# Special handling for numeric project/name
for k in "project", "name":
if k in cfg and isinstance(cfg[k], (int, float)):
cfg[k] = str(cfg[k])
if cfg.get("name") == "model": # assign model to 'name' arg
cfg["name"] = cfg.get("model", "").split(".")[0]
LOGGER.warning(f"WARNING ⚠️ 'name=model' automatically updated to 'name={cfg['name']}'.")
# Type and Value checks
check_cfg(cfg)
# Return instance
return IterableSimpleNamespace(**cfg)
def check_cfg(cfg, hard=True):
"""Check Ultralytics configuration argument types and values."""
for k, v in cfg.items():
if v is not None: # None values may be from optional args
if k in CFG_FLOAT_KEYS and not isinstance(v, (int, float)):
if hard:
raise TypeError(
f"'{k}={v}' is of invalid type {type(v).__name__}. "
f"Valid '{k}' types are int (i.e. '{k}=0') or float (i.e. '{k}=0.5')"
)
cfg[k] = float(v)
elif k in CFG_FRACTION_KEYS:
if not isinstance(v, (int, float)):
if hard:
raise TypeError(
f"'{k}={v}' is of invalid type {type(v).__name__}. "
f"Valid '{k}' types are int (i.e. '{k}=0') or float (i.e. '{k}=0.5')"
)
cfg[k] = v = float(v)
if not (0.0 <= v <= 1.0):
raise ValueError(f"'{k}={v}' is an invalid value. " f"Valid '{k}' values are between 0.0 and 1.0.")
elif k in CFG_INT_KEYS and not isinstance(v, int):
if hard:
raise TypeError(
f"'{k}={v}' is of invalid type {type(v).__name__}. " f"'{k}' must be an int (i.e. '{k}=8')"
)
cfg[k] = int(v)
elif k in CFG_BOOL_KEYS and not isinstance(v, bool):
if hard:
raise TypeError(
f"'{k}={v}' is of invalid type {type(v).__name__}. "
f"'{k}' must be a bool (i.e. '{k}=True' or '{k}=False')"
)
cfg[k] = bool(v)
def get_save_dir(args, name=None):
"""Return save_dir as created from train/val/predict arguments."""
if getattr(args, "save_dir", None):
save_dir = args.save_dir
else:
from ultralytics.utils.files import increment_path
project = args.project or (ROOT.parent / "tests/tmp/runs" if TESTS_RUNNING else RUNS_DIR) / args.task
name = name or args.name or f"{args.mode}"
save_dir = increment_path(Path(project) / name, exist_ok=args.exist_ok if RANK in (-1, 0) else True)
return Path(save_dir)
def _handle_deprecation(custom):
"""Hardcoded function to handle deprecated config keys."""
for key in custom.copy().keys():
if key == "boxes":
deprecation_warn(key, "show_boxes")
custom["show_boxes"] = custom.pop("boxes")
if key == "hide_labels":
deprecation_warn(key, "show_labels")
custom["show_labels"] = custom.pop("hide_labels") == "False"
if key == "hide_conf":
deprecation_warn(key, "show_conf")
custom["show_conf"] = custom.pop("hide_conf") == "False"
if key == "line_thickness":
deprecation_warn(key, "line_width")
custom["line_width"] = custom.pop("line_thickness")
return custom
def check_dict_alignment(base: Dict, custom: Dict, e=None):
"""
This function checks for any mismatched keys between a custom configuration list and a base configuration list. If
any mismatched keys are found, the function prints out similar keys from the base list and exits the program.
Args:
custom (dict): a dictionary of custom configuration options
base (dict): a dictionary of base configuration options
e (Error, optional): An optional error that is passed by the calling function.
"""
custom = _handle_deprecation(custom)
base_keys, custom_keys = (set(x.keys()) for x in (base, custom))
mismatched = [k for k in custom_keys if k not in base_keys]
if mismatched:
from difflib import get_close_matches
string = ""
for x in mismatched:
matches = get_close_matches(x, base_keys) # key list
matches = [f"{k}={base[k]}" if base.get(k) is not None else k for k in matches]
match_str = f"Similar arguments are i.e. {matches}." if matches else ""
string += f"'{colorstr('red', 'bold', x)}' is not a valid YOLO argument. {match_str}\n"
raise SyntaxError(string + CLI_HELP_MSG) from e
def merge_equals_args(args: List[str]) -> List[str]:
"""
Merges arguments around isolated '=' args in a list of strings. The function considers cases where the first
argument ends with '=' or the second starts with '=', as well as when the middle one is an equals sign.
Args:
args (List[str]): A list of strings where each element is an argument.
Returns:
(List[str]): A list of strings where the arguments around isolated '=' are merged.
"""
new_args = []
for i, arg in enumerate(args):
if arg == "=" and 0 < i < len(args) - 1: # merge ['arg', '=', 'val']
new_args[-1] += f"={args[i + 1]}"
del args[i + 1]
elif arg.endswith("=") and i < len(args) - 1 and "=" not in args[i + 1]: # merge ['arg=', 'val']
new_args.append(f"{arg}{args[i + 1]}")
del args[i + 1]
elif arg.startswith("=") and i > 0: # merge ['arg', '=val']
new_args[-1] += arg
else:
new_args.append(arg)
return new_args
def handle_yolo_hub(args: List[str]) -> None:
"""
Handle Ultralytics HUB command-line interface (CLI) commands.
This function processes Ultralytics HUB CLI commands such as login and logout.
It should be called when executing a script with arguments related to HUB authentication.
Args:
args (List[str]): A list of command line arguments
Example:
```bash
python my_script.py hub login your_api_key
```
"""
from ultralytics import hub
if args[0] == "login":
key = args[1] if len(args) > 1 else ""
# Log in to Ultralytics HUB using the provided API key
hub.login(key)
elif args[0] == "logout":
# Log out from Ultralytics HUB
hub.logout()
def handle_yolo_settings(args: List[str]) -> None:
"""
Handle YOLO settings command-line interface (CLI) commands.
This function processes YOLO settings CLI commands such as reset.
It should be called when executing a script with arguments related to YOLO settings management.
Args:
args (List[str]): A list of command line arguments for YOLO settings management.
Example:
```bash
python my_script.py yolo settings reset
```
"""
url = "https://docs.ultralytics.com/quickstart/#ultralytics-settings" # help URL
try:
if any(args):
if args[0] == "reset":
SETTINGS_YAML.unlink() # delete the settings file
SETTINGS.reset() # create new settings
LOGGER.info("Settings reset successfully") # inform the user that settings have been reset
else: # save a new setting
new = dict(parse_key_value_pair(a) for a in args)
check_dict_alignment(SETTINGS, new)
SETTINGS.update(new)
LOGGER.info(f"💡 Learn about settings at {url}")
yaml_print(SETTINGS_YAML) # print the current settings
except Exception as e:
LOGGER.warning(f"WARNING ⚠️ settings error: '{e}'. Please see {url} for help.")
def handle_explorer():
"""Open the Ultralytics Explorer GUI."""
checks.check_requirements("streamlit")
LOGGER.info("💡 Loading Explorer dashboard...")
subprocess.run(["streamlit", "run", ROOT / "data/explorer/gui/dash.py", "--server.maxMessageSize", "2048"])
def parse_key_value_pair(pair):
"""Parse one 'key=value' pair and return key and value."""
k, v = pair.split("=", 1) # split on first '=' sign
k, v = k.strip(), v.strip() # remove spaces
assert v, f"missing '{k}' value"
return k, smart_value(v)
def smart_value(v):
"""Convert a string to an underlying type such as int, float, bool, etc."""
v_lower = v.lower()
if v_lower == "none":
return None
elif v_lower == "true":
return True
elif v_lower == "false":
return False
else:
with contextlib.suppress(Exception):
return eval(v)
return v
def entrypoint(debug=""):
"""
This function is the ultralytics package entrypoint, it's responsible for parsing the command line arguments passed
to the package.
This function allows for:
- passing mandatory YOLO args as a list of strings
- specifying the task to be performed, either 'detect', 'segment' or 'classify'
- specifying the mode, either 'train', 'val', 'test', or 'predict'
- running special modes like 'checks'
- passing overrides to the package's configuration
It uses the package's default cfg and initializes it using the passed overrides.
Then it calls the CLI function with the composed cfg
"""
args = (debug.split(" ") if debug else sys.argv)[1:]
if not args: # no arguments passed
LOGGER.info(CLI_HELP_MSG)
return
special = {
"help": lambda: LOGGER.info(CLI_HELP_MSG),
"checks": checks.collect_system_info,
"version": lambda: LOGGER.info(__version__),
"settings": lambda: handle_yolo_settings(args[1:]),
"cfg": lambda: yaml_print(DEFAULT_CFG_PATH),
"hub": lambda: handle_yolo_hub(args[1:]),
"login": lambda: handle_yolo_hub(args),
"copy-cfg": copy_default_cfg,
"explorer": lambda: handle_explorer(),
}
full_args_dict = {**DEFAULT_CFG_DICT, **{k: None for k in TASKS}, **{k: None for k in MODES}, **special}
# Define common misuses of special commands, i.e. -h, -help, --help
special.update({k[0]: v for k, v in special.items()}) # singular
special.update({k[:-1]: v for k, v in special.items() if len(k) > 1 and k.endswith("s")}) # singular
special = {**special, **{f"-{k}": v for k, v in special.items()}, **{f"--{k}": v for k, v in special.items()}}
overrides = {} # basic overrides, i.e. imgsz=320
for a in merge_equals_args(args): # merge spaces around '=' sign
if a.startswith("--"):
LOGGER.warning(f"WARNING ⚠️ argument '{a}' does not require leading dashes '--', updating to '{a[2:]}'.")
a = a[2:]
if a.endswith(","):
LOGGER.warning(f"WARNING ⚠️ argument '{a}' does not require trailing comma ',', updating to '{a[:-1]}'.")
a = a[:-1]
if "=" in a:
try:
k, v = parse_key_value_pair(a)
if k == "cfg" and v is not None: # custom.yaml passed
LOGGER.info(f"Overriding {DEFAULT_CFG_PATH} with {v}")
overrides = {k: val for k, val in yaml_load(checks.check_yaml(v)).items() if k != "cfg"}
else:
overrides[k] = v
except (NameError, SyntaxError, ValueError, AssertionError) as e:
check_dict_alignment(full_args_dict, {a: ""}, e)
elif a in TASKS:
overrides["task"] = a
elif a in MODES:
overrides["mode"] = a
elif a.lower() in special:
special[a.lower()]()
return
elif a in DEFAULT_CFG_DICT and isinstance(DEFAULT_CFG_DICT[a], bool):
overrides[a] = True # auto-True for default bool args, i.e. 'yolo show' sets show=True
elif a in DEFAULT_CFG_DICT:
raise SyntaxError(
f"'{colorstr('red', 'bold', a)}' is a valid YOLO argument but is missing an '=' sign "
f"to set its value, i.e. try '{a}={DEFAULT_CFG_DICT[a]}'\n{CLI_HELP_MSG}"
)
else:
check_dict_alignment(full_args_dict, {a: ""})
# Check keys
check_dict_alignment(full_args_dict, overrides)
# Mode
mode = overrides.get("mode")
if mode is None:
mode = DEFAULT_CFG.mode or "predict"
LOGGER.warning(f"WARNING ⚠️ 'mode' argument is missing. Valid modes are {MODES}. Using default 'mode={mode}'.")
elif mode not in MODES:
raise ValueError(f"Invalid 'mode={mode}'. Valid modes are {MODES}.\n{CLI_HELP_MSG}")
# Task
task = overrides.pop("task", None)
if task:
if task not in TASKS:
raise ValueError(f"Invalid 'task={task}'. Valid tasks are {TASKS}.\n{CLI_HELP_MSG}")
if "model" not in overrides:
overrides["model"] = TASK2MODEL[task]
# Model
model = overrides.pop("model", DEFAULT_CFG.model)
if model is None:
model = "yolov8n.pt"
LOGGER.warning(f"WARNING ⚠️ 'model' argument is missing. Using default 'model={model}'.")
overrides["model"] = model
# stem = Path(model).stem.lower()
stem = model.lower()
if "rtdetr" in stem: # guess architecture
from ultralytics import RTDETR
model = RTDETR(model) # no task argument
elif "fastsam" in stem:
from ultralytics import FastSAM
model = FastSAM(model)
elif "sam" in stem:
from ultralytics import SAM
model = SAM(model)
elif re.search("v3|v5|v6|v8|v9", stem):
from ultralytics import YOLO
model = YOLO(model, task=task)
else:
from ultralytics import YOLOv10
# Special case for the HuggingFace Hub
split_path = model.split('/')
if len(split_path) == 2 and (not os.path.exists(model)):
model = YOLOv10.from_pretrained(model)
else:
model = YOLOv10(model)
if isinstance(overrides.get("pretrained"), str):
model.load(overrides["pretrained"])
# Task Update
if task != model.task:
if task:
LOGGER.warning(
f"WARNING ⚠️ conflicting 'task={task}' passed with 'task={model.task}' model. "
f"Ignoring 'task={task}' and updating to 'task={model.task}' to match model."
)
task = model.task
# Mode
if mode in ("predict", "track") and "source" not in overrides:
overrides["source"] = DEFAULT_CFG.source or ASSETS
LOGGER.warning(f"WARNING ⚠️ 'source' argument is missing. Using default 'source={overrides['source']}'.")
elif mode in ("train", "val"):
if "data" not in overrides and "resume" not in overrides:
overrides["data"] = DEFAULT_CFG.data or TASK2DATA.get(task or DEFAULT_CFG.task, DEFAULT_CFG.data)
LOGGER.warning(f"WARNING ⚠️ 'data' argument is missing. Using default 'data={overrides['data']}'.")
elif mode == "export":
if "format" not in overrides:
overrides["format"] = DEFAULT_CFG.format or "torchscript"
LOGGER.warning(f"WARNING ⚠️ 'format' argument is missing. Using default 'format={overrides['format']}'.")
# Run command in python
getattr(model, mode)(**overrides) # default args from model
# Show help
LOGGER.info(f"💡 Learn more at https://docs.ultralytics.com/modes/{mode}")
# Special modes --------------------------------------------------------------------------------------------------------
def copy_default_cfg():
"""Copy and create a new default configuration file with '_copy' appended to its name."""
new_file = Path.cwd() / DEFAULT_CFG_PATH.name.replace(".yaml", "_copy.yaml")
shutil.copy2(DEFAULT_CFG_PATH, new_file)
LOGGER.info(
f"{DEFAULT_CFG_PATH} copied to {new_file}\n"
f"Example YOLO command with this new custom cfg:\n yolo cfg='{new_file}' imgsz=320 batch=8"
)
if __name__ == "__main__":
# Example: entrypoint(debug='yolo predict model=yolov8n.pt')
entrypoint(debug="")

BIN
ultralytics/cfg/__pycache__/__init__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/cfg/__pycache__/__init__.cpython-39.pyc Normal file
View File

Binary file not shown.

74
ultralytics/cfg/datasets/Argoverse.yaml Normal file
View File

@ -0,0 +1,74 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Argoverse-HD dataset (ring-front-center camera) https://www.cs.cmu.edu/~mengtial/proj/streaming/ by Argo AI
# Documentation: https://docs.ultralytics.com/datasets/detect/argoverse/
# Example usage: yolo train data=Argoverse.yaml
# parent
# ├── ultralytics
# └── datasets
# └── Argoverse ← downloads here (31.5 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/Argoverse # dataset root dir
train: Argoverse-1.1/images/train/ # train images (relative to 'path') 39384 images
val: Argoverse-1.1/images/val/ # val images (relative to 'path') 15062 images
test: Argoverse-1.1/images/test/ # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: bus
5: truck
6: traffic_light
7: stop_sign
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import json
from tqdm import tqdm
from ultralytics.utils.downloads import download
from pathlib import Path
def argoverse2yolo(set):
labels = {}
a = json.load(open(set, "rb"))
for annot in tqdm(a['annotations'], desc=f"Converting {set} to YOLOv5 format..."):
img_id = annot['image_id']
img_name = a['images'][img_id]['name']
img_label_name = f'{img_name[:-3]}txt'
cls = annot['category_id'] # instance class id
x_center, y_center, width, height = annot['bbox']
x_center = (x_center + width / 2) / 1920.0 # offset and scale
y_center = (y_center + height / 2) / 1200.0 # offset and scale
width /= 1920.0 # scale
height /= 1200.0 # scale
img_dir = set.parents[2] / 'Argoverse-1.1' / 'labels' / a['seq_dirs'][a['images'][annot['image_id']]['sid']]
if not img_dir.exists():
img_dir.mkdir(parents=True, exist_ok=True)
k = str(img_dir / img_label_name)
if k not in labels:
labels[k] = []
labels[k].append(f"{cls} {x_center} {y_center} {width} {height}\n")
for k in labels:
with open(k, "w") as f:
f.writelines(labels[k])
# Download 'https://argoverse-hd.s3.us-east-2.amazonaws.com/Argoverse-HD-Full.zip' (deprecated S3 link)
dir = Path(yaml['path']) # dataset root dir
urls = ['https://drive.google.com/file/d/1st9qW3BeIwQsnR0t8mRpvbsSWIo16ACi/view?usp=drive_link']
print("\n\nWARNING: Argoverse dataset MUST be downloaded manually, autodownload will NOT work.")
print(f"WARNING: Manually download Argoverse dataset '{urls[0]}' to '{dir}' and re-run your command.\n\n")
# download(urls, dir=dir)
# Convert
annotations_dir = 'Argoverse-HD/annotations/'
(dir / 'Argoverse-1.1' / 'tracking').rename(dir / 'Argoverse-1.1' / 'images') # rename 'tracking' to 'images'
for d in "train.json", "val.json":
argoverse2yolo(dir / annotations_dir / d) # convert Argoverse annotations to YOLO labels

36
ultralytics/cfg/datasets/DOTAv1.5.yaml Normal file
View File

@ -0,0 +1,36 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# DOTA 1.5 dataset https://captain-whu.github.io/DOTA/index.html for object detection in aerial images by Wuhan University
# Documentation: https://docs.ultralytics.com/datasets/obb/dota-v2/
# Example usage: yolo train model=yolov8n-obb.pt data=DOTAv1.5.yaml
# parent
# ├── ultralytics
# └── datasets
# └── dota1.5 ← downloads here (2GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/DOTAv1.5 # dataset root dir
train: images/train # train images (relative to 'path') 1411 images
val: images/val # val images (relative to 'path') 458 images
test: images/test # test images (optional) 937 images
# Classes for DOTA 1.5
names:
0: plane
1: ship
2: storage tank
3: baseball diamond
4: tennis court
5: basketball court
6: ground track field
7: harbor
8: bridge
9: large vehicle
10: small vehicle
11: helicopter
12: roundabout
13: soccer ball field
14: swimming pool
15: container crane
# Download script/URL (optional)
download: https://github.com/ultralytics/yolov5/releases/download/v1.0/DOTAv1.5.zip

35
ultralytics/cfg/datasets/DOTAv1.yaml Normal file
View File

@ -0,0 +1,35 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# DOTA 1.0 dataset https://captain-whu.github.io/DOTA/index.html for object detection in aerial images by Wuhan University
# Documentation: https://docs.ultralytics.com/datasets/obb/dota-v2/
# Example usage: yolo train model=yolov8n-obb.pt data=DOTAv1.yaml
# parent
# ├── ultralytics
# └── datasets
# └── dota1 ← downloads here (2GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/DOTAv1 # dataset root dir
train: images/train # train images (relative to 'path') 1411 images
val: images/val # val images (relative to 'path') 458 images
test: images/test # test images (optional) 937 images
# Classes for DOTA 1.0
names:
0: plane
1: ship
2: storage tank
3: baseball diamond
4: tennis court
5: basketball court
6: ground track field
7: harbor
8: bridge
9: large vehicle
10: small vehicle
11: helicopter
12: roundabout
13: soccer ball field
14: swimming pool
# Download script/URL (optional)
download: https://github.com/ultralytics/yolov5/releases/download/v1.0/DOTAv1.zip

53
ultralytics/cfg/datasets/GlobalWheat2020.yaml Normal file
View File

@ -0,0 +1,53 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Global Wheat 2020 dataset https://www.global-wheat.com/ by University of Saskatchewan
# Documentation: https://docs.ultralytics.com/datasets/detect/globalwheat2020/
# Example usage: yolo train data=GlobalWheat2020.yaml
# parent
# ├── ultralytics
# └── datasets
# └── GlobalWheat2020 ← downloads here (7.0 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/GlobalWheat2020 # dataset root dir
train: # train images (relative to 'path') 3422 images
- images/arvalis_1
- images/arvalis_2
- images/arvalis_3
- images/ethz_1
- images/rres_1
- images/inrae_1
- images/usask_1
val: # val images (relative to 'path') 748 images (WARNING: train set contains ethz_1)
- images/ethz_1
test: # test images (optional) 1276 images
- images/utokyo_1
- images/utokyo_2
- images/nau_1
- images/uq_1
# Classes
names:
0: wheat_head
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
from ultralytics.utils.downloads import download
from pathlib import Path
# Download
dir = Path(yaml['path']) # dataset root dir
urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip',
'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip']
download(urls, dir=dir)
# Make Directories
for p in 'annotations', 'images', 'labels':
(dir / p).mkdir(parents=True, exist_ok=True)
# Move
for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \
'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1':
(dir / 'global-wheat-codalab-official' / p).rename(dir / 'images' / p) # move to /images
f = (dir / 'global-wheat-codalab-official' / p).with_suffix('.json') # json file
if f.exists():
f.rename((dir / 'annotations' / p).with_suffix('.json')) # move to /annotations

2024
ultralytics/cfg/datasets/ImageNet.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

442
ultralytics/cfg/datasets/Objects365.yaml Normal file
View File

@ -0,0 +1,442 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Objects365 dataset https://www.objects365.org/ by Megvii
# Documentation: https://docs.ultralytics.com/datasets/detect/objects365/
# Example usage: yolo train data=Objects365.yaml
# parent
# ├── ultralytics
# └── datasets
# └── Objects365 ← downloads here (712 GB = 367G data + 345G zips)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/Objects365 # dataset root dir
train: images/train # train images (relative to 'path') 1742289 images
val: images/val # val images (relative to 'path') 80000 images
test: # test images (optional)
# Classes
names:
0: Person
1: Sneakers
2: Chair
3: Other Shoes
4: Hat
5: Car
6: Lamp
7: Glasses
8: Bottle
9: Desk
10: Cup
11: Street Lights
12: Cabinet/shelf
13: Handbag/Satchel
14: Bracelet
15: Plate
16: Picture/Frame
17: Helmet
18: Book
19: Gloves
20: Storage box
21: Boat
22: Leather Shoes
23: Flower
24: Bench
25: Potted Plant
26: Bowl/Basin
27: Flag
28: Pillow
29: Boots
30: Vase
31: Microphone
32: Necklace
33: Ring
34: SUV
35: Wine Glass
36: Belt
37: Monitor/TV
38: Backpack
39: Umbrella
40: Traffic Light
41: Speaker
42: Watch
43: Tie
44: Trash bin Can
45: Slippers
46: Bicycle
47: Stool
48: Barrel/bucket
49: Van
50: Couch
51: Sandals
52: Basket
53: Drum
54: Pen/Pencil
55: Bus
56: Wild Bird
57: High Heels
58: Motorcycle
59: Guitar
60: Carpet
61: Cell Phone
62: Bread
63: Camera
64: Canned
65: Truck
66: Traffic cone
67: Cymbal
68: Lifesaver
69: Towel
70: Stuffed Toy
71: Candle
72: Sailboat
73: Laptop
74: Awning
75: Bed
76: Faucet
77: Tent
78: Horse
79: Mirror
80: Power outlet
81: Sink
82: Apple
83: Air Conditioner
84: Knife
85: Hockey Stick
86: Paddle
87: Pickup Truck
88: Fork
89: Traffic Sign
90: Balloon
91: Tripod
92: Dog
93: Spoon
94: Clock
95: Pot
96: Cow
97: Cake
98: Dinning Table
99: Sheep
100: Hanger
101: Blackboard/Whiteboard
102: Napkin
103: Other Fish
104: Orange/Tangerine
105: Toiletry
106: Keyboard
107: Tomato
108: Lantern
109: Machinery Vehicle
110: Fan
111: Green Vegetables
112: Banana
113: Baseball Glove
114: Airplane
115: Mouse
116: Train
117: Pumpkin
118: Soccer
119: Skiboard
120: Luggage
121: Nightstand
122: Tea pot
123: Telephone
124: Trolley
125: Head Phone
126: Sports Car
127: Stop Sign
128: Dessert
129: Scooter
130: Stroller
131: Crane
132: Remote
133: Refrigerator
134: Oven
135: Lemon
136: Duck
137: Baseball Bat
138: Surveillance Camera
139: Cat
140: Jug
141: Broccoli
142: Piano
143: Pizza
144: Elephant
145: Skateboard
146: Surfboard
147: Gun
148: Skating and Skiing shoes
149: Gas stove
150: Donut
151: Bow Tie
152: Carrot
153: Toilet
154: Kite
155: Strawberry
156: Other Balls
157: Shovel
158: Pepper
159: Computer Box
160: Toilet Paper
161: Cleaning Products
162: Chopsticks
163: Microwave
164: Pigeon
165: Baseball
166: Cutting/chopping Board
167: Coffee Table
168: Side Table
169: Scissors
170: Marker
171: Pie
172: Ladder
173: Snowboard
174: Cookies
175: Radiator
176: Fire Hydrant
177: Basketball
178: Zebra
179: Grape
180: Giraffe
181: Potato
182: Sausage
183: Tricycle
184: Violin
185: Egg
186: Fire Extinguisher
187: Candy
188: Fire Truck
189: Billiards
190: Converter
191: Bathtub
192: Wheelchair
193: Golf Club
194: Briefcase
195: Cucumber
196: Cigar/Cigarette
197: Paint Brush
198: Pear
199: Heavy Truck
200: Hamburger
201: Extractor
202: Extension Cord
203: Tong
204: Tennis Racket
205: Folder
206: American Football
207: earphone
208: Mask
209: Kettle
210: Tennis
211: Ship
212: Swing
213: Coffee Machine
214: Slide
215: Carriage
216: Onion
217: Green beans
218: Projector
219: Frisbee
220: Washing Machine/Drying Machine
221: Chicken
222: Printer
223: Watermelon
224: Saxophone
225: Tissue
226: Toothbrush
227: Ice cream
228: Hot-air balloon
229: Cello
230: French Fries
231: Scale
232: Trophy
233: Cabbage
234: Hot dog
235: Blender
236: Peach
237: Rice
238: Wallet/Purse
239: Volleyball
240: Deer
241: Goose
242: Tape
243: Tablet
244: Cosmetics
245: Trumpet
246: Pineapple
247: Golf Ball
248: Ambulance
249: Parking meter
250: Mango
251: Key
252: Hurdle
253: Fishing Rod
254: Medal
255: Flute
256: Brush
257: Penguin
258: Megaphone
259: Corn
260: Lettuce
261: Garlic
262: Swan
263: Helicopter
264: Green Onion
265: Sandwich
266: Nuts
267: Speed Limit Sign
268: Induction Cooker
269: Broom
270: Trombone
271: Plum
272: Rickshaw
273: Goldfish
274: Kiwi fruit
275: Router/modem
276: Poker Card
277: Toaster
278: Shrimp
279: Sushi
280: Cheese
281: Notepaper
282: Cherry
283: Pliers
284: CD
285: Pasta
286: Hammer
287: Cue
288: Avocado
289: Hamimelon
290: Flask
291: Mushroom
292: Screwdriver
293: Soap
294: Recorder
295: Bear
296: Eggplant
297: Board Eraser
298: Coconut
299: Tape Measure/Ruler
300: Pig
301: Showerhead
302: Globe
303: Chips
304: Steak
305: Crosswalk Sign
306: Stapler
307: Camel
308: Formula 1
309: Pomegranate
310: Dishwasher
311: Crab
312: Hoverboard
313: Meat ball
314: Rice Cooker
315: Tuba
316: Calculator
317: Papaya
318: Antelope
319: Parrot
320: Seal
321: Butterfly
322: Dumbbell
323: Donkey
324: Lion
325: Urinal
326: Dolphin
327: Electric Drill
328: Hair Dryer
329: Egg tart
330: Jellyfish
331: Treadmill
332: Lighter
333: Grapefruit
334: Game board
335: Mop
336: Radish
337: Baozi
338: Target
339: French
340: Spring Rolls
341: Monkey
342: Rabbit
343: Pencil Case
344: Yak
345: Red Cabbage
346: Binoculars
347: Asparagus
348: Barbell
349: Scallop
350: Noddles
351: Comb
352: Dumpling
353: Oyster
354: Table Tennis paddle
355: Cosmetics Brush/Eyeliner Pencil
356: Chainsaw
357: Eraser
358: Lobster
359: Durian
360: Okra
361: Lipstick
362: Cosmetics Mirror
363: Curling
364: Table Tennis
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
from tqdm import tqdm
from ultralytics.utils.checks import check_requirements
from ultralytics.utils.downloads import download
from ultralytics.utils.ops import xyxy2xywhn
import numpy as np
from pathlib import Path
check_requirements(('pycocotools>=2.0',))
from pycocotools.coco import COCO
# Make Directories
dir = Path(yaml['path']) # dataset root dir
for p in 'images', 'labels':
(dir / p).mkdir(parents=True, exist_ok=True)
for q in 'train', 'val':
(dir / p / q).mkdir(parents=True, exist_ok=True)
# Train, Val Splits
for split, patches in [('train', 50 + 1), ('val', 43 + 1)]:
print(f"Processing {split} in {patches} patches ...")
images, labels = dir / 'images' / split, dir / 'labels' / split
# Download
url = f"https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/{split}/"
if split == 'train':
download([f'{url}zhiyuan_objv2_{split}.tar.gz'], dir=dir) # annotations json
download([f'{url}patch{i}.tar.gz' for i in range(patches)], dir=images, curl=True, threads=8)
elif split == 'val':
download([f'{url}zhiyuan_objv2_{split}.json'], dir=dir) # annotations json
download([f'{url}images/v1/patch{i}.tar.gz' for i in range(15 + 1)], dir=images, curl=True, threads=8)
download([f'{url}images/v2/patch{i}.tar.gz' for i in range(16, patches)], dir=images, curl=True, threads=8)
# Move
for f in tqdm(images.rglob('*.jpg'), desc=f'Moving {split} images'):
f.rename(images / f.name) # move to /images/{split}
# Labels
coco = COCO(dir / f'zhiyuan_objv2_{split}.json')
names = [x["name"] for x in coco.loadCats(coco.getCatIds())]
for cid, cat in enumerate(names):
catIds = coco.getCatIds(catNms=[cat])
imgIds = coco.getImgIds(catIds=catIds)
for im in tqdm(coco.loadImgs(imgIds), desc=f'Class {cid + 1}/{len(names)} {cat}'):
width, height = im["width"], im["height"]
path = Path(im["file_name"]) # image filename
try:
with open(labels / path.with_suffix('.txt').name, 'a') as file:
annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None)
for a in coco.loadAnns(annIds):
x, y, w, h = a['bbox'] # bounding box in xywh (xy top-left corner)
xyxy = np.array([x, y, x + w, y + h])[None] # pixels(1,4)
x, y, w, h = xyxy2xywhn(xyxy, w=width, h=height, clip=True)[0] # normalized and clipped
file.write(f"{cid} {x:.5f} {y:.5f} {w:.5f} {h:.5f}\n")
except Exception as e:
print(e)

57
ultralytics/cfg/datasets/SKU-110K.yaml Normal file
View File

@ -0,0 +1,57 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19 by Trax Retail
# Documentation: https://docs.ultralytics.com/datasets/detect/sku-110k/
# Example usage: yolo train data=SKU-110K.yaml
# parent
# ├── ultralytics
# └── datasets
# └── SKU-110K ← downloads here (13.6 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/SKU-110K # dataset root dir
train: train.txt # train images (relative to 'path') 8219 images
val: val.txt # val images (relative to 'path') 588 images
test: test.txt # test images (optional) 2936 images
# Classes
names:
0: object
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import shutil
from pathlib import Path
import numpy as np
import pandas as pd
from tqdm import tqdm
from ultralytics.utils.downloads import download
from ultralytics.utils.ops import xyxy2xywh
# Download
dir = Path(yaml['path']) # dataset root dir
parent = Path(dir.parent) # download dir
urls = ['http://trax-geometry.s3.amazonaws.com/cvpr_challenge/SKU110K_fixed.tar.gz']
download(urls, dir=parent)
# Rename directories
if dir.exists():
shutil.rmtree(dir)
(parent / 'SKU110K_fixed').rename(dir) # rename dir
(dir / 'labels').mkdir(parents=True, exist_ok=True) # create labels dir
# Convert labels
names = 'image', 'x1', 'y1', 'x2', 'y2', 'class', 'image_width', 'image_height' # column names
for d in 'annotations_train.csv', 'annotations_val.csv', 'annotations_test.csv':
x = pd.read_csv(dir / 'annotations' / d, names=names).values # annotations
images, unique_images = x[:, 0], np.unique(x[:, 0])
with open((dir / d).with_suffix('.txt').__str__().replace('annotations_', ''), 'w') as f:
f.writelines(f'./images/{s}\n' for s in unique_images)
for im in tqdm(unique_images, desc=f'Converting {dir / d}'):
cls = 0 # single-class dataset
with open((dir / 'labels' / im).with_suffix('.txt'), 'a') as f:
for r in x[images == im]:
w, h = r[6], r[7] # image width, height
xywh = xyxy2xywh(np.array([[r[1] / w, r[2] / h, r[3] / w, r[4] / h]]))[0] # instance
f.write(f"{cls} {xywh[0]:.5f} {xywh[1]:.5f} {xywh[2]:.5f} {xywh[3]:.5f}\n") # write label

99
ultralytics/cfg/datasets/VOC.yaml Normal file
View File

@ -0,0 +1,99 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC by University of Oxford
# Documentation: # Documentation: https://docs.ultralytics.com/datasets/detect/voc/
# Example usage: yolo train data=VOC.yaml
# parent
# ├── ultralytics
# └── datasets
# └── VOC ← downloads here (2.8 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/VOC
train: # train images (relative to 'path') 16551 images
- images/train2012
- images/train2007
- images/val2012
- images/val2007
val: # val images (relative to 'path') 4952 images
- images/test2007
test: # test images (optional)
- images/test2007
# Classes
names:
0: aeroplane
1: bicycle
2: bird
3: boat
4: bottle
5: bus
6: car
7: cat
8: chair
9: cow
10: diningtable
11: dog
12: horse
13: motorbike
14: person
15: pottedplant
16: sheep
17: sofa
18: train
19: tvmonitor
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import xml.etree.ElementTree as ET
from tqdm import tqdm
from ultralytics.utils.downloads import download
from pathlib import Path
def convert_label(path, lb_path, year, image_id):
def convert_box(size, box):
dw, dh = 1. / size[0], 1. / size[1]
x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2]
return x * dw, y * dh, w * dw, h * dh
in_file = open(path / f'VOC{year}/Annotations/{image_id}.xml')
out_file = open(lb_path, 'w')
tree = ET.parse(in_file)
root = tree.getroot()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
names = list(yaml['names'].values()) # names list
for obj in root.iter('object'):
cls = obj.find('name').text
if cls in names and int(obj.find('difficult').text) != 1:
xmlbox = obj.find('bndbox')
bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ('xmin', 'xmax', 'ymin', 'ymax')])
cls_id = names.index(cls) # class id
out_file.write(" ".join(str(a) for a in (cls_id, *bb)) + '\n')
# Download
dir = Path(yaml['path']) # dataset root dir
url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
urls = [f'{url}VOCtrainval_06-Nov-2007.zip', # 446MB, 5012 images
f'{url}VOCtest_06-Nov-2007.zip', # 438MB, 4953 images
f'{url}VOCtrainval_11-May-2012.zip'] # 1.95GB, 17126 images
download(urls, dir=dir / 'images', curl=True, threads=3, exist_ok=True) # download and unzip over existing paths (required)
# Convert
path = dir / 'images/VOCdevkit'
for year, image_set in ('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test'):
imgs_path = dir / 'images' / f'{image_set}{year}'
lbs_path = dir / 'labels' / f'{image_set}{year}'
imgs_path.mkdir(exist_ok=True, parents=True)
lbs_path.mkdir(exist_ok=True, parents=True)
with open(path / f'VOC{year}/ImageSets/Main/{image_set}.txt') as f:
image_ids = f.read().strip().split()
for id in tqdm(image_ids, desc=f'{image_set}{year}'):
f = path / f'VOC{year}/JPEGImages/{id}.jpg' # old img path
lb_path = (lbs_path / f.name).with_suffix('.txt') # new label path
f.rename(imgs_path / f.name) # move image
convert_label(path, lb_path, year, id) # convert labels to YOLO format

72
ultralytics/cfg/datasets/VisDrone.yaml Normal file
View File

@ -0,0 +1,72 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset by Tianjin University
# Documentation: https://docs.ultralytics.com/datasets/detect/visdrone/
# Example usage: yolo train data=VisDrone.yaml
# parent
# ├── ultralytics
# └── datasets
# └── VisDrone ← downloads here (2.3 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/VisDrone # dataset root dir
train: VisDrone2019-DET-train/images # train images (relative to 'path') 6471 images
val: VisDrone2019-DET-val/images # val images (relative to 'path') 548 images
test: VisDrone2019-DET-test-dev/images # test images (optional) 1610 images
# Classes
names:
0: pedestrian
1: people
2: bicycle
3: car
4: van
5: truck
6: tricycle
7: awning-tricycle
8: bus
9: motor
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import os
from pathlib import Path
from ultralytics.utils.downloads import download
def visdrone2yolo(dir):
from PIL import Image
from tqdm import tqdm
def convert_box(size, box):
# Convert VisDrone box to YOLO xywh box
dw = 1. / size[0]
dh = 1. / size[1]
return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh
(dir / 'labels').mkdir(parents=True, exist_ok=True) # make labels directory
pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}')
for f in pbar:
img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size
lines = []
with open(f, 'r') as file: # read annotation.txt
for row in [x.split(',') for x in file.read().strip().splitlines()]:
if row[4] == '0': # VisDrone 'ignored regions' class 0
continue
cls = int(row[5]) - 1
box = convert_box(img_size, tuple(map(int, row[:4])))
lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n")
with open(str(f).replace(f'{os.sep}annotations{os.sep}', f'{os.sep}labels{os.sep}'), 'w') as fl:
fl.writelines(lines) # write label.txt
# Download
dir = Path(yaml['path']) # dataset root dir
urls = ['https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-train.zip',
'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-val.zip',
'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-dev.zip',
'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-challenge.zip']
download(urls, dir=dir, curl=True, threads=4)
# Convert
for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev':
visdrone2yolo(dir / d) # convert VisDrone annotations to YOLO labels

24
ultralytics/cfg/datasets/african-wildlife.yaml Normal file
View File

@ -0,0 +1,24 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# African-wildlife dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/african-wildlife/
# Example usage: yolo train data=african-wildlife.yaml
# parent
# ├── ultralytics
# └── datasets
# └── african-wildlife ← downloads here (100 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/african-wildlife # dataset root dir
train: train/images # train images (relative to 'path') 1052 images
val: valid/images # val images (relative to 'path') 225 images
test: test/images # test images (relative to 'path') 227 images
# Classes
names:
0: buffalo
1: elephant
2: rhino
3: zebra
# Download script/URL (optional)
download: https://ultralytics.com/assets/african-wildlife.zip

22
ultralytics/cfg/datasets/brain-tumor.yaml Normal file
View File

@ -0,0 +1,22 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Brain-tumor dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/brain-tumor/
# Example usage: yolo train data=brain-tumor.yaml
# parent
# ├── ultralytics
# └── datasets
# └── brain-tumor ← downloads here (4.05 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/brain-tumor # dataset root dir
train: train/images # train images (relative to 'path') 893 images
val: valid/images # val images (relative to 'path') 223 images
test: # test images (relative to 'path')
# Classes
names:
0: negative
1: positive
# Download script/URL (optional)
download: https://ultralytics.com/assets/brain-tumor.zip

43
ultralytics/cfg/datasets/carparts-seg.yaml Normal file
View File

@ -0,0 +1,43 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Carparts-seg dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/segment/carparts-seg/
# Example usage: yolo train data=carparts-seg.yaml
# parent
# ├── ultralytics
# └── datasets
# └── carparts-seg ← downloads here (132 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/carparts-seg # dataset root dir
train: train/images # train images (relative to 'path') 3516 images
val: valid/images # val images (relative to 'path') 276 images
test: test/images # test images (relative to 'path') 401 images
# Classes
names:
0: back_bumper
1: back_door
2: back_glass
3: back_left_door
4: back_left_light
5: back_light
6: back_right_door
7: back_right_light
8: front_bumper
9: front_door
10: front_glass
11: front_left_door
12: front_left_light
13: front_light
14: front_right_door
15: front_right_light
16: hood
17: left_mirror
18: object
19: right_mirror
20: tailgate
21: trunk
22: wheel
# Download script/URL (optional)
download: https://ultralytics.com/assets/carparts-seg.zip

38
ultralytics/cfg/datasets/coco-pose.yaml Normal file
View File

@ -0,0 +1,38 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# COCO 2017 dataset https://cocodataset.org by Microsoft
# Documentation: https://docs.ultralytics.com/datasets/pose/coco/
# Example usage: yolo train data=coco-pose.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco-pose ← downloads here (20.1 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/coco-pose # dataset root dir
train: train2017.txt # train images (relative to 'path') 118287 images
val: val2017.txt # val images (relative to 'path') 5000 images
test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
# Keypoints
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
# Classes
names:
0: person
# Download script/URL (optional)
download: |
from ultralytics.utils.downloads import download
from pathlib import Path
# Download labels
dir = Path(yaml['path']) # dataset root dir
url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
urls = [url + 'coco2017labels-pose.zip'] # labels
download(urls, dir=dir.parent)
# Download data
urls = ['http://images.cocodataset.org/zips/train2017.zip', # 19G, 118k images
'http://images.cocodataset.org/zips/val2017.zip', # 1G, 5k images
'http://images.cocodataset.org/zips/test2017.zip'] # 7G, 41k images (optional)
download(urls, dir=dir / 'images', threads=3)

114
ultralytics/cfg/datasets/coco.yaml Normal file
View File

@ -0,0 +1,114 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# COCO 2017 dataset https://cocodataset.org by Microsoft
# Documentation: https://docs.ultralytics.com/datasets/detect/coco/
# Example usage: yolo train data=coco.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco ← downloads here (20.1 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/coco # dataset root dir
train: train2017.txt # train images (relative to 'path') 118287 images
val: val2017.txt # val images (relative to 'path') 5000 images
test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: |
from ultralytics.utils.downloads import download
from pathlib import Path
# Download labels
segments = True # segment or box labels
dir = Path(yaml['path']) # dataset root dir
url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
urls = [url + ('coco2017labels-segments.zip' if segments else 'coco2017labels.zip')] # labels
download(urls, dir=dir.parent)
# Download data
urls = ['http://images.cocodataset.org/zips/train2017.zip', # 19G, 118k images
'http://images.cocodataset.org/zips/val2017.zip', # 1G, 5k images
'http://images.cocodataset.org/zips/test2017.zip'] # 7G, 41k images (optional)
download(urls, dir=dir / 'images', threads=3)

100
ultralytics/cfg/datasets/coco128-seg.yaml Normal file
View File

@ -0,0 +1,100 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# COCO128-seg dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/segment/coco/
# Example usage: yolo train data=coco128.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco128-seg ← downloads here (7 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/coco128-seg # dataset root dir
train: images/train2017 # train images (relative to 'path') 128 images
val: images/train2017 # val images (relative to 'path') 128 images
test: # test images (optional)
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: https://ultralytics.com/assets/coco128-seg.zip

100
ultralytics/cfg/datasets/coco128.yaml Normal file
View File

@ -0,0 +1,100 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/coco/
# Example usage: yolo train data=coco128.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco128 ← downloads here (7 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/coco128 # dataset root dir
train: images/train2017 # train images (relative to 'path') 128 images
val: images/train2017 # val images (relative to 'path') 128 images
test: # test images (optional)
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: https://ultralytics.com/assets/coco128.zip

25
ultralytics/cfg/datasets/coco8-pose.yaml Normal file
View File

@ -0,0 +1,25 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# COCO8-pose dataset (first 8 images from COCO train2017) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/pose/coco8-pose/
# Example usage: yolo train data=coco8-pose.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco8-pose ← downloads here (1 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/coco8-pose # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
test: # test images (optional)
# Keypoints
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
# Classes
names:
0: person
# Download script/URL (optional)
download: https://ultralytics.com/assets/coco8-pose.zip

100
ultralytics/cfg/datasets/coco8-seg.yaml Normal file
View File

@ -0,0 +1,100 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# COCO8-seg dataset (first 8 images from COCO train2017) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/segment/coco8-seg/
# Example usage: yolo train data=coco8-seg.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco8-seg ← downloads here (1 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/coco8-seg # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
test: # test images (optional)
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: https://ultralytics.com/assets/coco8-seg.zip

100
ultralytics/cfg/datasets/coco8.yaml Normal file
View File

@ -0,0 +1,100 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# COCO8 dataset (first 8 images from COCO train2017) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/coco8/
# Example usage: yolo train data=coco8.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco8 ← downloads here (1 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/coco8 # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
test: # test images (optional)
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: https://ultralytics.com/assets/coco8.zip

21
ultralytics/cfg/datasets/crack-seg.yaml Normal file
View File

@ -0,0 +1,21 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Crack-seg dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/segment/crack-seg/
# Example usage: yolo train data=crack-seg.yaml
# parent
# ├── ultralytics
# └── datasets
# └── crack-seg ← downloads here (91.2 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/crack-seg # dataset root dir
train: train/images # train images (relative to 'path') 3717 images
val: valid/images # val images (relative to 'path') 112 images
test: test/images # test images (relative to 'path') 200 images
# Classes
names:
0: crack
# Download script/URL (optional)
download: https://ultralytics.com/assets/crack-seg.zip

34
ultralytics/cfg/datasets/dota8.yaml Normal file
View File

@ -0,0 +1,34 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# DOTA8 dataset 8 images from split DOTAv1 dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/obb/dota8/
# Example usage: yolo train model=yolov8n-obb.pt data=dota8.yaml
# parent
# ├── ultralytics
# └── datasets
# └── dota8 ← downloads here (1MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/dota8 # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
# Classes for DOTA 1.0
names:
0: plane
1: ship
2: storage tank
3: baseball diamond
4: tennis court
5: basketball court
6: ground track field
7: harbor
8: bridge
9: large vehicle
10: small vehicle
11: helicopter
12: roundabout
13: soccer ball field
14: swimming pool
# Download script/URL (optional)
download: https://github.com/ultralytics/yolov5/releases/download/v1.0/dota8.zip

660
ultralytics/cfg/datasets/open-images-v7.yaml Normal file
View File

@ -0,0 +1,660 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Open Images v7 dataset https://storage.googleapis.com/openimages/web/index.html by Google
# Documentation: https://docs.ultralytics.com/datasets/detect/open-images-v7/
# Example usage: yolo train data=open-images-v7.yaml
# parent
# ├── ultralytics
# └── datasets
# └── open-images-v7 ← downloads here (561 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/open-images-v7 # dataset root dir
train: images/train # train images (relative to 'path') 1743042 images
val: images/val # val images (relative to 'path') 41620 images
test: # test images (optional)
# Classes
names:
0: Accordion
1: Adhesive tape
2: Aircraft
3: Airplane
4: Alarm clock
5: Alpaca
6: Ambulance
7: Animal
8: Ant
9: Antelope
10: Apple
11: Armadillo
12: Artichoke
13: Auto part
14: Axe
15: Backpack
16: Bagel
17: Baked goods
18: Balance beam
19: Ball
20: Balloon
21: Banana
22: Band-aid
23: Banjo
24: Barge
25: Barrel
26: Baseball bat
27: Baseball glove
28: Bat (Animal)
29: Bathroom accessory
30: Bathroom cabinet
31: Bathtub
32: Beaker
33: Bear
34: Bed
35: Bee
36: Beehive
37: Beer
38: Beetle
39: Bell pepper
40: Belt
41: Bench
42: Bicycle
43: Bicycle helmet
44: Bicycle wheel
45: Bidet
46: Billboard
47: Billiard table
48: Binoculars
49: Bird
50: Blender
51: Blue jay
52: Boat
53: Bomb
54: Book
55: Bookcase
56: Boot
57: Bottle
58: Bottle opener
59: Bow and arrow
60: Bowl
61: Bowling equipment
62: Box
63: Boy
64: Brassiere
65: Bread
66: Briefcase
67: Broccoli
68: Bronze sculpture
69: Brown bear
70: Building
71: Bull
72: Burrito
73: Bus
74: Bust
75: Butterfly
76: Cabbage
77: Cabinetry
78: Cake
79: Cake stand
80: Calculator
81: Camel
82: Camera
83: Can opener
84: Canary
85: Candle
86: Candy
87: Cannon
88: Canoe
89: Cantaloupe
90: Car
91: Carnivore
92: Carrot
93: Cart
94: Cassette deck
95: Castle
96: Cat
97: Cat furniture
98: Caterpillar
99: Cattle
100: Ceiling fan
101: Cello
102: Centipede
103: Chainsaw
104: Chair
105: Cheese
106: Cheetah
107: Chest of drawers
108: Chicken
109: Chime
110: Chisel
111: Chopsticks
112: Christmas tree
113: Clock
114: Closet
115: Clothing
116: Coat
117: Cocktail
118: Cocktail shaker
119: Coconut
120: Coffee
121: Coffee cup
122: Coffee table
123: Coffeemaker
124: Coin
125: Common fig
126: Common sunflower
127: Computer keyboard
128: Computer monitor
129: Computer mouse
130: Container
131: Convenience store
132: Cookie
133: Cooking spray
134: Corded phone
135: Cosmetics
136: Couch
137: Countertop
138: Cowboy hat
139: Crab
140: Cream
141: Cricket ball
142: Crocodile
143: Croissant
144: Crown
145: Crutch
146: Cucumber
147: Cupboard
148: Curtain
149: Cutting board
150: Dagger
151: Dairy Product
152: Deer
153: Desk
154: Dessert
155: Diaper
156: Dice
157: Digital clock
158: Dinosaur
159: Dishwasher
160: Dog
161: Dog bed
162: Doll
163: Dolphin
164: Door
165: Door handle
166: Doughnut
167: Dragonfly
168: Drawer
169: Dress
170: Drill (Tool)
171: Drink
172: Drinking straw
173: Drum
174: Duck
175: Dumbbell
176: Eagle
177: Earrings
178: Egg (Food)
179: Elephant
180: Envelope
181: Eraser
182: Face powder
183: Facial tissue holder
184: Falcon
185: Fashion accessory
186: Fast food
187: Fax
188: Fedora
189: Filing cabinet
190: Fire hydrant
191: Fireplace
192: Fish
193: Flag
194: Flashlight
195: Flower
196: Flowerpot
197: Flute
198: Flying disc
199: Food
200: Food processor
201: Football
202: Football helmet
203: Footwear
204: Fork
205: Fountain
206: Fox
207: French fries
208: French horn
209: Frog
210: Fruit
211: Frying pan
212: Furniture
213: Garden Asparagus
214: Gas stove
215: Giraffe
216: Girl
217: Glasses
218: Glove
219: Goat
220: Goggles
221: Goldfish
222: Golf ball
223: Golf cart
224: Gondola
225: Goose
226: Grape
227: Grapefruit
228: Grinder
229: Guacamole
230: Guitar
231: Hair dryer
232: Hair spray
233: Hamburger
234: Hammer
235: Hamster
236: Hand dryer
237: Handbag
238: Handgun
239: Harbor seal
240: Harmonica
241: Harp
242: Harpsichord
243: Hat
244: Headphones
245: Heater
246: Hedgehog
247: Helicopter
248: Helmet
249: High heels
250: Hiking equipment
251: Hippopotamus
252: Home appliance
253: Honeycomb
254: Horizontal bar
255: Horse
256: Hot dog
257: House
258: Houseplant
259: Human arm
260: Human beard
261: Human body
262: Human ear
263: Human eye
264: Human face
265: Human foot
266: Human hair
267: Human hand
268: Human head
269: Human leg
270: Human mouth
271: Human nose
272: Humidifier
273: Ice cream
274: Indoor rower
275: Infant bed
276: Insect
277: Invertebrate
278: Ipod
279: Isopod
280: Jacket
281: Jacuzzi
282: Jaguar (Animal)
283: Jeans
284: Jellyfish
285: Jet ski
286: Jug
287: Juice
288: Kangaroo
289: Kettle
290: Kitchen & dining room table
291: Kitchen appliance
292: Kitchen knife
293: Kitchen utensil
294: Kitchenware
295: Kite
296: Knife
297: Koala
298: Ladder
299: Ladle
300: Ladybug
301: Lamp
302: Land vehicle
303: Lantern
304: Laptop
305: Lavender (Plant)
306: Lemon
307: Leopard
308: Light bulb
309: Light switch
310: Lighthouse
311: Lily
312: Limousine
313: Lion
314: Lipstick
315: Lizard
316: Lobster
317: Loveseat
318: Luggage and bags
319: Lynx
320: Magpie
321: Mammal
322: Man
323: Mango
324: Maple
325: Maracas
326: Marine invertebrates
327: Marine mammal
328: Measuring cup
329: Mechanical fan
330: Medical equipment
331: Microphone
332: Microwave oven
333: Milk
334: Miniskirt
335: Mirror
336: Missile
337: Mixer
338: Mixing bowl
339: Mobile phone
340: Monkey
341: Moths and butterflies
342: Motorcycle
343: Mouse
344: Muffin
345: Mug
346: Mule
347: Mushroom
348: Musical instrument
349: Musical keyboard
350: Nail (Construction)
351: Necklace
352: Nightstand
353: Oboe
354: Office building
355: Office supplies
356: Orange
357: Organ (Musical Instrument)
358: Ostrich
359: Otter
360: Oven
361: Owl
362: Oyster
363: Paddle
364: Palm tree
365: Pancake
366: Panda
367: Paper cutter
368: Paper towel
369: Parachute
370: Parking meter
371: Parrot
372: Pasta
373: Pastry
374: Peach
375: Pear
376: Pen
377: Pencil case
378: Pencil sharpener
379: Penguin
380: Perfume
381: Person
382: Personal care
383: Personal flotation device
384: Piano
385: Picnic basket
386: Picture frame
387: Pig
388: Pillow
389: Pineapple
390: Pitcher (Container)
391: Pizza
392: Pizza cutter
393: Plant
394: Plastic bag
395: Plate
396: Platter
397: Plumbing fixture
398: Polar bear
399: Pomegranate
400: Popcorn
401: Porch
402: Porcupine
403: Poster
404: Potato
405: Power plugs and sockets
406: Pressure cooker
407: Pretzel
408: Printer
409: Pumpkin
410: Punching bag
411: Rabbit
412: Raccoon
413: Racket
414: Radish
415: Ratchet (Device)
416: Raven
417: Rays and skates
418: Red panda
419: Refrigerator
420: Remote control
421: Reptile
422: Rhinoceros
423: Rifle
424: Ring binder
425: Rocket
426: Roller skates
427: Rose
428: Rugby ball
429: Ruler
430: Salad
431: Salt and pepper shakers
432: Sandal
433: Sandwich
434: Saucer
435: Saxophone
436: Scale
437: Scarf
438: Scissors
439: Scoreboard
440: Scorpion
441: Screwdriver
442: Sculpture
443: Sea lion
444: Sea turtle
445: Seafood
446: Seahorse
447: Seat belt
448: Segway
449: Serving tray
450: Sewing machine
451: Shark
452: Sheep
453: Shelf
454: Shellfish
455: Shirt
456: Shorts
457: Shotgun
458: Shower
459: Shrimp
460: Sink
461: Skateboard
462: Ski
463: Skirt
464: Skull
465: Skunk
466: Skyscraper
467: Slow cooker
468: Snack
469: Snail
470: Snake
471: Snowboard
472: Snowman
473: Snowmobile
474: Snowplow
475: Soap dispenser
476: Sock
477: Sofa bed
478: Sombrero
479: Sparrow
480: Spatula
481: Spice rack
482: Spider
483: Spoon
484: Sports equipment
485: Sports uniform
486: Squash (Plant)
487: Squid
488: Squirrel
489: Stairs
490: Stapler
491: Starfish
492: Stationary bicycle
493: Stethoscope
494: Stool
495: Stop sign
496: Strawberry
497: Street light
498: Stretcher
499: Studio couch
500: Submarine
501: Submarine sandwich
502: Suit
503: Suitcase
504: Sun hat
505: Sunglasses
506: Surfboard
507: Sushi
508: Swan
509: Swim cap
510: Swimming pool
511: Swimwear
512: Sword
513: Syringe
514: Table
515: Table tennis racket
516: Tablet computer
517: Tableware
518: Taco
519: Tank
520: Tap
521: Tart
522: Taxi
523: Tea
524: Teapot
525: Teddy bear
526: Telephone
527: Television
528: Tennis ball
529: Tennis racket
530: Tent
531: Tiara
532: Tick
533: Tie
534: Tiger
535: Tin can
536: Tire
537: Toaster
538: Toilet
539: Toilet paper
540: Tomato
541: Tool
542: Toothbrush
543: Torch
544: Tortoise
545: Towel
546: Tower
547: Toy
548: Traffic light
549: Traffic sign
550: Train
551: Training bench
552: Treadmill
553: Tree
554: Tree house
555: Tripod
556: Trombone
557: Trousers
558: Truck
559: Trumpet
560: Turkey
561: Turtle
562: Umbrella
563: Unicycle
564: Van
565: Vase
566: Vegetable
567: Vehicle
568: Vehicle registration plate
569: Violin
570: Volleyball (Ball)
571: Waffle
572: Waffle iron
573: Wall clock
574: Wardrobe
575: Washing machine
576: Waste container
577: Watch
578: Watercraft
579: Watermelon
580: Weapon
581: Whale
582: Wheel
583: Wheelchair
584: Whisk
585: Whiteboard
586: Willow
587: Window
588: Window blind
589: Wine
590: Wine glass
591: Wine rack
592: Winter melon
593: Wok
594: Woman
595: Wood-burning stove
596: Woodpecker
597: Worm
598: Wrench
599: Zebra
600: Zucchini
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
from ultralytics.utils import LOGGER, SETTINGS, Path, is_ubuntu, get_ubuntu_version
from ultralytics.utils.checks import check_requirements, check_version
check_requirements('fiftyone')
if is_ubuntu() and check_version(get_ubuntu_version(), '>=22.04'):
# Ubuntu>=22.04 patch https://github.com/voxel51/fiftyone/issues/2961#issuecomment-1666519347
check_requirements('fiftyone-db-ubuntu2204')
import fiftyone as fo
import fiftyone.zoo as foz
import warnings
name = 'open-images-v7'
fraction = 1.0 # fraction of full dataset to use
LOGGER.warning('WARNING ⚠️ Open Images V7 dataset requires at least **561 GB of free space. Starting download...')
for split in 'train', 'validation': # 1743042 train, 41620 val images
train = split == 'train'
# Load Open Images dataset
dataset = foz.load_zoo_dataset(name,
split=split,
label_types=['detections'],
dataset_dir=Path(SETTINGS['datasets_dir']) / 'fiftyone' / name,
max_samples=round((1743042 if train else 41620) * fraction))
# Define classes
if train:
classes = dataset.default_classes # all classes
# classes = dataset.distinct('ground_truth.detections.label') # only observed classes
# Export to YOLO format
with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=UserWarning, module="fiftyone.utils.yolo")
dataset.export(export_dir=str(Path(SETTINGS['datasets_dir']) / name),
dataset_type=fo.types.YOLOv5Dataset,
label_field='ground_truth',
split='val' if split == 'validation' else split,
classes=classes,
overwrite=train)

21
ultralytics/cfg/datasets/package-seg.yaml Normal file
View File

@ -0,0 +1,21 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Package-seg dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/segment/package-seg/
# Example usage: yolo train data=package-seg.yaml
# parent
# ├── ultralytics
# └── datasets
# └── package-seg ← downloads here (102 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/package-seg # dataset root dir
train: images/train # train images (relative to 'path') 1920 images
val: images/val # val images (relative to 'path') 89 images
test: test/images # test images (relative to 'path') 188 images
# Classes
names:
0: package
# Download script/URL (optional)
download: https://ultralytics.com/assets/package-seg.zip

24
ultralytics/cfg/datasets/tiger-pose.yaml Normal file
View File

@ -0,0 +1,24 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Tiger Pose dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/pose/tiger-pose/
# Example usage: yolo train data=tiger-pose.yaml
# parent
# ├── ultralytics
# └── datasets
# └── tiger-pose ← downloads here (75.3 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/tiger-pose # dataset root dir
train: train # train images (relative to 'path') 210 images
val: val # val images (relative to 'path') 53 images
# Keypoints
kpt_shape: [12, 2] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
flip_idx: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
# Classes
names:
0: tiger
# Download script/URL (optional)
download: https://ultralytics.com/assets/tiger-pose.zip

152
ultralytics/cfg/datasets/xView.yaml Normal file
View File

@ -0,0 +1,152 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# DIUx xView 2018 Challenge https://challenge.xviewdataset.org by U.S. National Geospatial-Intelligence Agency (NGA)
# -------- DOWNLOAD DATA MANUALLY and jar xf val_images.zip to 'datasets/xView' before running train command! --------
# Documentation: https://docs.ultralytics.com/datasets/detect/xview/
# Example usage: yolo train data=xView.yaml
# parent
# ├── ultralytics
# └── datasets
# └── xView ← downloads here (20.7 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/xView # dataset root dir
train: images/autosplit_train.txt # train images (relative to 'path') 90% of 847 train images
val: images/autosplit_val.txt # train images (relative to 'path') 10% of 847 train images
# Classes
names:
0: Fixed-wing Aircraft
1: Small Aircraft
2: Cargo Plane
3: Helicopter
4: Passenger Vehicle
5: Small Car
6: Bus
7: Pickup Truck
8: Utility Truck
9: Truck
10: Cargo Truck
11: Truck w/Box
12: Truck Tractor
13: Trailer
14: Truck w/Flatbed
15: Truck w/Liquid
16: Crane Truck
17: Railway Vehicle
18: Passenger Car
19: Cargo Car
20: Flat Car
21: Tank car
22: Locomotive
23: Maritime Vessel
24: Motorboat
25: Sailboat
26: Tugboat
27: Barge
28: Fishing Vessel
29: Ferry
30: Yacht
31: Container Ship
32: Oil Tanker
33: Engineering Vehicle
34: Tower crane
35: Container Crane
36: Reach Stacker
37: Straddle Carrier
38: Mobile Crane
39: Dump Truck
40: Haul Truck
41: Scraper/Tractor
42: Front loader/Bulldozer
43: Excavator
44: Cement Mixer
45: Ground Grader
46: Hut/Tent
47: Shed
48: Building
49: Aircraft Hangar
50: Damaged Building
51: Facility
52: Construction Site
53: Vehicle Lot
54: Helipad
55: Storage Tank
56: Shipping container lot
57: Shipping Container
58: Pylon
59: Tower
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import json
import os
from pathlib import Path
import numpy as np
from PIL import Image
from tqdm import tqdm
from ultralytics.data.utils import autosplit
from ultralytics.utils.ops import xyxy2xywhn
def convert_labels(fname=Path('xView/xView_train.geojson')):
# Convert xView geoJSON labels to YOLO format
path = fname.parent
with open(fname) as f:
print(f'Loading {fname}...')
data = json.load(f)
# Make dirs
labels = Path(path / 'labels' / 'train')
os.system(f'rm -rf {labels}')
labels.mkdir(parents=True, exist_ok=True)
# xView classes 11-94 to 0-59
xview_class2index = [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, -1, 3, -1, 4, 5, 6, 7, 8, -1, 9, 10, 11,
12, 13, 14, 15, -1, -1, 16, 17, 18, 19, 20, 21, 22, -1, 23, 24, 25, -1, 26, 27, -1, 28, -1,
29, 30, 31, 32, 33, 34, 35, 36, 37, -1, 38, 39, 40, 41, 42, 43, 44, 45, -1, -1, -1, -1, 46,
47, 48, 49, -1, 50, 51, -1, 52, -1, -1, -1, 53, 54, -1, 55, -1, -1, 56, -1, 57, -1, 58, 59]
shapes = {}
for feature in tqdm(data['features'], desc=f'Converting {fname}'):
p = feature['properties']
if p['bounds_imcoords']:
id = p['image_id']
file = path / 'train_images' / id
if file.exists(): # 1395.tif missing
try:
box = np.array([int(num) for num in p['bounds_imcoords'].split(",")])
assert box.shape[0] == 4, f'incorrect box shape {box.shape[0]}'
cls = p['type_id']
cls = xview_class2index[int(cls)] # xView class to 0-60
assert 59 >= cls >= 0, f'incorrect class index {cls}'
# Write YOLO label
if id not in shapes:
shapes[id] = Image.open(file).size
box = xyxy2xywhn(box[None].astype(np.float), w=shapes[id][0], h=shapes[id][1], clip=True)
with open((labels / id).with_suffix('.txt'), 'a') as f:
f.write(f"{cls} {' '.join(f'{x:.6f}' for x in box[0])}\n") # write label.txt
except Exception as e:
print(f'WARNING: skipping one label for {file}: {e}')
# Download manually from https://challenge.xviewdataset.org
dir = Path(yaml['path']) # dataset root dir
# urls = ['https://d307kc0mrhucc3.cloudfront.net/train_labels.zip', # train labels
# 'https://d307kc0mrhucc3.cloudfront.net/train_images.zip', # 15G, 847 train images
# 'https://d307kc0mrhucc3.cloudfront.net/val_images.zip'] # 5G, 282 val images (no labels)
# download(urls, dir=dir)
# Convert labels
convert_labels(dir / 'xView_train.geojson')
# Move images
images = Path(dir / 'images')
images.mkdir(parents=True, exist_ok=True)
Path(dir / 'train_images').rename(dir / 'images' / 'train')
Path(dir / 'val_images').rename(dir / 'images' / 'val')
# Split
autosplit(dir / 'images' / 'train')

127
ultralytics/cfg/default.yaml Normal file
View File

@ -0,0 +1,127 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Default training settings and hyperparameters for medium-augmentation COCO training
task: detect # (str) YOLO task, i.e. detect, segment, classify, pose
mode: train # (str) YOLO mode, i.e. train, val, predict, export, track, benchmark
# Train settings -------------------------------------------------------------------------------------------------------
model: # (str, optional) path to model file, i.e. yolov8n.pt, yolov8n.yaml
data: # (str, optional) path to data file, i.e. coco128.yaml
epochs: 100 # (int) number of epochs to train for
time: # (float, optional) number of hours to train for, overrides epochs if supplied
patience: 100 # (int) epochs to wait for no observable improvement for early stopping of training
batch: 16 # (int) number of images per batch (-1 for AutoBatch)
imgsz: 640 # (int | list) input images size as int for train and val modes, or list[w,h] for predict and export modes
save: True # (bool) save train checkpoints and predict results
save_period: -1 # (int) Save checkpoint every x epochs (disabled if < 1)
val_period: 1 # (int) Validation every x epochs
cache: False # (bool) True/ram, disk or False. Use cache for data loading
device: # (int | str | list, optional) device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu
workers: 8 # (int) number of worker threads for data loading (per RANK if DDP)
project: # (str, optional) project name
name: # (str, optional) experiment name, results saved to 'project/name' directory
exist_ok: False # (bool) whether to overwrite existing experiment
pretrained: True # (bool | str) whether to use a pretrained model (bool) or a model to load weights from (str)
optimizer: auto # (str) optimizer to use, choices=[SGD, Adam, Adamax, AdamW, NAdam, RAdam, RMSProp, auto]
verbose: True # (bool) whether to print verbose output
seed: 0 # (int) random seed for reproducibility
deterministic: True # (bool) whether to enable deterministic mode
single_cls: False # (bool) train multi-class data as single-class
rect: False # (bool) rectangular training if mode='train' or rectangular validation if mode='val'
cos_lr: False # (bool) use cosine learning rate scheduler
close_mosaic: 10 # (int) disable mosaic augmentation for final epochs (0 to disable)
resume: False # (bool) resume training from last checkpoint
amp: True # (bool) Automatic Mixed Precision (AMP) training, choices=[True, False], True runs AMP check
fraction: 1.0 # (float) dataset fraction to train on (default is 1.0, all images in train set)
profile: False # (bool) profile ONNX and TensorRT speeds during training for loggers
freeze: None # (int | list, optional) freeze first n layers, or freeze list of layer indices during training
multi_scale: False # (bool) Whether to use multiscale during training
# Segmentation
overlap_mask: True # (bool) masks should overlap during training (segment train only)
mask_ratio: 4 # (int) mask downsample ratio (segment train only)
# Classification
dropout: 0.0 # (float) use dropout regularization (classify train only)
# Val/Test settings ----------------------------------------------------------------------------------------------------
val: True # (bool) validate/test during training
split: val # (str) dataset split to use for validation, i.e. 'val', 'test' or 'train'
save_json: False # (bool) save results to JSON file
save_hybrid: False # (bool) save hybrid version of labels (labels + additional predictions)
conf: # (float, optional) object confidence threshold for detection (default 0.25 predict, 0.001 val)
iou: 0.7 # (float) intersection over union (IoU) threshold for NMS
max_det: 300 # (int) maximum number of detections per image
half: False # (bool) use half precision (FP16)
dnn: False # (bool) use OpenCV DNN for ONNX inference
plots: True # (bool) save plots and images during train/val
# Predict settings -----------------------------------------------------------------------------------------------------
source: # (str, optional) source directory for images or videos
vid_stride: 1 # (int) video frame-rate stride
stream_buffer: False # (bool) buffer all streaming frames (True) or return the most recent frame (False)
visualize: False # (bool) visualize model features
augment: False # (bool) apply image augmentation to prediction sources
agnostic_nms: False # (bool) class-agnostic NMS
classes: # (int | list[int], optional) filter results by class, i.e. classes=0, or classes=[0,2,3]
retina_masks: False # (bool) use high-resolution segmentation masks
embed: # (list[int], optional) return feature vectors/embeddings from given layers
# Visualize settings ---------------------------------------------------------------------------------------------------
show: False # (bool) show predicted images and videos if environment allows
save_frames: False # (bool) save predicted individual video frames
save_txt: False # (bool) save results as .txt file
save_conf: False # (bool) save results with confidence scores
save_crop: False # (bool) save cropped images with results
show_labels: True # (bool) show prediction labels, i.e. 'person'
show_conf: True # (bool) show prediction confidence, i.e. '0.99'
show_boxes: True # (bool) show prediction boxes
line_width: # (int, optional) line width of the bounding boxes. Scaled to image size if None.
# Export settings ------------------------------------------------------------------------------------------------------
format: torchscript # (str) format to export to, choices at https://docs.ultralytics.com/modes/export/#export-formats
keras: False # (bool) use Kera=s
optimize: False # (bool) TorchScript: optimize for mobile
int8: False # (bool) CoreML/TF INT8 quantization
dynamic: False # (bool) ONNX/TF/TensorRT: dynamic axes
simplify: False # (bool) ONNX: simplify model using `onnxslim`
opset: # (int, optional) ONNX: opset version
workspace: 4 # (int) TensorRT: workspace size (GB)
nms: False # (bool) CoreML: add NMS
# Hyperparameters ------------------------------------------------------------------------------------------------------
lr0: 0.01 # (float) initial learning rate (i.e. SGD=1E-2, Adam=1E-3)
lrf: 0.01 # (float) final learning rate (lr0 * lrf)
momentum: 0.937 # (float) SGD momentum/Adam beta1
weight_decay: 0.0005 # (float) optimizer weight decay 5e-4
warmup_epochs: 3.0 # (float) warmup epochs (fractions ok)
warmup_momentum: 0.8 # (float) warmup initial momentum
warmup_bias_lr: 0.1 # (float) warmup initial bias lr
box: 7.5 # (float) box loss gain
cls: 0.5 # (float) cls loss gain (scale with pixels)
dfl: 1.5 # (float) dfl loss gain
pose: 12.0 # (float) pose loss gain
kobj: 1.0 # (float) keypoint obj loss gain
label_smoothing: 0.0 # (float) label smoothing (fraction)
nbs: 64 # (int) nominal batch size
hsv_h: 0.015 # (float) image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # (float) image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # (float) image HSV-Value augmentation (fraction)
degrees: 0.0 # (float) image rotation (+/- deg)
translate: 0.1 # (float) image translation (+/- fraction)
scale: 0.5 # (float) image scale (+/- gain)
shear: 0.0 # (float) image shear (+/- deg)
perspective: 0.0 # (float) image perspective (+/- fraction), range 0-0.001
flipud: 0.0 # (float) image flip up-down (probability)
fliplr: 0.5 # (float) image flip left-right (probability)
bgr: 0.0 # (float) image channel BGR (probability)
mosaic: 1.0 # (float) image mosaic (probability)
mixup: 0.0 # (float) image mixup (probability)
copy_paste: 0.0 # (float) segment copy-paste (probability)
auto_augment: randaugment # (str) auto augmentation policy for classification (randaugment, autoaugment, augmix)
erasing: 0.4 # (float) probability of random erasing during classification training (0-1)
crop_fraction: 1.0 # (float) image crop fraction for classification evaluation/inference (0-1)
# Custom config.yaml ---------------------------------------------------------------------------------------------------
cfg: # (str, optional) for overriding defaults.yaml
# Tracker settings ------------------------------------------------------------------------------------------------------
tracker: botsort.yaml # (str) tracker type, choices=[botsort.yaml, bytetrack.yaml]

40
ultralytics/cfg/models/README.md Normal file
View File

@ -0,0 +1,40 @@
## Models
Welcome to the Ultralytics Models directory! Here you will find a wide variety of pre-configured model configuration files (`*.yaml`s) that can be used to create custom YOLO models. The models in this directory have been expertly crafted and fine-tuned by the Ultralytics team to provide the best performance for a wide range of object detection and image segmentation tasks.
These model configurations cover a wide range of scenarios, from simple object detection to more complex tasks like instance segmentation and object tracking. They are also designed to run efficiently on a variety of hardware platforms, from CPUs to GPUs. Whether you are a seasoned machine learning practitioner or just getting started with YOLO, this directory provides a great starting point for your custom model development needs.
To get started, simply browse through the models in this directory and find one that best suits your needs. Once you've selected a model, you can use the provided `*.yaml` file to train and deploy your custom YOLO model with ease. See full details at the Ultralytics [Docs](https://docs.ultralytics.com/models), and if you need help or have any questions, feel free to reach out to the Ultralytics team for support. So, don't wait, start creating your custom YOLO model now!
### Usage
Model `*.yaml` files may be used directly in the Command Line Interface (CLI) with a `yolo` command:
```bash
yolo task=detect mode=train model=yolov8n.yaml data=coco128.yaml epochs=100
```
They may also be used directly in a Python environment, and accepts the same [arguments](https://docs.ultralytics.com/usage/cfg/) as in the CLI example above:
```python
from ultralytics import YOLO
model = YOLO("model.yaml") # build a YOLOv8n model from scratch
# YOLO("model.pt") use pre-trained model if available
model.info() # display model information
model.train(data="coco128.yaml", epochs=100) # train the model
```
## Pre-trained Model Architectures
Ultralytics supports many model architectures. Visit https://docs.ultralytics.com/models to view detailed information and usage. Any of these models can be used by loading their configs or pretrained checkpoints if available.
## Contribute New Models
Have you trained a new YOLO variant or achieved state-of-the-art performance with specific tuning? We'd love to showcase your work in our Models section! Contributions from the community in the form of new models, architectures, or optimizations are highly valued and can significantly enrich our repository.
By contributing to this section, you're helping us offer a wider array of model choices and configurations to the community. It's a fantastic way to share your knowledge and expertise while making the Ultralytics YOLO ecosystem even more versatile.
To get started, please consult our [Contributing Guide](https://docs.ultralytics.com/help/contributing) for step-by-step instructions on how to submit a Pull Request (PR) 🛠️. Your contributions are eagerly awaited!
Let's join hands to extend the range and capabilities of the Ultralytics YOLO models 🙏!

50
ultralytics/cfg/models/rt-detr/rtdetr-l.yaml Normal file
View File

@ -0,0 +1,50 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# RT-DETR-l object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/rtdetr
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
l: [1.00, 1.00, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, HGStem, [32, 48]] # 0-P2/4
- [-1, 6, HGBlock, [48, 128, 3]] # stage 1
- [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8
- [-1, 6, HGBlock, [96, 512, 3]] # stage 2
- [-1, 1, DWConv, [512, 3, 2, 1, False]] # 4-P3/16
- [-1, 6, HGBlock, [192, 1024, 5, True, False]] # cm, c2, k, light, shortcut
- [-1, 6, HGBlock, [192, 1024, 5, True, True]]
- [-1, 6, HGBlock, [192, 1024, 5, True, True]] # stage 3
- [-1, 1, DWConv, [1024, 3, 2, 1, False]] # 8-P4/32
- [-1, 6, HGBlock, [384, 2048, 5, True, False]] # stage 4
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 10 input_proj.2
- [-1, 1, AIFI, [1024, 8]]
- [-1, 1, Conv, [256, 1, 1]] # 12, Y5, lateral_convs.0
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [7, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14 input_proj.1
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [256]] # 16, fpn_blocks.0
- [-1, 1, Conv, [256, 1, 1]] # 17, Y4, lateral_convs.1
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 19 input_proj.0
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (21), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 22, downsample_convs.0
- [[-1, 17], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [256]] # F4 (24), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 25, downsample_convs.1
- [[-1, 12], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [256]] # F5 (27), pan_blocks.1
- [[21, 24, 27], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

42
ultralytics/cfg/models/rt-detr/rtdetr-resnet101.yaml Normal file
View File

@ -0,0 +1,42 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# RT-DETR-ResNet101 object detection model with P3-P5 outputs.
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
l: [1.00, 1.00, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0
- [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1
- [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2
- [-1, 1, ResNetLayer, [512, 256, 2, False, 23]] # 3
- [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5
- [-1, 1, AIFI, [1024, 8]]
- [-1, 1, Conv, [256, 1, 1]] # 7
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [256]] # 11
- [-1, 1, Conv, [256, 1, 1]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0
- [[-1, 12], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1
- [[-1, 7], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1
- [[16, 19, 22], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

42
ultralytics/cfg/models/rt-detr/rtdetr-resnet50.yaml Normal file
View File

@ -0,0 +1,42 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# RT-DETR-ResNet50 object detection model with P3-P5 outputs.
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
l: [1.00, 1.00, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0
- [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1
- [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2
- [-1, 1, ResNetLayer, [512, 256, 2, False, 6]] # 3
- [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5
- [-1, 1, AIFI, [1024, 8]]
- [-1, 1, Conv, [256, 1, 1]] # 7
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [256]] # 11
- [-1, 1, Conv, [256, 1, 1]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0
- [[-1, 12], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1
- [[-1, 7], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1
- [[16, 19, 22], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

54
ultralytics/cfg/models/rt-detr/rtdetr-x.yaml Normal file
View File

@ -0,0 +1,54 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# RT-DETR-x object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/rtdetr
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
x: [1.00, 1.00, 2048]
backbone:
# [from, repeats, module, args]
- [-1, 1, HGStem, [32, 64]] # 0-P2/4
- [-1, 6, HGBlock, [64, 128, 3]] # stage 1
- [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8
- [-1, 6, HGBlock, [128, 512, 3]]
- [-1, 6, HGBlock, [128, 512, 3, False, True]] # 4-stage 2
- [-1, 1, DWConv, [512, 3, 2, 1, False]] # 5-P3/16
- [-1, 6, HGBlock, [256, 1024, 5, True, False]] # cm, c2, k, light, shortcut
- [-1, 6, HGBlock, [256, 1024, 5, True, True]]
- [-1, 6, HGBlock, [256, 1024, 5, True, True]]
- [-1, 6, HGBlock, [256, 1024, 5, True, True]]
- [-1, 6, HGBlock, [256, 1024, 5, True, True]] # 10-stage 3
- [-1, 1, DWConv, [1024, 3, 2, 1, False]] # 11-P4/32
- [-1, 6, HGBlock, [512, 2048, 5, True, False]]
- [-1, 6, HGBlock, [512, 2048, 5, True, True]] # 13-stage 4
head:
- [-1, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 14 input_proj.2
- [-1, 1, AIFI, [2048, 8]]
- [-1, 1, Conv, [384, 1, 1]] # 16, Y5, lateral_convs.0
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [10, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 18 input_proj.1
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [384]] # 20, fpn_blocks.0
- [-1, 1, Conv, [384, 1, 1]] # 21, Y4, lateral_convs.1
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [4, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 23 input_proj.0
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [384]] # X3 (25), fpn_blocks.1
- [-1, 1, Conv, [384, 3, 2]] # 26, downsample_convs.0
- [[-1, 21], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [384]] # F4 (28), pan_blocks.0
- [-1, 1, Conv, [384, 3, 2]] # 29, downsample_convs.1
- [[-1, 16], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [384]] # F5 (31), pan_blocks.1
- [[25, 28, 31], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

40
ultralytics/cfg/models/v10/yolov10b.yaml Normal file
View File

@ -0,0 +1,40 @@
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
b: [0.67, 1.00, 512]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2fCIB, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 1, PSA, [1024]] # 10
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2fCIB, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
- [-1, 1, SCDown, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

40
ultralytics/cfg/models/v10/yolov10l.yaml Normal file
View File

@ -0,0 +1,40 @@
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2fCIB, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 1, PSA, [1024]] # 10
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2fCIB, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
- [-1, 1, SCDown, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

43
ultralytics/cfg/models/v10/yolov10m.yaml Normal file
View File

@ -0,0 +1,43 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2fCIB, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 1, PSA, [1024]] # 10
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
- [-1, 1, SCDown, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

40
ultralytics/cfg/models/v10/yolov10n.yaml Normal file
View File

@ -0,0 +1,40 @@
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 1, PSA, [1024]] # 10
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 19 (P4/16-medium)
- [-1, 1, SCDown, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fCIB, [1024, True, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

39
ultralytics/cfg/models/v10/yolov10s.yaml Normal file
View File

@ -0,0 +1,39 @@
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
s: [0.33, 0.50, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2fCIB, [1024, True, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 1, PSA, [1024]] # 10
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 19 (P4/16-medium)
- [-1, 1, SCDown, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fCIB, [1024, True, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

40
ultralytics/cfg/models/v10/yolov10x.yaml Normal file
View File

@ -0,0 +1,40 @@
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
x: [1.00, 1.25, 512]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2fCIB, [512, True]]
- [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2fCIB, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 1, PSA, [1024]] # 10
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2fCIB, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
- [-1, 1, SCDown, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

46
ultralytics/cfg/models/v3/yolov3-spp.yaml Normal file
View File

@ -0,0 +1,46 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv3-SPP object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/yolov3
# Parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# darknet53 backbone
backbone:
# [from, number, module, args]
- [-1, 1, Conv, [32, 3, 1]] # 0
- [-1, 1, Conv, [64, 3, 2]] # 1-P1/2
- [-1, 1, Bottleneck, [64]]
- [-1, 1, Conv, [128, 3, 2]] # 3-P2/4
- [-1, 2, Bottleneck, [128]]
- [-1, 1, Conv, [256, 3, 2]] # 5-P3/8
- [-1, 8, Bottleneck, [256]]
- [-1, 1, Conv, [512, 3, 2]] # 7-P4/16
- [-1, 8, Bottleneck, [512]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P5/32
- [-1, 4, Bottleneck, [1024]] # 10
# YOLOv3-SPP head
head:
- [-1, 1, Bottleneck, [1024, False]]
- [-1, 1, SPP, [512, [5, 9, 13]]]
- [-1, 1, Conv, [1024, 3, 1]]
- [-1, 1, Conv, [512, 1, 1]]
- [-1, 1, Conv, [1024, 3, 1]] # 15 (P5/32-large)
- [-2, 1, Conv, [256, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P4
- [-1, 1, Bottleneck, [512, False]]
- [-1, 1, Bottleneck, [512, False]]
- [-1, 1, Conv, [256, 1, 1]]
- [-1, 1, Conv, [512, 3, 1]] # 22 (P4/16-medium)
- [-2, 1, Conv, [128, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P3
- [-1, 1, Bottleneck, [256, False]]
- [-1, 2, Bottleneck, [256, False]] # 27 (P3/8-small)
- [[27, 22, 15], 1, Detect, [nc]] # Detect(P3, P4, P5)

37
ultralytics/cfg/models/v3/yolov3-tiny.yaml Normal file
View File

@ -0,0 +1,37 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv3-tiny object detection model with P4-P5 outputs. For details see https://docs.ultralytics.com/models/yolov3
# Parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# YOLOv3-tiny backbone
backbone:
# [from, number, module, args]
- [-1, 1, Conv, [16, 3, 1]] # 0
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 1-P1/2
- [-1, 1, Conv, [32, 3, 1]]
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 3-P2/4
- [-1, 1, Conv, [64, 3, 1]]
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 5-P3/8
- [-1, 1, Conv, [128, 3, 1]]
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 7-P4/16
- [-1, 1, Conv, [256, 3, 1]]
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 9-P5/32
- [-1, 1, Conv, [512, 3, 1]]
- [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]] # 11
- [-1, 1, nn.MaxPool2d, [2, 1, 0]] # 12
# YOLOv3-tiny head
head:
- [-1, 1, Conv, [1024, 3, 1]]
- [-1, 1, Conv, [256, 1, 1]]
- [-1, 1, Conv, [512, 3, 1]] # 15 (P5/32-large)
- [-2, 1, Conv, [128, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P4
- [-1, 1, Conv, [256, 3, 1]] # 19 (P4/16-medium)
- [[19, 15], 1, Detect, [nc]] # Detect(P4, P5)

46
ultralytics/cfg/models/v3/yolov3.yaml Normal file
View File

@ -0,0 +1,46 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv3 object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/yolov3
# Parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# darknet53 backbone
backbone:
# [from, number, module, args]
- [-1, 1, Conv, [32, 3, 1]] # 0
- [-1, 1, Conv, [64, 3, 2]] # 1-P1/2
- [-1, 1, Bottleneck, [64]]
- [-1, 1, Conv, [128, 3, 2]] # 3-P2/4
- [-1, 2, Bottleneck, [128]]
- [-1, 1, Conv, [256, 3, 2]] # 5-P3/8
- [-1, 8, Bottleneck, [256]]
- [-1, 1, Conv, [512, 3, 2]] # 7-P4/16
- [-1, 8, Bottleneck, [512]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P5/32
- [-1, 4, Bottleneck, [1024]] # 10
# YOLOv3 head
head:
- [-1, 1, Bottleneck, [1024, False]]
- [-1, 1, Conv, [512, 1, 1]]
- [-1, 1, Conv, [1024, 3, 1]]
- [-1, 1, Conv, [512, 1, 1]]
- [-1, 1, Conv, [1024, 3, 1]] # 15 (P5/32-large)
- [-2, 1, Conv, [256, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P4
- [-1, 1, Bottleneck, [512, False]]
- [-1, 1, Bottleneck, [512, False]]
- [-1, 1, Conv, [256, 1, 1]]
- [-1, 1, Conv, [512, 3, 1]] # 22 (P4/16-medium)
- [-2, 1, Conv, [128, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P3
- [-1, 1, Bottleneck, [256, False]]
- [-1, 2, Bottleneck, [256, False]] # 27 (P3/8-small)
- [[27, 22, 15], 1, Detect, [nc]] # Detect(P3, P4, P5)

59
ultralytics/cfg/models/v5/yolov5-p6.yaml Normal file
View File

@ -0,0 +1,59 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv5 object detection model with P3-P6 outputs. For details see https://docs.ultralytics.com/models/yolov5
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov5n-p6.yaml' will call yolov5-p6.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 1024]
l: [1.00, 1.00, 1024]
x: [1.33, 1.25, 1024]
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
- [-1, 1, Conv, [64, 6, 2, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C3, [128]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C3, [256]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 9, C3, [512]]
- [-1, 1, Conv, [768, 3, 2]] # 7-P5/32
- [-1, 3, C3, [768]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64
- [-1, 3, C3, [1024]]
- [-1, 1, SPPF, [1024, 5]] # 11
# YOLOv5 v6.0 head
head:
- [-1, 1, Conv, [768, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
- [-1, 3, C3, [768, False]] # 15
- [-1, 1, Conv, [512, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C3, [512, False]] # 19
- [-1, 1, Conv, [256, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C3, [256, False]] # 23 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 20], 1, Concat, [1]] # cat head P4
- [-1, 3, C3, [512, False]] # 26 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 16], 1, Concat, [1]] # cat head P5
- [-1, 3, C3, [768, False]] # 29 (P5/32-large)
- [-1, 1, Conv, [768, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P6
- [-1, 3, C3, [1024, False]] # 32 (P6/64-xlarge)
- [[23, 26, 29, 32], 1, Detect, [nc]] # Detect(P3, P4, P5, P6)

48
ultralytics/cfg/models/v5/yolov5.yaml Normal file
View File

@ -0,0 +1,48 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv5 object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/yolov5
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov5n.yaml' will call yolov5.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 1024]
l: [1.00, 1.00, 1024]
x: [1.33, 1.25, 1024]
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
- [-1, 1, Conv, [64, 6, 2, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C3, [128]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C3, [256]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 9, C3, [512]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C3, [1024]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv5 v6.0 head
head:
- [-1, 1, Conv, [512, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C3, [512, False]] # 13
- [-1, 1, Conv, [256, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C3, [256, False]] # 17 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 14], 1, Concat, [1]] # cat head P4
- [-1, 3, C3, [512, False]] # 20 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C3, [1024, False]] # 23 (P5/32-large)
- [[17, 20, 23], 1, Detect, [nc]] # Detect(P3, P4, P5)

53
ultralytics/cfg/models/v6/yolov6.yaml Normal file
View File

@ -0,0 +1,53 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv6 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/models/yolov6
# Parameters
nc: 80 # number of classes
activation: nn.ReLU() # (optional) model default activation function
scales: # model compound scaling constants, i.e. 'model=yolov6n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv6-3.0s backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 6, Conv, [128, 3, 1]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 12, Conv, [256, 3, 1]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 18, Conv, [512, 3, 1]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 6, Conv, [1024, 3, 1]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv6-3.0s head
head:
- [-1, 1, Conv, [256, 1, 1]]
- [-1, 1, nn.ConvTranspose2d, [256, 2, 2, 0]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 1, Conv, [256, 3, 1]]
- [-1, 9, Conv, [256, 3, 1]] # 14
- [-1, 1, Conv, [128, 1, 1]]
- [-1, 1, nn.ConvTranspose2d, [128, 2, 2, 0]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 1, Conv, [128, 3, 1]]
- [-1, 9, Conv, [128, 3, 1]] # 19
- [-1, 1, Conv, [128, 3, 2]]
- [[-1, 15], 1, Concat, [1]] # cat head P4
- [-1, 1, Conv, [256, 3, 1]]
- [-1, 9, Conv, [256, 3, 1]] # 23
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, Conv, [512, 3, 1]]
- [-1, 9, Conv, [512, 3, 1]] # 27
- [[19, 23, 27], 1, Detect, [nc]] # Detect(P3, P4, P5)

25
ultralytics/cfg/models/v8/yolov8-cls-resnet101.yaml Normal file
View File

@ -0,0 +1,25 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8-cls image classification model. For Usage examples see https://docs.ultralytics.com/tasks/classify
# Parameters
nc: 1000 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 1024]
l: [1.00, 1.00, 1024]
x: [1.00, 1.25, 1024]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0-P1/2
- [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1-P2/4
- [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2-P3/8
- [-1, 1, ResNetLayer, [512, 256, 2, False, 23]] # 3-P4/16
- [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4-P5/32
# YOLOv8.0n head
head:
- [-1, 1, Classify, [nc]] # Classify

25
ultralytics/cfg/models/v8/yolov8-cls-resnet50.yaml Normal file
View File

@ -0,0 +1,25 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8-cls image classification model. For Usage examples see https://docs.ultralytics.com/tasks/classify
# Parameters
nc: 1000 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 1024]
l: [1.00, 1.00, 1024]
x: [1.00, 1.25, 1024]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0-P1/2
- [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1-P2/4
- [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2-P3/8
- [-1, 1, ResNetLayer, [512, 256, 2, False, 6]] # 3-P4/16
- [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4-P5/32
# YOLOv8.0n head
head:
- [-1, 1, Classify, [nc]] # Classify

29
ultralytics/cfg/models/v8/yolov8-cls.yaml Normal file
View File

@ -0,0 +1,29 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8-cls image classification model. For Usage examples see https://docs.ultralytics.com/tasks/classify
# Parameters
nc: 1000 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 1024]
l: [1.00, 1.00, 1024]
x: [1.00, 1.25, 1024]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
# YOLOv8.0n head
head:
- [-1, 1, Classify, [nc]] # Classify

54
ultralytics/cfg/models/v8/yolov8-ghost-p2.yaml Normal file
View File

@ -0,0 +1,54 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P2-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n-ghost-p2 summary: 491 layers, 2033944 parameters, 2033928 gradients, 13.8 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s-ghost-p2 summary: 491 layers, 5562080 parameters, 5562064 gradients, 25.1 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m-ghost-p2 summary: 731 layers, 9031728 parameters, 9031712 gradients, 42.8 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l-ghost-p2 summary: 971 layers, 12214448 parameters, 12214432 gradients, 69.1 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x-ghost-p2 summary: 971 layers, 18664776 parameters, 18664760 gradients, 103.3 GFLOPs
# YOLOv8.0-ghost backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, GhostConv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C3Ghost, [128, True]]
- [-1, 1, GhostConv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C3Ghost, [256, True]]
- [-1, 1, GhostConv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C3Ghost, [512, True]]
- [-1, 1, GhostConv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C3Ghost, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0-ghost-p2 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C3Ghost, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C3Ghost, [256]] # 15 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 2], 1, Concat, [1]] # cat backbone P2
- [-1, 3, C3Ghost, [128]] # 18 (P2/4-xsmall)
- [-1, 1, GhostConv, [128, 3, 2]]
- [[-1, 15], 1, Concat, [1]] # cat head P3
- [-1, 3, C3Ghost, [256]] # 21 (P3/8-small)
- [-1, 1, GhostConv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C3Ghost, [512]] # 24 (P4/16-medium)
- [-1, 1, GhostConv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C3Ghost, [1024]] # 27 (P5/32-large)
- [[18, 21, 24, 27], 1, Detect, [nc]] # Detect(P2, P3, P4, P5)

56
ultralytics/cfg/models/v8/yolov8-ghost-p6.yaml Normal file
View File

@ -0,0 +1,56 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P6 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n-ghost-p6 summary: 529 layers, 2901100 parameters, 2901084 gradients, 5.8 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s-ghost-p6 summary: 529 layers, 9520008 parameters, 9519992 gradients, 16.4 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m-ghost-p6 summary: 789 layers, 18002904 parameters, 18002888 gradients, 34.4 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l-ghost-p6 summary: 1049 layers, 21227584 parameters, 21227568 gradients, 55.3 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x-ghost-p6 summary: 1049 layers, 33057852 parameters, 33057836 gradients, 85.7 GFLOPs
# YOLOv8.0-ghost backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, GhostConv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C3Ghost, [128, True]]
- [-1, 1, GhostConv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C3Ghost, [256, True]]
- [-1, 1, GhostConv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C3Ghost, [512, True]]
- [-1, 1, GhostConv, [768, 3, 2]] # 7-P5/32
- [-1, 3, C3Ghost, [768, True]]
- [-1, 1, GhostConv, [1024, 3, 2]] # 9-P6/64
- [-1, 3, C3Ghost, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 11
# YOLOv8.0-ghost-p6 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
- [-1, 3, C3Ghost, [768]] # 14
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C3Ghost, [512]] # 17
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C3Ghost, [256]] # 20 (P3/8-small)
- [-1, 1, GhostConv, [256, 3, 2]]
- [[-1, 17], 1, Concat, [1]] # cat head P4
- [-1, 3, C3Ghost, [512]] # 23 (P4/16-medium)
- [-1, 1, GhostConv, [512, 3, 2]]
- [[-1, 14], 1, Concat, [1]] # cat head P5
- [-1, 3, C3Ghost, [768]] # 26 (P5/32-large)
- [-1, 1, GhostConv, [768, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P6
- [-1, 3, C3Ghost, [1024]] # 29 (P6/64-xlarge)
- [[20, 23, 26, 29], 1, Detect, [nc]] # Detect(P3, P4, P5, P6)

47
ultralytics/cfg/models/v8/yolov8-ghost.yaml Normal file
View File

@ -0,0 +1,47 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Employs Ghost convolutions and modules proposed in Huawei's GhostNet in https://arxiv.org/abs/1911.11907v2
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n-ghost summary: 403 layers, 1865316 parameters, 1865300 gradients, 5.8 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s-ghost summary: 403 layers, 5960072 parameters, 5960056 gradients, 16.4 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m-ghost summary: 603 layers, 10336312 parameters, 10336296 gradients, 32.7 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l-ghost summary: 803 layers, 14277872 parameters, 14277856 gradients, 53.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x-ghost summary: 803 layers, 22229308 parameters, 22229292 gradients, 83.3 GFLOPs
# YOLOv8.0n-ghost backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, GhostConv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C3Ghost, [128, True]]
- [-1, 1, GhostConv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C3Ghost, [256, True]]
- [-1, 1, GhostConv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C3Ghost, [512, True]]
- [-1, 1, GhostConv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C3Ghost, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C3Ghost, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C3Ghost, [256]] # 15 (P3/8-small)
- [-1, 1, GhostConv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C3Ghost, [512]] # 18 (P4/16-medium)
- [-1, 1, GhostConv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C3Ghost, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

46
ultralytics/cfg/models/v8/yolov8-obb.yaml Normal file
View File

@ -0,0 +1,46 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 Oriented Bounding Boxes (OBB) model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, OBB, [nc, 1]] # OBB(P3, P4, P5)

54
ultralytics/cfg/models/v8/yolov8-p2.yaml Normal file
View File

@ -0,0 +1,54 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P2-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv8.0 backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0-p2 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 2], 1, Concat, [1]] # cat backbone P2
- [-1, 3, C2f, [128]] # 18 (P2/4-xsmall)
- [-1, 1, Conv, [128, 3, 2]]
- [[-1, 15], 1, Concat, [1]] # cat head P3
- [-1, 3, C2f, [256]] # 21 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 24 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 27 (P5/32-large)
- [[18, 21, 24, 27], 1, Detect, [nc]] # Detect(P2, P3, P4, P5)

56
ultralytics/cfg/models/v8/yolov8-p6.yaml Normal file
View File

@ -0,0 +1,56 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P6 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv8.0x6 backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [768, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [768, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 11
# YOLOv8.0x6 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
- [-1, 3, C2, [768, False]] # 14
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2, [512, False]] # 17
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2, [256, False]] # 20 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 17], 1, Concat, [1]] # cat head P4
- [-1, 3, C2, [512, False]] # 23 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 14], 1, Concat, [1]] # cat head P5
- [-1, 3, C2, [768, False]] # 26 (P5/32-large)
- [-1, 1, Conv, [768, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P6
- [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge)
- [[20, 23, 26, 29], 1, Detect, [nc]] # Detect(P3, P4, P5, P6)

57
ultralytics/cfg/models/v8/yolov8-pose-p6.yaml Normal file
View File

@ -0,0 +1,57 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8-pose-p6 keypoints/pose estimation model. For Usage examples see https://docs.ultralytics.com/tasks/pose
# Parameters
nc: 1 # number of classes
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv8.0x6 backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [768, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [768, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 11
# YOLOv8.0x6 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
- [-1, 3, C2, [768, False]] # 14
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2, [512, False]] # 17
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2, [256, False]] # 20 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 17], 1, Concat, [1]] # cat head P4
- [-1, 3, C2, [512, False]] # 23 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 14], 1, Concat, [1]] # cat head P5
- [-1, 3, C2, [768, False]] # 26 (P5/32-large)
- [-1, 1, Conv, [768, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P6
- [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge)
- [[20, 23, 26, 29], 1, Pose, [nc, kpt_shape]] # Pose(P3, P4, P5, P6)

47
ultralytics/cfg/models/v8/yolov8-pose.yaml Normal file
View File

@ -0,0 +1,47 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8-pose keypoints/pose estimation model. For Usage examples see https://docs.ultralytics.com/tasks/pose
# Parameters
nc: 1 # number of classes
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
scales: # model compound scaling constants, i.e. 'model=yolov8n-pose.yaml' will call yolov8-pose.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Pose, [nc, kpt_shape]] # Pose(P3, P4, P5)

46
ultralytics/cfg/models/v8/yolov8-rtdetr.yaml Normal file
View File

@ -0,0 +1,46 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

56
ultralytics/cfg/models/v8/yolov8-seg-p6.yaml Normal file
View File

@ -0,0 +1,56 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8-seg-p6 instance segmentation model. For Usage examples see https://docs.ultralytics.com/tasks/segment
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-seg-p6.yaml' will call yolov8-seg-p6.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv8.0x6 backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [768, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [768, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 11
# YOLOv8.0x6 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
- [-1, 3, C2, [768, False]] # 14
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2, [512, False]] # 17
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2, [256, False]] # 20 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 17], 1, Concat, [1]] # cat head P4
- [-1, 3, C2, [512, False]] # 23 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 14], 1, Concat, [1]] # cat head P5
- [-1, 3, C2, [768, False]] # 26 (P5/32-large)
- [-1, 1, Conv, [768, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P6
- [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge)
- [[20, 23, 26, 29], 1, Segment, [nc, 32, 256]] # Pose(P3, P4, P5, P6)

46
ultralytics/cfg/models/v8/yolov8-seg.yaml Normal file
View File

@ -0,0 +1,46 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8-seg instance segmentation model. For Usage examples see https://docs.ultralytics.com/tasks/segment
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-seg.yaml' will call yolov8-seg.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5)

48
ultralytics/cfg/models/v8/yolov8-world.yaml Normal file
View File

@ -0,0 +1,48 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8-World object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2fAttn, [512, 256, 8]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2fAttn, [256, 128, 4]] # 15 (P3/8-small)
- [[15, 12, 9], 1, ImagePoolingAttn, [256]] # 16 (P3/8-small)
- [15, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fAttn, [512, 256, 8]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fAttn, [1024, 512, 16]] # 22 (P5/32-large)
- [[15, 19, 22], 1, WorldDetect, [nc, 512, False]] # Detect(P3, P4, P5)

46
ultralytics/cfg/models/v8/yolov8-worldv2.yaml Normal file
View File

@ -0,0 +1,46 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8-World-v2 object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2fAttn, [512, 256, 8]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2fAttn, [256, 128, 4]] # 15 (P3/8-small)
- [15, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fAttn, [512, 256, 8]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fAttn, [1024, 512, 16]] # 21 (P5/32-large)
- [[15, 18, 21], 1, WorldDetect, [nc, 512, True]] # Detect(P3, P4, P5)

46
ultralytics/cfg/models/v8/yolov8.yaml Normal file
View File

@ -0,0 +1,46 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

36
ultralytics/cfg/models/v9/yolov9c.yaml Normal file
View File

@ -0,0 +1,36 @@
# YOLOv9
# parameters
nc: 80 # number of classes
# gelan backbone
backbone:
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 1, RepNCSPELAN4, [256, 128, 64, 1]] # 2
- [-1, 1, ADown, [256]] # 3-P3/8
- [-1, 1, RepNCSPELAN4, [512, 256, 128, 1]] # 4
- [-1, 1, ADown, [512]] # 5-P4/16
- [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 6
- [-1, 1, ADown, [512]] # 7-P5/32
- [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 8
- [-1, 1, SPPELAN, [512, 256]] # 9
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 1, RepNCSPELAN4, [256, 256, 128, 1]] # 15 (P3/8-small)
- [-1, 1, ADown, [256]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 18 (P4/16-medium)
- [-1, 1, ADown, [512]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # DDetect(P3, P4, P5)

60
ultralytics/cfg/models/v9/yolov9e.yaml Normal file
View File

@ -0,0 +1,60 @@
# YOLOv9
# parameters
nc: 80 # number of classes
# gelan backbone
backbone:
- [-1, 1, Silence, []]
- [-1, 1, Conv, [64, 3, 2]] # 1-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 2-P2/4
- [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]] # 3
- [-1, 1, ADown, [256]] # 4-P3/8
- [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]] # 5
- [-1, 1, ADown, [512]] # 6-P4/16
- [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 7
- [-1, 1, ADown, [1024]] # 8-P5/32
- [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 9
- [1, 1, CBLinear, [[64]]] # 10
- [3, 1, CBLinear, [[64, 128]]] # 11
- [5, 1, CBLinear, [[64, 128, 256]]] # 12
- [7, 1, CBLinear, [[64, 128, 256, 512]]] # 13
- [9, 1, CBLinear, [[64, 128, 256, 512, 1024]]] # 14
- [0, 1, Conv, [64, 3, 2]] # 15-P1/2
- [[10, 11, 12, 13, 14, -1], 1, CBFuse, [[0, 0, 0, 0, 0]]] # 16
- [-1, 1, Conv, [128, 3, 2]] # 17-P2/4
- [[11, 12, 13, 14, -1], 1, CBFuse, [[1, 1, 1, 1]]] # 18
- [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]] # 19
- [-1, 1, ADown, [256]] # 20-P3/8
- [[12, 13, 14, -1], 1, CBFuse, [[2, 2, 2]]] # 21
- [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]] # 22
- [-1, 1, ADown, [512]] # 23-P4/16
- [[13, 14, -1], 1, CBFuse, [[3, 3]]] # 24
- [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 25
- [-1, 1, ADown, [1024]] # 26-P5/32
- [[14, -1], 1, CBFuse, [[4]]] # 27
- [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 28
- [-1, 1, SPPELAN, [512, 256]] # 29
# gelan head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 25], 1, Concat, [1]] # cat backbone P4
- [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]] # 32
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 22], 1, Concat, [1]] # cat backbone P3
- [-1, 1, RepNCSPELAN4, [256, 256, 128, 2]] # 35 (P3/8-small)
- [-1, 1, ADown, [256]]
- [[-1, 32], 1, Concat, [1]] # cat head P4
- [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]] # 38 (P4/16-medium)
- [-1, 1, ADown, [512]]
- [[-1, 29], 1, Concat, [1]] # cat head P5
- [-1, 1, RepNCSPELAN4, [512, 1024, 512, 2]] # 41 (P5/32-large)
# detect
- [[35, 38, 41], 1, Detect, [nc]] # Detect(P3, P4, P5)

18
ultralytics/cfg/trackers/botsort.yaml Normal file
View File

@ -0,0 +1,18 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Default YOLO tracker settings for BoT-SORT tracker https://github.com/NirAharon/BoT-SORT
tracker_type: botsort # tracker type, ['botsort', 'bytetrack']
track_high_thresh: 0.5 # threshold for the first association
track_low_thresh: 0.1 # threshold for the second association
new_track_thresh: 0.6 # threshold for init new track if the detection does not match any tracks
track_buffer: 30 # buffer to calculate the time when to remove tracks
match_thresh: 0.8 # threshold for matching tracks
# min_box_area: 10 # threshold for min box areas(for tracker evaluation, not used for now)
# mot20: False # for tracker evaluation(not used for now)
# BoT-SORT settings
gmc_method: sparseOptFlow # method of global motion compensation
# ReID model related thresh (not supported yet)
proximity_thresh: 0.5
appearance_thresh: 0.25
with_reid: False

11
ultralytics/cfg/trackers/bytetrack.yaml Normal file
View File

@ -0,0 +1,11 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Default YOLO tracker settings for ByteTrack tracker https://github.com/ifzhang/ByteTrack
tracker_type: bytetrack # tracker type, ['botsort', 'bytetrack']
track_high_thresh: 0.5 # threshold for the first association
track_low_thresh: 0.1 # threshold for the second association
new_track_thresh: 0.6 # threshold for init new track if the detection does not match any tracks
track_buffer: 30 # buffer to calculate the time when to remove tracks
match_thresh: 0.8 # threshold for matching tracks
# min_box_area: 10 # threshold for min box areas(for tracker evaluation, not used for now)
# mot20: False # for tracker evaluation(not used for now)

15
ultralytics/data/__init__.py Normal file
View File

@ -0,0 +1,15 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
from .base import BaseDataset
from .build import build_dataloader, build_yolo_dataset, load_inference_source
from .dataset import ClassificationDataset, SemanticDataset, YOLODataset
__all__ = (
"BaseDataset",
"ClassificationDataset",
"SemanticDataset",
"YOLODataset",
"build_yolo_dataset",
"build_dataloader",
"load_inference_source",
)

BIN
ultralytics/data/__pycache__/__init__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/__init__.cpython-39.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/augment.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/augment.cpython-39.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/base.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/base.cpython-39.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/build.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/build.cpython-39.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/converter.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/converter.cpython-39.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/dataset.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/dataset.cpython-39.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/loaders.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/loaders.cpython-39.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/utils.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/__pycache__/utils.cpython-39.pyc Normal file
View File

Binary file not shown.

50
ultralytics/data/annotator.py Normal file
View File

@ -0,0 +1,50 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
from pathlib import Path
from ultralytics import SAM, YOLO
def auto_annotate(data, det_model="yolov8x.pt", sam_model="sam_b.pt", device="", output_dir=None):
"""
Automatically annotates images using a YOLO object detection model and a SAM segmentation model.
Args:
data (str): Path to a folder containing images to be annotated.
det_model (str, optional): Pre-trained YOLO detection model. Defaults to 'yolov8x.pt'.
sam_model (str, optional): Pre-trained SAM segmentation model. Defaults to 'sam_b.pt'.
device (str, optional): Device to run the models on. Defaults to an empty string (CPU or GPU, if available).
output_dir (str | None | optional): Directory to save the annotated results.
Defaults to a 'labels' folder in the same directory as 'data'.
Example:
```python
from ultralytics.data.annotator import auto_annotate
auto_annotate(data='ultralytics/assets', det_model='yolov8n.pt', sam_model='mobile_sam.pt')
```
"""
det_model = YOLO(det_model)
sam_model = SAM(sam_model)
data = Path(data)
if not output_dir:
output_dir = data.parent / f"{data.stem}_auto_annotate_labels"
Path(output_dir).mkdir(exist_ok=True, parents=True)
det_results = det_model(data, stream=True, device=device)
for result in det_results:
class_ids = result.boxes.cls.int().tolist() # noqa
if len(class_ids):
boxes = result.boxes.xyxy # Boxes object for bbox outputs
sam_results = sam_model(result.orig_img, bboxes=boxes, verbose=False, save=False, device=device)
segments = sam_results[0].masks.xyn # noqa
with open(f"{Path(output_dir) / Path(result.path).stem}.txt", "w") as f:
for i in range(len(segments)):
s = segments[i]
if len(s) == 0:
continue
segment = map(str, segments[i].reshape(-1).tolist())
f.write(f"{class_ids[i]} " + " ".join(segment) + "\n")

1254
ultralytics/data/augment.py Normal file
View File

File diff suppressed because it is too large Load Diff

311
ultralytics/data/base.py Normal file
View File

@ -0,0 +1,311 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
import glob
import math
import os
import random
from copy import deepcopy
from multiprocessing.pool import ThreadPool
from pathlib import Path
from typing import Optional
import cv2
import numpy as np
import psutil
from torch.utils.data import Dataset
from ultralytics.utils import DEFAULT_CFG, LOCAL_RANK, LOGGER, NUM_THREADS, TQDM
from .utils import HELP_URL, IMG_FORMATS
class BaseDataset(Dataset):
"""
Base dataset class for loading and processing image data.
Args:
img_path (str): Path to the folder containing images.
imgsz (int, optional): Image size. Defaults to 640.
cache (bool, optional): Cache images to RAM or disk during training. Defaults to False.
augment (bool, optional): If True, data augmentation is applied. Defaults to True.
hyp (dict, optional): Hyperparameters to apply data augmentation. Defaults to None.
prefix (str, optional): Prefix to print in log messages. Defaults to ''.
rect (bool, optional): If True, rectangular training is used. Defaults to False.
batch_size (int, optional): Size of batches. Defaults to None.
stride (int, optional): Stride. Defaults to 32.
pad (float, optional): Padding. Defaults to 0.0.
single_cls (bool, optional): If True, single class training is used. Defaults to False.
classes (list): List of included classes. Default is None.
fraction (float): Fraction of dataset to utilize. Default is 1.0 (use all data).
Attributes:
im_files (list): List of image file paths.
labels (list): List of label data dictionaries.
ni (int): Number of images in the dataset.
ims (list): List of loaded images.
npy_files (list): List of numpy file paths.
transforms (callable): Image transformation function.
"""
def __init__(
self,
img_path,
imgsz=640,
cache=False,
augment=True,
hyp=DEFAULT_CFG,
prefix="",
rect=False,
batch_size=16,
stride=32,
pad=0.5,
single_cls=False,
classes=None,
fraction=1.0,
):
"""Initialize BaseDataset with given configuration and options."""
super().__init__()
self.img_path = img_path
self.imgsz = imgsz
self.augment = augment
self.single_cls = single_cls
self.prefix = prefix
self.fraction = fraction
self.im_files = self.get_img_files(self.img_path)
self.labels = self.get_labels()
self.update_labels(include_class=classes) # single_cls and include_class
self.ni = len(self.labels) # number of images
self.rect = rect
self.batch_size = batch_size
self.stride = stride
self.pad = pad
if self.rect:
assert self.batch_size is not None
self.set_rectangle()
# Buffer thread for mosaic images
self.buffer = [] # buffer size = batch size
self.max_buffer_length = min((self.ni, self.batch_size * 8, 1000)) if self.augment else 0
# Cache images
if cache == "ram" and not self.check_cache_ram():
cache = False
self.ims, self.im_hw0, self.im_hw = [None] * self.ni, [None] * self.ni, [None] * self.ni
self.npy_files = [Path(f).with_suffix(".npy") for f in self.im_files]
if cache:
self.cache_images(cache)
# Transforms
self.transforms = self.build_transforms(hyp=hyp)
def get_img_files(self, img_path):
"""Read image files."""
try:
f = [] # image files
for p in img_path if isinstance(img_path, list) else [img_path]:
p = Path(p) # os-agnostic
if p.is_dir(): # dir
f += glob.glob(str(p / "**" / "*.*"), recursive=True)
# F = list(p.rglob('*.*')) # pathlib
elif p.is_file(): # file
with open(p) as t:
t = t.read().strip().splitlines()
parent = str(p.parent) + os.sep
f += [x.replace("./", parent) if x.startswith("./") else x for x in t] # local to global path
# F += [p.parent / x.lstrip(os.sep) for x in t] # local to global path (pathlib)
else:
raise FileNotFoundError(f"{self.prefix}{p} does not exist")
im_files = sorted(x.replace("/", os.sep) for x in f if x.split(".")[-1].lower() in IMG_FORMATS)
# self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS]) # pathlib
assert im_files, f"{self.prefix}No images found in {img_path}"
except Exception as e:
raise FileNotFoundError(f"{self.prefix}Error loading data from {img_path}\n{HELP_URL}") from e
if self.fraction < 1:
# im_files = im_files[: round(len(im_files) * self.fraction)]
num_elements_to_select = round(len(im_files) * self.fraction)
im_files = random.sample(im_files, num_elements_to_select)
return im_files
def update_labels(self, include_class: Optional[list]):
"""Update labels to include only these classes (optional)."""
include_class_array = np.array(include_class).reshape(1, -1)
for i in range(len(self.labels)):
if include_class is not None:
cls = self.labels[i]["cls"]
bboxes = self.labels[i]["bboxes"]
segments = self.labels[i]["segments"]
keypoints = self.labels[i]["keypoints"]
j = (cls == include_class_array).any(1)
self.labels[i]["cls"] = cls[j]
self.labels[i]["bboxes"] = bboxes[j]
if segments:
self.labels[i]["segments"] = [segments[si] for si, idx in enumerate(j) if idx]
if keypoints is not None:
self.labels[i]["keypoints"] = keypoints[j]
if self.single_cls:
self.labels[i]["cls"][:, 0] = 0
def load_image(self, i, rect_mode=True):
"""Loads 1 image from dataset index 'i', returns (im, resized hw)."""
im, f, fn = self.ims[i], self.im_files[i], self.npy_files[i]
if im is None: # not cached in RAM
if fn.exists(): # load npy
try:
im = np.load(fn)
except Exception as e:
LOGGER.warning(f"{self.prefix}WARNING ⚠️ Removing corrupt *.npy image file {fn} due to: {e}")
Path(fn).unlink(missing_ok=True)
im = cv2.imread(f) # BGR
else: # read image
im = cv2.imread(f) # BGR
if im is None:
raise FileNotFoundError(f"Image Not Found {f}")
h0, w0 = im.shape[:2] # orig hw
if rect_mode: # resize long side to imgsz while maintaining aspect ratio
r = self.imgsz / max(h0, w0) # ratio
if r != 1: # if sizes are not equal
w, h = (min(math.ceil(w0 * r), self.imgsz), min(math.ceil(h0 * r), self.imgsz))
im = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR)
elif not (h0 == w0 == self.imgsz): # resize by stretching image to square imgsz
im = cv2.resize(im, (self.imgsz, self.imgsz), interpolation=cv2.INTER_LINEAR)
# Add to buffer if training with augmentations
if self.augment:
self.ims[i], self.im_hw0[i], self.im_hw[i] = im, (h0, w0), im.shape[:2] # im, hw_original, hw_resized
self.buffer.append(i)
if len(self.buffer) >= self.max_buffer_length:
j = self.buffer.pop(0)
self.ims[j], self.im_hw0[j], self.im_hw[j] = None, None, None
return im, (h0, w0), im.shape[:2]
return self.ims[i], self.im_hw0[i], self.im_hw[i]
def cache_images(self, cache):
"""Cache images to memory or disk."""
b, gb = 0, 1 << 30 # bytes of cached images, bytes per gigabytes
fcn = self.cache_images_to_disk if cache == "disk" else self.load_image
with ThreadPool(NUM_THREADS) as pool:
results = pool.imap(fcn, range(self.ni))
pbar = TQDM(enumerate(results), total=self.ni, disable=LOCAL_RANK > 0)
for i, x in pbar:
if cache == "disk":
b += self.npy_files[i].stat().st_size
else: # 'ram'
self.ims[i], self.im_hw0[i], self.im_hw[i] = x # im, hw_orig, hw_resized = load_image(self, i)
b += self.ims[i].nbytes
pbar.desc = f"{self.prefix}Caching images ({b / gb:.1f}GB {cache})"
pbar.close()
def cache_images_to_disk(self, i):
"""Saves an image as an *.npy file for faster loading."""
f = self.npy_files[i]
if not f.exists():
np.save(f.as_posix(), cv2.imread(self.im_files[i]), allow_pickle=False)
def check_cache_ram(self, safety_margin=0.5):
"""Check image caching requirements vs available memory."""
b, gb = 0, 1 << 30 # bytes of cached images, bytes per gigabytes
n = min(self.ni, 30) # extrapolate from 30 random images
for _ in range(n):
im = cv2.imread(random.choice(self.im_files)) # sample image
ratio = self.imgsz / max(im.shape[0], im.shape[1]) # max(h, w) # ratio
b += im.nbytes * ratio**2
mem_required = b * self.ni / n * (1 + safety_margin) # GB required to cache dataset into RAM
mem = psutil.virtual_memory()
cache = mem_required < mem.available # to cache or not to cache, that is the question
if not cache:
LOGGER.info(
f'{self.prefix}{mem_required / gb:.1f}GB RAM required to cache images '
f'with {int(safety_margin * 100)}% safety margin but only '
f'{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, '
f"{'caching images ✅' if cache else 'not caching images ⚠️'}"
)
return cache
def set_rectangle(self):
"""Sets the shape of bounding boxes for YOLO detections as rectangles."""
bi = np.floor(np.arange(self.ni) / self.batch_size).astype(int) # batch index
nb = bi[-1] + 1 # number of batches
s = np.array([x.pop("shape") for x in self.labels]) # hw
ar = s[:, 0] / s[:, 1] # aspect ratio
irect = ar.argsort()
self.im_files = [self.im_files[i] for i in irect]
self.labels = [self.labels[i] for i in irect]
ar = ar[irect]
# Set training image shapes
shapes = [[1, 1]] * nb
for i in range(nb):
ari = ar[bi == i]
mini, maxi = ari.min(), ari.max()
if maxi < 1:
shapes[i] = [maxi, 1]
elif mini > 1:
shapes[i] = [1, 1 / mini]
self.batch_shapes = np.ceil(np.array(shapes) * self.imgsz / self.stride + self.pad).astype(int) * self.stride
self.batch = bi # batch index of image
def __getitem__(self, index):
"""Returns transformed label information for given index."""
return self.transforms(self.get_image_and_label(index))
def get_image_and_label(self, index):
"""Get and return label information from the dataset."""
label = deepcopy(self.labels[index]) # requires deepcopy() https://github.com/ultralytics/ultralytics/pull/1948
label.pop("shape", None) # shape is for rect, remove it
label["img"], label["ori_shape"], label["resized_shape"] = self.load_image(index)
label["ratio_pad"] = (
label["resized_shape"][0] / label["ori_shape"][0],
label["resized_shape"][1] / label["ori_shape"][1],
) # for evaluation
if self.rect:
label["rect_shape"] = self.batch_shapes[self.batch[index]]
return self.update_labels_info(label)
def __len__(self):
"""Returns the length of the labels list for the dataset."""
return len(self.labels)
def update_labels_info(self, label):
"""Custom your label format here."""
return label
def build_transforms(self, hyp=None):
"""
Users can customize augmentations here.
Example:
```python
if self.augment:
# Training transforms
return Compose([])
else:
# Val transforms
return Compose([])
```
"""
raise NotImplementedError
def get_labels(self):
"""
Users can customize their own format here.
Note:
Ensure output is a dictionary with the following keys:
```python
dict(
im_file=im_file,
shape=shape, # format: (height, width)
cls=cls,
bboxes=bboxes, # xywh
segments=segments, # xy
keypoints=keypoints, # xy
normalized=True, # or False
bbox_format="xyxy", # or xywh, ltwh
)
```
"""
raise NotImplementedError

186
ultralytics/data/build.py Normal file
View File

@ -0,0 +1,186 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
import os
import random
from pathlib import Path
import numpy as np
import torch
from PIL import Image
from torch.utils.data import dataloader, distributed
from ultralytics.data.loaders import (
LOADERS,
LoadImagesAndVideos,
LoadPilAndNumpy,
LoadScreenshots,
LoadStreams,
LoadTensor,
SourceTypes,
autocast_list,
)
from ultralytics.data.utils import IMG_FORMATS, VID_FORMATS
from ultralytics.utils import RANK, colorstr
from ultralytics.utils.checks import check_file
from .dataset import YOLODataset
from .utils import PIN_MEMORY
class InfiniteDataLoader(dataloader.DataLoader):
"""
Dataloader that reuses workers.
Uses same syntax as vanilla DataLoader.
"""
def __init__(self, *args, **kwargs):
"""Dataloader that infinitely recycles workers, inherits from DataLoader."""
super().__init__(*args, **kwargs)
object.__setattr__(self, "batch_sampler", _RepeatSampler(self.batch_sampler))
self.iterator = super().__iter__()
def __len__(self):
"""Returns the length of the batch sampler's sampler."""
return len(self.batch_sampler.sampler)
def __iter__(self):
"""Creates a sampler that repeats indefinitely."""
for _ in range(len(self)):
yield next(self.iterator)
def reset(self):
"""
Reset iterator.
This is useful when we want to modify settings of dataset while training.
"""
self.iterator = self._get_iterator()
class _RepeatSampler:
"""
Sampler that repeats forever.
Args:
sampler (Dataset.sampler): The sampler to repeat.
"""
def __init__(self, sampler):
"""Initializes an object that repeats a given sampler indefinitely."""
self.sampler = sampler
def __iter__(self):
"""Iterates over the 'sampler' and yields its contents."""
while True:
yield from iter(self.sampler)
def seed_worker(worker_id): # noqa
"""Set dataloader worker seed https://pytorch.org/docs/stable/notes/randomness.html#dataloader."""
worker_seed = torch.initial_seed() % 2**32
np.random.seed(worker_seed)
random.seed(worker_seed)
def build_yolo_dataset(cfg, img_path, batch, data, mode="train", rect=False, stride=32):
"""Build YOLO Dataset."""
return YOLODataset(
img_path=img_path,
imgsz=cfg.imgsz,
batch_size=batch,
augment=mode == "train", # augmentation
hyp=cfg, # TODO: probably add a get_hyps_from_cfg function
rect=cfg.rect or rect, # rectangular batches
cache=cfg.cache or None,
single_cls=cfg.single_cls or False,
stride=int(stride),
pad=0.0 if mode == "train" else 0.5,
prefix=colorstr(f"{mode}: "),
task=cfg.task,
classes=cfg.classes,
data=data,
fraction=cfg.fraction if mode == "train" else 1.0,
)
def build_dataloader(dataset, batch, workers, shuffle=True, rank=-1):
"""Return an InfiniteDataLoader or DataLoader for training or validation set."""
batch = min(batch, len(dataset))
nd = torch.cuda.device_count() # number of CUDA devices
nw = min([os.cpu_count() // max(nd, 1), workers]) # number of workers
sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle)
generator = torch.Generator()
generator.manual_seed(6148914691236517205 + RANK)
return InfiniteDataLoader(
dataset=dataset,
batch_size=batch,
shuffle=shuffle and sampler is None,
num_workers=nw,
sampler=sampler,
pin_memory=PIN_MEMORY,
collate_fn=getattr(dataset, "collate_fn", None),
worker_init_fn=seed_worker,
generator=generator,
)
def check_source(source):
"""Check source type and return corresponding flag values."""
webcam, screenshot, from_img, in_memory, tensor = False, False, False, False, False
if isinstance(source, (str, int, Path)): # int for local usb camera
source = str(source)
is_file = Path(source).suffix[1:] in (IMG_FORMATS | VID_FORMATS)
is_url = source.lower().startswith(("https://", "http://", "rtsp://", "rtmp://", "tcp://"))
webcam = source.isnumeric() or source.endswith(".streams") or (is_url and not is_file)
screenshot = source.lower() == "screen"
if is_url and is_file:
source = check_file(source) # download
elif isinstance(source, LOADERS):
in_memory = True
elif isinstance(source, (list, tuple)):
source = autocast_list(source) # convert all list elements to PIL or np arrays
from_img = True
elif isinstance(source, (Image.Image, np.ndarray)):
from_img = True
elif isinstance(source, torch.Tensor):
tensor = True
else:
raise TypeError("Unsupported image type. For supported types see https://docs.ultralytics.com/modes/predict")
return source, webcam, screenshot, from_img, in_memory, tensor
def load_inference_source(source=None, batch=1, vid_stride=1, buffer=False):
"""
Loads an inference source for object detection and applies necessary transformations.
Args:
source (str, Path, Tensor, PIL.Image, np.ndarray): The input source for inference.
batch (int, optional): Batch size for dataloaders. Default is 1.
vid_stride (int, optional): The frame interval for video sources. Default is 1.
buffer (bool, optional): Determined whether stream frames will be buffered. Default is False.
Returns:
dataset (Dataset): A dataset object for the specified input source.
"""
source, stream, screenshot, from_img, in_memory, tensor = check_source(source)
source_type = source.source_type if in_memory else SourceTypes(stream, screenshot, from_img, tensor)
# Dataloader
if tensor:
dataset = LoadTensor(source)
elif in_memory:
dataset = source
elif stream:
dataset = LoadStreams(source, vid_stride=vid_stride, buffer=buffer)
elif screenshot:
dataset = LoadScreenshots(source)
elif from_img:
dataset = LoadPilAndNumpy(source)
else:
dataset = LoadImagesAndVideos(source, batch=batch, vid_stride=vid_stride)
# Attach source types to the dataset
setattr(dataset, "source_type", source_type)
return dataset

542
ultralytics/data/converter.py Normal file
View File

@ -0,0 +1,542 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
import json
from collections import defaultdict
from pathlib import Path
import cv2
import numpy as np
from ultralytics.utils import LOGGER, TQDM
from ultralytics.utils.files import increment_path
def coco91_to_coco80_class():
"""
Converts 91-index COCO class IDs to 80-index COCO class IDs.
Returns:
(list): A list of 91 class IDs where the index represents the 80-index class ID and the value is the
corresponding 91-index class ID.
"""
return [
0,
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
None,
11,
12,
13,
14,
15,
16,
17,
18,
19,
20,
21,
22,
23,
None,
24,
25,
None,
None,
26,
27,
28,
29,
30,
31,
32,
33,
34,
35,
36,
37,
38,
39,
None,
40,
41,
42,
43,
44,
45,
46,
47,
48,
49,
50,
51,
52,
53,
54,
55,
56,
57,
58,
59,
None,
60,
None,
None,
61,
None,
62,
63,
64,
65,
66,
67,
68,
69,
70,
71,
72,
None,
73,
74,
75,
76,
77,
78,
79,
None,
]
def coco80_to_coco91_class():
"""
Converts 80-index (val2014) to 91-index (paper).
For details see https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/.
Example:
```python
import numpy as np
a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n')
b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n')
x1 = [list(a[i] == b).index(True) + 1 for i in range(80)] # darknet to coco
x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)] # coco to darknet
```
"""
return [
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11,
13,
14,
15,
16,
17,
18,
19,
20,
21,
22,
23,
24,
25,
27,
28,
31,
32,
33,
34,
35,
36,
37,
38,
39,
40,
41,
42,
43,
44,
46,
47,
48,
49,
50,
51,
52,
53,
54,
55,
56,
57,
58,
59,
60,
61,
62,
63,
64,
65,
67,
70,
72,
73,
74,
75,
76,
77,
78,
79,
80,
81,
82,
84,
85,
86,
87,
88,
89,
90,
]
def convert_coco(
labels_dir="../coco/annotations/",
save_dir="coco_converted/",
use_segments=False,
use_keypoints=False,
cls91to80=True,
):
"""
Converts COCO dataset annotations to a YOLO annotation format suitable for training YOLO models.
Args:
labels_dir (str, optional): Path to directory containing COCO dataset annotation files.
save_dir (str, optional): Path to directory to save results to.
use_segments (bool, optional): Whether to include segmentation masks in the output.
use_keypoints (bool, optional): Whether to include keypoint annotations in the output.
cls91to80 (bool, optional): Whether to map 91 COCO class IDs to the corresponding 80 COCO class IDs.
Example:
```python
from ultralytics.data.converter import convert_coco
convert_coco('../datasets/coco/annotations/', use_segments=True, use_keypoints=False, cls91to80=True)
```
Output:
Generates output files in the specified output directory.
"""
# Create dataset directory
save_dir = increment_path(save_dir) # increment if save directory already exists
for p in save_dir / "labels", save_dir / "images":
p.mkdir(parents=True, exist_ok=True) # make dir
# Convert classes
coco80 = coco91_to_coco80_class()
# Import json
for json_file in sorted(Path(labels_dir).resolve().glob("*.json")):
fn = Path(save_dir) / "labels" / json_file.stem.replace("instances_", "") # folder name
fn.mkdir(parents=True, exist_ok=True)
with open(json_file) as f:
data = json.load(f)
# Create image dict
images = {f'{x["id"]:d}': x for x in data["images"]}
# Create image-annotations dict
imgToAnns = defaultdict(list)
for ann in data["annotations"]:
imgToAnns[ann["image_id"]].append(ann)
# Write labels file
for img_id, anns in TQDM(imgToAnns.items(), desc=f"Annotations {json_file}"):
img = images[f"{img_id:d}"]
h, w, f = img["height"], img["width"], img["file_name"]
bboxes = []
segments = []
keypoints = []
for ann in anns:
if ann["iscrowd"]:
continue
# The COCO box format is [top left x, top left y, width, height]
box = np.array(ann["bbox"], dtype=np.float64)
box[:2] += box[2:] / 2 # xy top-left corner to center
box[[0, 2]] /= w # normalize x
box[[1, 3]] /= h # normalize y
if box[2] <= 0 or box[3] <= 0: # if w <= 0 and h <= 0
continue
cls = coco80[ann["category_id"] - 1] if cls91to80 else ann["category_id"] - 1 # class
box = [cls] + box.tolist()
if box not in bboxes:
bboxes.append(box)
if use_segments and ann.get("segmentation") is not None:
if len(ann["segmentation"]) == 0:
segments.append([])
continue
elif len(ann["segmentation"]) > 1:
s = merge_multi_segment(ann["segmentation"])
s = (np.concatenate(s, axis=0) / np.array([w, h])).reshape(-1).tolist()
else:
s = [j for i in ann["segmentation"] for j in i] # all segments concatenated
s = (np.array(s).reshape(-1, 2) / np.array([w, h])).reshape(-1).tolist()
s = [cls] + s
segments.append(s)
if use_keypoints and ann.get("keypoints") is not None:
keypoints.append(
box + (np.array(ann["keypoints"]).reshape(-1, 3) / np.array([w, h, 1])).reshape(-1).tolist()
)
# Write
with open((fn / f).with_suffix(".txt"), "a") as file:
for i in range(len(bboxes)):
if use_keypoints:
line = (*(keypoints[i]),) # cls, box, keypoints
else:
line = (
*(segments[i] if use_segments and len(segments[i]) > 0 else bboxes[i]),
) # cls, box or segments
file.write(("%g " * len(line)).rstrip() % line + "\n")
LOGGER.info(f"COCO data converted successfully.\nResults saved to {save_dir.resolve()}")
def convert_dota_to_yolo_obb(dota_root_path: str):
"""
Converts DOTA dataset annotations to YOLO OBB (Oriented Bounding Box) format.
The function processes images in the 'train' and 'val' folders of the DOTA dataset. For each image, it reads the
associated label from the original labels directory and writes new labels in YOLO OBB format to a new directory.
Args:
dota_root_path (str): The root directory path of the DOTA dataset.
Example:
```python
from ultralytics.data.converter import convert_dota_to_yolo_obb
convert_dota_to_yolo_obb('path/to/DOTA')
```
Notes:
The directory structure assumed for the DOTA dataset:
- DOTA
├─ images
│ ├─ train
│ └─ val
└─ labels
├─ train_original
└─ val_original
After execution, the function will organize the labels into:
- DOTA
└─ labels
├─ train
└─ val
"""
dota_root_path = Path(dota_root_path)
# Class names to indices mapping
class_mapping = {
"plane": 0,
"ship": 1,
"storage-tank": 2,
"baseball-diamond": 3,
"tennis-court": 4,
"basketball-court": 5,
"ground-track-field": 6,
"harbor": 7,
"bridge": 8,
"large-vehicle": 9,
"small-vehicle": 10,
"helicopter": 11,
"roundabout": 12,
"soccer-ball-field": 13,
"swimming-pool": 14,
"container-crane": 15,
"airport": 16,
"helipad": 17,
}
def convert_label(image_name, image_width, image_height, orig_label_dir, save_dir):
"""Converts a single image's DOTA annotation to YOLO OBB format and saves it to a specified directory."""
orig_label_path = orig_label_dir / f"{image_name}.txt"
save_path = save_dir / f"{image_name}.txt"
with orig_label_path.open("r") as f, save_path.open("w") as g:
lines = f.readlines()
for line in lines:
parts = line.strip().split()
if len(parts) < 9:
continue
class_name = parts[8]
class_idx = class_mapping[class_name]
coords = [float(p) for p in parts[:8]]
normalized_coords = [
coords[i] / image_width if i % 2 == 0 else coords[i] / image_height for i in range(8)
]
formatted_coords = ["{:.6g}".format(coord) for coord in normalized_coords]
g.write(f"{class_idx} {' '.join(formatted_coords)}\n")
for phase in ["train", "val"]:
image_dir = dota_root_path / "images" / phase
orig_label_dir = dota_root_path / "labels" / f"{phase}_original"
save_dir = dota_root_path / "labels" / phase
save_dir.mkdir(parents=True, exist_ok=True)
image_paths = list(image_dir.iterdir())
for image_path in TQDM(image_paths, desc=f"Processing {phase} images"):
if image_path.suffix != ".png":
continue
image_name_without_ext = image_path.stem
img = cv2.imread(str(image_path))
h, w = img.shape[:2]
convert_label(image_name_without_ext, w, h, orig_label_dir, save_dir)
def min_index(arr1, arr2):
"""
Find a pair of indexes with the shortest distance between two arrays of 2D points.
Args:
arr1 (np.ndarray): A NumPy array of shape (N, 2) representing N 2D points.
arr2 (np.ndarray): A NumPy array of shape (M, 2) representing M 2D points.
Returns:
(tuple): A tuple containing the indexes of the points with the shortest distance in arr1 and arr2 respectively.
"""
dis = ((arr1[:, None, :] - arr2[None, :, :]) ** 2).sum(-1)
return np.unravel_index(np.argmin(dis, axis=None), dis.shape)
def merge_multi_segment(segments):
"""
Merge multiple segments into one list by connecting the coordinates with the minimum distance between each segment.
This function connects these coordinates with a thin line to merge all segments into one.
Args:
segments (List[List]): Original segmentations in COCO's JSON file.
Each element is a list of coordinates, like [segmentation1, segmentation2,...].
Returns:
s (List[np.ndarray]): A list of connected segments represented as NumPy arrays.
"""
s = []
segments = [np.array(i).reshape(-1, 2) for i in segments]
idx_list = [[] for _ in range(len(segments))]
# Record the indexes with min distance between each segment
for i in range(1, len(segments)):
idx1, idx2 = min_index(segments[i - 1], segments[i])
idx_list[i - 1].append(idx1)
idx_list[i].append(idx2)
# Use two round to connect all the segments
for k in range(2):
# Forward connection
if k == 0:
for i, idx in enumerate(idx_list):
# Middle segments have two indexes, reverse the index of middle segments
if len(idx) == 2 and idx[0] > idx[1]:
idx = idx[::-1]
segments[i] = segments[i][::-1, :]
segments[i] = np.roll(segments[i], -idx[0], axis=0)
segments[i] = np.concatenate([segments[i], segments[i][:1]])
# Deal with the first segment and the last one
if i in [0, len(idx_list) - 1]:
s.append(segments[i])
else:
idx = [0, idx[1] - idx[0]]
s.append(segments[i][idx[0] : idx[1] + 1])
else:
for i in range(len(idx_list) - 1, -1, -1):
if i not in [0, len(idx_list) - 1]:
idx = idx_list[i]
nidx = abs(idx[1] - idx[0])
s.append(segments[i][nidx:])
return s
def yolo_bbox2segment(im_dir, save_dir=None, sam_model="sam_b.pt"):
"""
Converts existing object detection dataset (bounding boxes) to segmentation dataset or oriented bounding box (OBB)
in YOLO format. Generates segmentation data using SAM auto-annotator as needed.
Args:
im_dir (str | Path): Path to image directory to convert.
save_dir (str | Path): Path to save the generated labels, labels will be saved
into `labels-segment` in the same directory level of `im_dir` if save_dir is None. Default: None.
sam_model (str): Segmentation model to use for intermediate segmentation data; optional.
Notes:
The input directory structure assumed for dataset:
- im_dir
├─ 001.jpg
├─ ..
└─ NNN.jpg
- labels
├─ 001.txt
├─ ..
└─ NNN.txt
"""
from ultralytics.data import YOLODataset
from ultralytics.utils.ops import xywh2xyxy
from ultralytics.utils import LOGGER
from ultralytics import SAM
from tqdm import tqdm
# NOTE: add placeholder to pass class index check
dataset = YOLODataset(im_dir, data=dict(names=list(range(1000))))
if len(dataset.labels[0]["segments"]) > 0: # if it's segment data
LOGGER.info("Segmentation labels detected, no need to generate new ones!")
return
LOGGER.info("Detection labels detected, generating segment labels by SAM model!")
sam_model = SAM(sam_model)
for l in tqdm(dataset.labels, total=len(dataset.labels), desc="Generating segment labels"):
h, w = l["shape"]
boxes = l["bboxes"]
if len(boxes) == 0: # skip empty labels
continue
boxes[:, [0, 2]] *= w
boxes[:, [1, 3]] *= h
im = cv2.imread(l["im_file"])
sam_results = sam_model(im, bboxes=xywh2xyxy(boxes), verbose=False, save=False)
l["segments"] = sam_results[0].masks.xyn
save_dir = Path(save_dir) if save_dir else Path(im_dir).parent / "labels-segment"
save_dir.mkdir(parents=True, exist_ok=True)
for l in dataset.labels:
texts = []
lb_name = Path(l["im_file"]).with_suffix(".txt").name
txt_file = save_dir / lb_name
cls = l["cls"]
for i, s in enumerate(l["segments"]):
line = (int(cls[i]), *s.reshape(-1))
texts.append(("%g " * len(line)).rstrip() % line)
if texts:
with open(txt_file, "a") as f:
f.writelines(text + "\n" for text in texts)
LOGGER.info(f"Generated segment labels saved in {save_dir}")

383
ultralytics/data/dataset.py Normal file
View File

@ -0,0 +1,383 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
import contextlib
from itertools import repeat
from multiprocessing.pool import ThreadPool
from pathlib import Path
import cv2
import numpy as np
import torch
import torchvision
from PIL import Image
from ultralytics.utils import LOCAL_RANK, NUM_THREADS, TQDM, colorstr, is_dir_writeable
from ultralytics.utils.ops import resample_segments
from .augment import Compose, Format, Instances, LetterBox, classify_augmentations, classify_transforms, v8_transforms
from .base import BaseDataset
from .utils import HELP_URL, LOGGER, get_hash, img2label_paths, verify_image, verify_image_label
# Ultralytics dataset *.cache version, >= 1.0.0 for YOLOv8
DATASET_CACHE_VERSION = "1.0.3"
class YOLODataset(BaseDataset):
"""
Dataset class for loading object detection and/or segmentation labels in YOLO format.
Args:
data (dict, optional): A dataset YAML dictionary. Defaults to None.
task (str): An explicit arg to point current task, Defaults to 'detect'.
Returns:
(torch.utils.data.Dataset): A PyTorch dataset object that can be used for training an object detection model.
"""
def __init__(self, *args, data=None, task="detect", **kwargs):
"""Initializes the YOLODataset with optional configurations for segments and keypoints."""
self.use_segments = task == "segment"
self.use_keypoints = task == "pose"
self.use_obb = task == "obb"
self.data = data
assert not (self.use_segments and self.use_keypoints), "Can not use both segments and keypoints."
super().__init__(*args, **kwargs)
def cache_labels(self, path=Path("./labels.cache")):
"""
Cache dataset labels, check images and read shapes.
Args:
path (Path): Path where to save the cache file. Default is Path('./labels.cache').
Returns:
(dict): labels.
"""
x = {"labels": []}
nm, nf, ne, nc, msgs = 0, 0, 0, 0, [] # number missing, found, empty, corrupt, messages
desc = f"{self.prefix}Scanning {path.parent / path.stem}..."
total = len(self.im_files)
nkpt, ndim = self.data.get("kpt_shape", (0, 0))
if self.use_keypoints and (nkpt <= 0 or ndim not in (2, 3)):
raise ValueError(
"'kpt_shape' in data.yaml missing or incorrect. Should be a list with [number of "
"keypoints, number of dims (2 for x,y or 3 for x,y,visible)], i.e. 'kpt_shape: [17, 3]'"
)
with ThreadPool(NUM_THREADS) as pool:
results = pool.imap(
func=verify_image_label,
iterable=zip(
self.im_files,
self.label_files,
repeat(self.prefix),
repeat(self.use_keypoints),
repeat(len(self.data["names"])),
repeat(nkpt),
repeat(ndim),
),
)
pbar = TQDM(results, desc=desc, total=total)
for im_file, lb, shape, segments, keypoint, nm_f, nf_f, ne_f, nc_f, msg in pbar:
nm += nm_f
nf += nf_f
ne += ne_f
nc += nc_f
if im_file:
x["labels"].append(
dict(
im_file=im_file,
shape=shape,
cls=lb[:, 0:1], # n, 1
bboxes=lb[:, 1:], # n, 4
segments=segments,
keypoints=keypoint,
normalized=True,
bbox_format="xywh",
)
)
if msg:
msgs.append(msg)
pbar.desc = f"{desc} {nf} images, {nm + ne} backgrounds, {nc} corrupt"
pbar.close()
if msgs:
LOGGER.info("\n".join(msgs))
if nf == 0:
LOGGER.warning(f"{self.prefix}WARNING ⚠️ No labels found in {path}. {HELP_URL}")
x["hash"] = get_hash(self.label_files + self.im_files)
x["results"] = nf, nm, ne, nc, len(self.im_files)
x["msgs"] = msgs # warnings
save_dataset_cache_file(self.prefix, path, x)
return x
def get_labels(self):
"""Returns dictionary of labels for YOLO training."""
self.label_files = img2label_paths(self.im_files)
cache_path = Path(self.label_files[0]).parent.with_suffix(".cache")
try:
cache, exists = load_dataset_cache_file(cache_path), True # attempt to load a *.cache file
assert cache["version"] == DATASET_CACHE_VERSION # matches current version
assert cache["hash"] == get_hash(self.label_files + self.im_files) # identical hash
except (FileNotFoundError, AssertionError, AttributeError):
cache, exists = self.cache_labels(cache_path), False # run cache ops
# Display cache
nf, nm, ne, nc, n = cache.pop("results") # found, missing, empty, corrupt, total
if exists and LOCAL_RANK in (-1, 0):
d = f"Scanning {cache_path}... {nf} images, {nm + ne} backgrounds, {nc} corrupt"
TQDM(None, desc=self.prefix + d, total=n, initial=n) # display results
if cache["msgs"]:
LOGGER.info("\n".join(cache["msgs"])) # display warnings
# Read cache
[cache.pop(k) for k in ("hash", "version", "msgs")] # remove items
labels = cache["labels"]
if not labels:
LOGGER.warning(f"WARNING ⚠️ No images found in {cache_path}, training may not work correctly. {HELP_URL}")
self.im_files = [lb["im_file"] for lb in labels] # update im_files
# Check if the dataset is all boxes or all segments
lengths = ((len(lb["cls"]), len(lb["bboxes"]), len(lb["segments"])) for lb in labels)
len_cls, len_boxes, len_segments = (sum(x) for x in zip(*lengths))
if len_segments and len_boxes != len_segments:
LOGGER.warning(
f"WARNING ⚠️ Box and segment counts should be equal, but got len(segments) = {len_segments}, "
f"len(boxes) = {len_boxes}. To resolve this only boxes will be used and all segments will be removed. "
"To avoid this please supply either a detect or segment dataset, not a detect-segment mixed dataset."
)
for lb in labels:
lb["segments"] = []
if len_cls == 0:
LOGGER.warning(f"WARNING ⚠️ No labels found in {cache_path}, training may not work correctly. {HELP_URL}")
return labels
def build_transforms(self, hyp=None):
"""Builds and appends transforms to the list."""
if self.augment:
hyp.mosaic = hyp.mosaic if self.augment and not self.rect else 0.0
hyp.mixup = hyp.mixup if self.augment and not self.rect else 0.0
transforms = v8_transforms(self, self.imgsz, hyp)
else:
transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), scaleup=False)])
transforms.append(
Format(
bbox_format="xywh",
normalize=True,
return_mask=self.use_segments,
return_keypoint=self.use_keypoints,
return_obb=self.use_obb,
batch_idx=True,
mask_ratio=hyp.mask_ratio,
mask_overlap=hyp.overlap_mask,
bgr=hyp.bgr if self.augment else 0.0, # only affect training.
)
)
return transforms
def close_mosaic(self, hyp):
"""Sets mosaic, copy_paste and mixup options to 0.0 and builds transformations."""
hyp.mosaic = 0.0 # set mosaic ratio=0.0
hyp.copy_paste = 0.0 # keep the same behavior as previous v8 close-mosaic
hyp.mixup = 0.0 # keep the same behavior as previous v8 close-mosaic
self.transforms = self.build_transforms(hyp)
def update_labels_info(self, label):
"""
Custom your label format here.
Note:
cls is not with bboxes now, classification and semantic segmentation need an independent cls label
Can also support classification and semantic segmentation by adding or removing dict keys there.
"""
bboxes = label.pop("bboxes")
segments = label.pop("segments", [])
keypoints = label.pop("keypoints", None)
bbox_format = label.pop("bbox_format")
normalized = label.pop("normalized")
# NOTE: do NOT resample oriented boxes
segment_resamples = 100 if self.use_obb else 1000
if len(segments) > 0:
# list[np.array(1000, 2)] * num_samples
# (N, 1000, 2)
segments = np.stack(resample_segments(segments, n=segment_resamples), axis=0)
else:
segments = np.zeros((0, segment_resamples, 2), dtype=np.float32)
label["instances"] = Instances(bboxes, segments, keypoints, bbox_format=bbox_format, normalized=normalized)
return label
@staticmethod
def collate_fn(batch):
"""Collates data samples into batches."""
new_batch = {}
keys = batch[0].keys()
values = list(zip(*[list(b.values()) for b in batch]))
for i, k in enumerate(keys):
value = values[i]
if k == "img":
value = torch.stack(value, 0)
if k in ["masks", "keypoints", "bboxes", "cls", "segments", "obb"]:
value = torch.cat(value, 0)
new_batch[k] = value
new_batch["batch_idx"] = list(new_batch["batch_idx"])
for i in range(len(new_batch["batch_idx"])):
new_batch["batch_idx"][i] += i # add target image index for build_targets()
new_batch["batch_idx"] = torch.cat(new_batch["batch_idx"], 0)
return new_batch
# Classification dataloaders -------------------------------------------------------------------------------------------
class ClassificationDataset(torchvision.datasets.ImageFolder):
"""
Extends torchvision ImageFolder to support YOLO classification tasks, offering functionalities like image
augmentation, caching, and verification. It's designed to efficiently handle large datasets for training deep
learning models, with optional image transformations and caching mechanisms to speed up training.
This class allows for augmentations using both torchvision and Albumentations libraries, and supports caching images
in RAM or on disk to reduce IO overhead during training. Additionally, it implements a robust verification process
to ensure data integrity and consistency.
Attributes:
cache_ram (bool): Indicates if caching in RAM is enabled.
cache_disk (bool): Indicates if caching on disk is enabled.
samples (list): A list of tuples, each containing the path to an image, its class index, path to its .npy cache
file (if caching on disk), and optionally the loaded image array (if caching in RAM).
torch_transforms (callable): PyTorch transforms to be applied to the images.
"""
def __init__(self, root, args, augment=False, prefix=""):
"""
Initialize YOLO object with root, image size, augmentations, and cache settings.
Args:
root (str): Path to the dataset directory where images are stored in a class-specific folder structure.
args (Namespace): Configuration containing dataset-related settings such as image size, augmentation
parameters, and cache settings. It includes attributes like `imgsz` (image size), `fraction` (fraction
of data to use), `scale`, `fliplr`, `flipud`, `cache` (disk or RAM caching for faster training),
`auto_augment`, `hsv_h`, `hsv_s`, `hsv_v`, and `crop_fraction`.
augment (bool, optional): Whether to apply augmentations to the dataset. Default is False.
prefix (str, optional): Prefix for logging and cache filenames, aiding in dataset identification and
debugging. Default is an empty string.
"""
super().__init__(root=root)
if augment and args.fraction < 1.0: # reduce training fraction
self.samples = self.samples[: round(len(self.samples) * args.fraction)]
self.prefix = colorstr(f"{prefix}: ") if prefix else ""
self.cache_ram = args.cache is True or args.cache == "ram" # cache images into RAM
self.cache_disk = args.cache == "disk" # cache images on hard drive as uncompressed *.npy files
self.samples = self.verify_images() # filter out bad images
self.samples = [list(x) + [Path(x[0]).with_suffix(".npy"), None] for x in self.samples] # file, index, npy, im
scale = (1.0 - args.scale, 1.0) # (0.08, 1.0)
self.torch_transforms = (
classify_augmentations(
size=args.imgsz,
scale=scale,
hflip=args.fliplr,
vflip=args.flipud,
erasing=args.erasing,
auto_augment=args.auto_augment,
hsv_h=args.hsv_h,
hsv_s=args.hsv_s,
hsv_v=args.hsv_v,
)
if augment
else classify_transforms(size=args.imgsz, crop_fraction=args.crop_fraction)
)
def __getitem__(self, i):
"""Returns subset of data and targets corresponding to given indices."""
f, j, fn, im = self.samples[i] # filename, index, filename.with_suffix('.npy'), image
if self.cache_ram and im is None:
im = self.samples[i][3] = cv2.imread(f)
elif self.cache_disk:
if not fn.exists(): # load npy
np.save(fn.as_posix(), cv2.imread(f), allow_pickle=False)
im = np.load(fn)
else: # read image
im = cv2.imread(f) # BGR
# Convert NumPy array to PIL image
im = Image.fromarray(cv2.cvtColor(im, cv2.COLOR_BGR2RGB))
sample = self.torch_transforms(im)
return {"img": sample, "cls": j}
def __len__(self) -> int:
"""Return the total number of samples in the dataset."""
return len(self.samples)
def verify_images(self):
"""Verify all images in dataset."""
desc = f"{self.prefix}Scanning {self.root}..."
path = Path(self.root).with_suffix(".cache") # *.cache file path
with contextlib.suppress(FileNotFoundError, AssertionError, AttributeError):
cache = load_dataset_cache_file(path) # attempt to load a *.cache file
assert cache["version"] == DATASET_CACHE_VERSION # matches current version
assert cache["hash"] == get_hash([x[0] for x in self.samples]) # identical hash
nf, nc, n, samples = cache.pop("results") # found, missing, empty, corrupt, total
if LOCAL_RANK in (-1, 0):
d = f"{desc} {nf} images, {nc} corrupt"
TQDM(None, desc=d, total=n, initial=n)
if cache["msgs"]:
LOGGER.info("\n".join(cache["msgs"])) # display warnings
return samples
# Run scan if *.cache retrieval failed
nf, nc, msgs, samples, x = 0, 0, [], [], {}
with ThreadPool(NUM_THREADS) as pool:
results = pool.imap(func=verify_image, iterable=zip(self.samples, repeat(self.prefix)))
pbar = TQDM(results, desc=desc, total=len(self.samples))
for sample, nf_f, nc_f, msg in pbar:
if nf_f:
samples.append(sample)
if msg:
msgs.append(msg)
nf += nf_f
nc += nc_f
pbar.desc = f"{desc} {nf} images, {nc} corrupt"
pbar.close()
if msgs:
LOGGER.info("\n".join(msgs))
x["hash"] = get_hash([x[0] for x in self.samples])
x["results"] = nf, nc, len(samples), samples
x["msgs"] = msgs # warnings
save_dataset_cache_file(self.prefix, path, x)
return samples
def load_dataset_cache_file(path):
"""Load an Ultralytics *.cache dictionary from path."""
import gc
gc.disable() # reduce pickle load time https://github.com/ultralytics/ultralytics/pull/1585
cache = np.load(str(path), allow_pickle=True).item() # load dict
gc.enable()
return cache
def save_dataset_cache_file(prefix, path, x):
"""Save an Ultralytics dataset *.cache dictionary x to path."""
x["version"] = DATASET_CACHE_VERSION # add cache version
if is_dir_writeable(path.parent):
if path.exists():
path.unlink() # remove *.cache file if exists
np.save(str(path), x) # save cache for next time
path.with_suffix(".cache.npy").rename(path) # remove .npy suffix
LOGGER.info(f"{prefix}New cache created: {path}")
else:
LOGGER.warning(f"{prefix}WARNING ⚠️ Cache directory {path.parent} is not writeable, cache not saved.")
# TODO: support semantic segmentation
class SemanticDataset(BaseDataset):
"""
Semantic Segmentation Dataset.
This class is responsible for handling datasets used for semantic segmentation tasks. It inherits functionalities
from the BaseDataset class.
Note:
This class is currently a placeholder and needs to be populated with methods and attributes for supporting
semantic segmentation tasks.
"""
def __init__(self):
"""Initialize a SemanticDataset object."""
super().__init__()

5
ultralytics/data/explorer/__init__.py Normal file
View File

@ -0,0 +1,5 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
from .utils import plot_query_result
__all__ = ["plot_query_result"]

BIN
ultralytics/data/explorer/__pycache__/__init__.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/explorer/__pycache__/__init__.cpython-39.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/explorer/__pycache__/explorer.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/explorer/__pycache__/explorer.cpython-39.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/explorer/__pycache__/utils.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
ultralytics/data/explorer/__pycache__/utils.cpython-39.pyc Normal file
View File

Binary file not shown.

Some files were not shown because too many files have changed in this diff Show More