退购1.1定位算法
This commit is contained in:
jiajie555
0
ultralytics/yolo/data/dataloaders/__init__.py
Normal file
0
ultralytics/yolo/data/dataloaders/__init__.py
Normal file
344
ultralytics/yolo/data/dataloaders/stream_loaders.py
Normal file
344
ultralytics/yolo/data/dataloaders/stream_loaders.py
Normal file
@ -0,0 +1,344 @@
|
||||
# Ultralytics YOLO 🚀, AGPL-3.0 license
|
||||
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from threading import Thread
|
||||
from urllib.parse import urlparse
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import requests
|
||||
import torch
|
||||
from PIL import Image
|
||||
|
||||
from ultralytics.yolo.data.utils import IMG_FORMATS, VID_FORMATS
|
||||
from ultralytics.yolo.utils import LOGGER, ROOT, is_colab, is_kaggle, ops
|
||||
from ultralytics.yolo.utils.checks import check_requirements
|
||||
|
||||
|
||||
@dataclass
|
||||
class SourceTypes:
|
||||
webcam: bool = False
|
||||
screenshot: bool = False
|
||||
from_img: bool = False
|
||||
tensor: bool = False
|
||||
|
||||
|
||||
class LoadStreams:
|
||||
# YOLOv8 streamloader, i.e. `yolo predict source='rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP streams`
|
||||
def __init__(self, sources='file.streams', imgsz=640, vid_stride=1):
|
||||
"""Initialize instance variables and check for consistent input stream shapes."""
|
||||
torch.backends.cudnn.benchmark = True # faster for fixed-size inference
|
||||
self.mode = 'stream'
|
||||
self.imgsz = imgsz
|
||||
self.vid_stride = vid_stride # video frame-rate stride
|
||||
sources = Path(sources).read_text().rsplit() if os.path.isfile(sources) else [sources]
|
||||
n = len(sources)
|
||||
self.sources = [ops.clean_str(x) for x in sources] # clean source names for later
|
||||
self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n
|
||||
for i, s in enumerate(sources): # index, source
|
||||
# Start thread to read frames from video stream
|
||||
st = f'{i + 1}/{n}: {s}... '
|
||||
if urlparse(s).hostname in ('www.youtube.com', 'youtube.com', 'youtu.be'): # if source is YouTube video
|
||||
# YouTube format i.e. 'https://www.youtube.com/watch?v=Zgi9g1ksQHc' or 'https://youtu.be/Zgi9g1ksQHc'
|
||||
check_requirements(('pafy', 'youtube_dl==2020.12.2'))
|
||||
import pafy # noqa
|
||||
s = pafy.new(s).getbest(preftype='mp4').url # YouTube URL
|
||||
s = eval(s) if s.isnumeric() else s # i.e. s = '0' local webcam
|
||||
if s == 0 and (is_colab() or is_kaggle()):
|
||||
raise NotImplementedError("'source=0' webcam not supported in Colab and Kaggle notebooks. "
|
||||
"Try running 'source=0' in a local environment.")
|
||||
cap = cv2.VideoCapture(s)
|
||||
if not cap.isOpened():
|
||||
raise ConnectionError(f'{st}Failed to open {s}')
|
||||
w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
||||
h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
||||
fps = cap.get(cv2.CAP_PROP_FPS) # warning: may return 0 or nan
|
||||
self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf') # infinite stream fallback
|
||||
self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30 # 30 FPS fallback
|
||||
|
||||
success, self.imgs[i] = cap.read() # guarantee first frame
|
||||
if not success or self.imgs[i] is None:
|
||||
raise ConnectionError(f'{st}Failed to read images from {s}')
|
||||
self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True)
|
||||
LOGGER.info(f'{st}Success ✅ ({self.frames[i]} frames of shape {w}x{h} at {self.fps[i]:.2f} FPS)')
|
||||
self.threads[i].start()
|
||||
LOGGER.info('') # newline
|
||||
|
||||
# Check for common shapes
|
||||
self.bs = self.__len__()
|
||||
|
||||
def update(self, i, cap, stream):
|
||||
"""Read stream `i` frames in daemon thread."""
|
||||
n, f = 0, self.frames[i] # frame number, frame array
|
||||
while cap.isOpened() and n < f:
|
||||
n += 1
|
||||
cap.grab() # .read() = .grab() followed by .retrieve()
|
||||
if n % self.vid_stride == 0:
|
||||
success, im = cap.retrieve()
|
||||
if success:
|
||||
self.imgs[i] = im
|
||||
else:
|
||||
LOGGER.warning('WARNING ⚠️ Video stream unresponsive, please check your IP camera connection.')
|
||||
self.imgs[i] = np.zeros_like(self.imgs[i])
|
||||
cap.open(stream) # re-open stream if signal was lost
|
||||
time.sleep(0.0) # wait time
|
||||
|
||||
def __iter__(self):
|
||||
"""Iterates through YOLO image feed and re-opens unresponsive streams."""
|
||||
self.count = -1
|
||||
return self
|
||||
|
||||
def __next__(self):
|
||||
"""Returns source paths, transformed and original images for processing YOLOv5."""
|
||||
self.count += 1
|
||||
if not all(x.is_alive() for x in self.threads) or cv2.waitKey(1) == ord('q'): # q to quit
|
||||
cv2.destroyAllWindows()
|
||||
raise StopIteration
|
||||
|
||||
im0 = self.imgs.copy()
|
||||
return self.sources, im0, None, ''
|
||||
|
||||
def __len__(self):
|
||||
"""Return the length of the sources object."""
|
||||
return len(self.sources) # 1E12 frames = 32 streams at 30 FPS for 30 years
|
||||
|
||||
|
||||
class LoadScreenshots:
|
||||
# YOLOv8 screenshot dataloader, i.e. `yolo predict source=screen`
|
||||
def __init__(self, source, imgsz=640):
|
||||
"""source = [screen_number left top width height] (pixels)."""
|
||||
check_requirements('mss')
|
||||
import mss # noqa
|
||||
|
||||
source, *params = source.split()
|
||||
self.screen, left, top, width, height = 0, None, None, None, None # default to full screen 0
|
||||
if len(params) == 1:
|
||||
self.screen = int(params[0])
|
||||
elif len(params) == 4:
|
||||
left, top, width, height = (int(x) for x in params)
|
||||
elif len(params) == 5:
|
||||
self.screen, left, top, width, height = (int(x) for x in params)
|
||||
self.imgsz = imgsz
|
||||
self.mode = 'stream'
|
||||
self.frame = 0
|
||||
self.sct = mss.mss()
|
||||
self.bs = 1
|
||||
|
||||
# Parse monitor shape
|
||||
monitor = self.sct.monitors[self.screen]
|
||||
self.top = monitor['top'] if top is None else (monitor['top'] + top)
|
||||
self.left = monitor['left'] if left is None else (monitor['left'] + left)
|
||||
self.width = width or monitor['width']
|
||||
self.height = height or monitor['height']
|
||||
self.monitor = {'left': self.left, 'top': self.top, 'width': self.width, 'height': self.height}
|
||||
|
||||
def __iter__(self):
|
||||
"""Returns an iterator of the object."""
|
||||
return self
|
||||
|
||||
def __next__(self):
|
||||
"""mss screen capture: get raw pixels from the screen as np array."""
|
||||
im0 = np.array(self.sct.grab(self.monitor))[:, :, :3] # [:, :, :3] BGRA to BGR
|
||||
s = f'screen {self.screen} (LTWH): {self.left},{self.top},{self.width},{self.height}: '
|
||||
|
||||
self.frame += 1
|
||||
return str(self.screen), im0, None, s # screen, img, original img, im0s, s
|
||||
|
||||
|
||||
class LoadImages:
|
||||
# YOLOv8 image/video dataloader, i.e. `yolo predict source=image.jpg/vid.mp4`
|
||||
def __init__(self, path, imgsz=640, vid_stride=1):
|
||||
"""Initialize the Dataloader and raise FileNotFoundError if file not found."""
|
||||
if isinstance(path, str) and Path(path).suffix == '.txt': # *.txt file with img/vid/dir on each line
|
||||
path = Path(path).read_text().rsplit()
|
||||
files = []
|
||||
for p in sorted(path) if isinstance(path, (list, tuple)) else [path]:
|
||||
p = str(Path(p).resolve())
|
||||
if '*' in p:
|
||||
files.extend(sorted(glob.glob(p, recursive=True))) # glob
|
||||
elif os.path.isdir(p):
|
||||
files.extend(sorted(glob.glob(os.path.join(p, '*.*')))) # dir
|
||||
elif os.path.isfile(p):
|
||||
files.append(p) # files
|
||||
else:
|
||||
raise FileNotFoundError(f'{p} does not exist')
|
||||
|
||||
images = [x for x in files if x.split('.')[-1].lower() in IMG_FORMATS]
|
||||
videos = [x for x in files if x.split('.')[-1].lower() in VID_FORMATS]
|
||||
ni, nv = len(images), len(videos)
|
||||
|
||||
self.imgsz = imgsz
|
||||
self.files = images + videos
|
||||
self.nf = ni + nv # number of files
|
||||
self.video_flag = [False] * ni + [True] * nv
|
||||
self.mode = 'image'
|
||||
self.vid_stride = vid_stride # video frame-rate stride
|
||||
self.bs = 1
|
||||
if any(videos):
|
||||
self.orientation = None # rotation degrees
|
||||
self._new_video(videos[0]) # new video
|
||||
else:
|
||||
self.cap = None
|
||||
if self.nf == 0:
|
||||
raise FileNotFoundError(f'No images or videos found in {p}. '
|
||||
f'Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}')
|
||||
|
||||
def __iter__(self):
|
||||
"""Returns an iterator object for VideoStream or ImageFolder."""
|
||||
self.count = 0
|
||||
return self
|
||||
|
||||
def __next__(self):
|
||||
"""Return next image, path and metadata from dataset."""
|
||||
if self.count == self.nf:
|
||||
raise StopIteration
|
||||
path = self.files[self.count]
|
||||
|
||||
if self.video_flag[self.count]:
|
||||
# Read video
|
||||
self.mode = 'video'
|
||||
for _ in range(self.vid_stride):
|
||||
self.cap.grab()
|
||||
success, im0 = self.cap.retrieve()
|
||||
while not success:
|
||||
self.count += 1
|
||||
self.cap.release()
|
||||
if self.count == self.nf: # last video
|
||||
raise StopIteration
|
||||
path = self.files[self.count]
|
||||
self._new_video(path)
|
||||
success, im0 = self.cap.read()
|
||||
|
||||
self.frame += 1
|
||||
im0 = self._cv2_rotate(im0) # for use if cv2 autorotation is False
|
||||
s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: '
|
||||
|
||||
else:
|
||||
# Read image
|
||||
self.count += 1
|
||||
im0 = cv2.imread(path) # BGR
|
||||
if im0 is None:
|
||||
raise FileNotFoundError(f'Image Not Found {path}')
|
||||
s = f'image {self.count}/{self.nf} {path}: '
|
||||
|
||||
return [path], [im0], self.cap, s
|
||||
|
||||
def _new_video(self, path):
|
||||
"""Create a new video capture object."""
|
||||
self.frame = 0
|
||||
self.cap = cv2.VideoCapture(path)
|
||||
self.frames = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT) / self.vid_stride)
|
||||
if hasattr(cv2, 'CAP_PROP_ORIENTATION_META'): # cv2<4.6.0 compatibility
|
||||
self.orientation = int(self.cap.get(cv2.CAP_PROP_ORIENTATION_META)) # rotation degrees
|
||||
# Disable auto-orientation due to known issues in https://github.com/ultralytics/yolov5/issues/8493
|
||||
# self.cap.set(cv2.CAP_PROP_ORIENTATION_AUTO, 0)
|
||||
|
||||
def _cv2_rotate(self, im):
|
||||
"""Rotate a cv2 video manually."""
|
||||
if self.orientation == 0:
|
||||
return cv2.rotate(im, cv2.ROTATE_90_CLOCKWISE)
|
||||
elif self.orientation == 180:
|
||||
return cv2.rotate(im, cv2.ROTATE_90_COUNTERCLOCKWISE)
|
||||
elif self.orientation == 90:
|
||||
return cv2.rotate(im, cv2.ROTATE_180)
|
||||
return im
|
||||
|
||||
def __len__(self):
|
||||
"""Returns the number of files in the object."""
|
||||
return self.nf # number of files
|
||||
|
||||
|
||||
class LoadPilAndNumpy:
|
||||
|
||||
def __init__(self, im0, imgsz=640):
|
||||
"""Initialize PIL and Numpy Dataloader."""
|
||||
if not isinstance(im0, list):
|
||||
im0 = [im0]
|
||||
self.paths = [getattr(im, 'filename', f'image{i}.jpg') for i, im in enumerate(im0)]
|
||||
self.im0 = [self._single_check(im) for im in im0]
|
||||
self.imgsz = imgsz
|
||||
self.mode = 'image'
|
||||
# Generate fake paths
|
||||
self.bs = len(self.im0)
|
||||
|
||||
@staticmethod
|
||||
def _single_check(im):
|
||||
"""Validate and format an image to numpy array."""
|
||||
assert isinstance(im, (Image.Image, np.ndarray)), f'Expected PIL/np.ndarray image type, but got {type(im)}'
|
||||
if isinstance(im, Image.Image):
|
||||
if im.mode != 'RGB':
|
||||
im = im.convert('RGB')
|
||||
im = np.asarray(im)[:, :, ::-1]
|
||||
im = np.ascontiguousarray(im) # contiguous
|
||||
return im
|
||||
|
||||
def __len__(self):
|
||||
"""Returns the length of the 'im0' attribute."""
|
||||
return len(self.im0)
|
||||
|
||||
def __next__(self):
|
||||
"""Returns batch paths, images, processed images, None, ''."""
|
||||
if self.count == 1: # loop only once as it's batch inference
|
||||
raise StopIteration
|
||||
self.count += 1
|
||||
return self.paths, self.im0, None, ''
|
||||
|
||||
def __iter__(self):
|
||||
"""Enables iteration for class LoadPilAndNumpy."""
|
||||
self.count = 0
|
||||
return self
|
||||
|
||||
|
||||
class LoadTensor:
|
||||
|
||||
def __init__(self, imgs) -> None:
|
||||
self.im0 = imgs
|
||||
self.bs = imgs.shape[0]
|
||||
self.mode = 'image'
|
||||
|
||||
def __iter__(self):
|
||||
"""Returns an iterator object."""
|
||||
self.count = 0
|
||||
return self
|
||||
|
||||
def __next__(self):
|
||||
"""Return next item in the iterator."""
|
||||
if self.count == 1:
|
||||
raise StopIteration
|
||||
self.count += 1
|
||||
return None, self.im0, None, '' # self.paths, im, self.im0, None, ''
|
||||
|
||||
def __len__(self):
|
||||
"""Returns the batch size."""
|
||||
return self.bs
|
||||
|
||||
|
||||
def autocast_list(source):
|
||||
"""
|
||||
Merges a list of source of different types into a list of numpy arrays or PIL images
|
||||
"""
|
||||
files = []
|
||||
for im in source:
|
||||
if isinstance(im, (str, Path)): # filename or uri
|
||||
files.append(Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im))
|
||||
elif isinstance(im, (Image.Image, np.ndarray)): # PIL or np Image
|
||||
files.append(im)
|
||||
else:
|
||||
raise TypeError(f'type {type(im).__name__} is not a supported Ultralytics prediction source type. \n'
|
||||
f'See https://docs.ultralytics.com/modes/predict for supported source types.')
|
||||
|
||||
return files
|
||||
|
||||
|
||||
LOADERS = [LoadStreams, LoadPilAndNumpy, LoadImages, LoadScreenshots]
|
||||
|
||||
if __name__ == '__main__':
|
||||
img = cv2.imread(str(ROOT / 'assets/bus.jpg'))
|
||||
dataset = LoadPilAndNumpy(im0=img)
|
||||
for d in dataset:
|
||||
print(d[0])
|
||||
407
ultralytics/yolo/data/dataloaders/v5augmentations.py
Normal file
407
ultralytics/yolo/data/dataloaders/v5augmentations.py
Normal file
@ -0,0 +1,407 @@
|
||||
# Ultralytics YOLO 🚀, AGPL-3.0 license
|
||||
"""
|
||||
Image augmentation functions
|
||||
"""
|
||||
|
||||
import math
|
||||
import random
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import torch
|
||||
import torchvision.transforms as T
|
||||
import torchvision.transforms.functional as TF
|
||||
|
||||
from ultralytics.yolo.utils import LOGGER, colorstr
|
||||
from ultralytics.yolo.utils.checks import check_version
|
||||
from ultralytics.yolo.utils.metrics import bbox_ioa
|
||||
from ultralytics.yolo.utils.ops import resample_segments, segment2box, xywhn2xyxy
|
||||
|
||||
IMAGENET_MEAN = 0.485, 0.456, 0.406 # RGB mean
|
||||
IMAGENET_STD = 0.229, 0.224, 0.225 # RGB standard deviation
|
||||
|
||||
|
||||
class Albumentations:
|
||||
# YOLOv5 Albumentations class (optional, only used if package is installed)
|
||||
def __init__(self, size=640):
|
||||
"""Instantiate object with image augmentations for YOLOv5."""
|
||||
self.transform = None
|
||||
prefix = colorstr('albumentations: ')
|
||||
try:
|
||||
import albumentations as A
|
||||
check_version(A.__version__, '1.0.3', hard=True) # version requirement
|
||||
|
||||
T = [
|
||||
A.RandomResizedCrop(height=size, width=size, scale=(0.8, 1.0), ratio=(0.9, 1.11), p=0.0),
|
||||
A.Blur(p=0.01),
|
||||
A.MedianBlur(p=0.01),
|
||||
A.ToGray(p=0.01),
|
||||
A.CLAHE(p=0.01),
|
||||
A.RandomBrightnessContrast(p=0.0),
|
||||
A.RandomGamma(p=0.0),
|
||||
A.ImageCompression(quality_lower=75, p=0.0)] # transforms
|
||||
self.transform = A.Compose(T, bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels']))
|
||||
|
||||
LOGGER.info(prefix + ', '.join(f'{x}'.replace('always_apply=False, ', '') for x in T if x.p))
|
||||
except ImportError: # package not installed, skip
|
||||
pass
|
||||
except Exception as e:
|
||||
LOGGER.info(f'{prefix}{e}')
|
||||
|
||||
def __call__(self, im, labels, p=1.0):
|
||||
"""Transforms input image and labels with probability 'p'."""
|
||||
if self.transform and random.random() < p:
|
||||
new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0]) # transformed
|
||||
im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])])
|
||||
return im, labels
|
||||
|
||||
|
||||
def normalize(x, mean=IMAGENET_MEAN, std=IMAGENET_STD, inplace=False):
|
||||
"""Denormalize RGB images x per ImageNet stats in BCHW format, i.e. = (x - mean) / std."""
|
||||
return TF.normalize(x, mean, std, inplace=inplace)
|
||||
|
||||
|
||||
def denormalize(x, mean=IMAGENET_MEAN, std=IMAGENET_STD):
|
||||
"""Denormalize RGB images x per ImageNet stats in BCHW format, i.e. = x * std + mean."""
|
||||
for i in range(3):
|
||||
x[:, i] = x[:, i] * std[i] + mean[i]
|
||||
return x
|
||||
|
||||
|
||||
def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5):
|
||||
"""HSV color-space augmentation."""
|
||||
if hgain or sgain or vgain:
|
||||
r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains
|
||||
hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV))
|
||||
dtype = im.dtype # uint8
|
||||
|
||||
x = np.arange(0, 256, dtype=r.dtype)
|
||||
lut_hue = ((x * r[0]) % 180).astype(dtype)
|
||||
lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
|
||||
lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
|
||||
|
||||
im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
|
||||
cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im) # no return needed
|
||||
|
||||
|
||||
def hist_equalize(im, clahe=True, bgr=False):
|
||||
"""Equalize histogram on BGR image 'im' with im.shape(n,m,3) and range 0-255."""
|
||||
yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV)
|
||||
if clahe:
|
||||
c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
|
||||
yuv[:, :, 0] = c.apply(yuv[:, :, 0])
|
||||
else:
|
||||
yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0]) # equalize Y channel histogram
|
||||
return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB) # convert YUV image to RGB
|
||||
|
||||
|
||||
def replicate(im, labels):
|
||||
"""Replicate labels."""
|
||||
h, w = im.shape[:2]
|
||||
boxes = labels[:, 1:].astype(int)
|
||||
x1, y1, x2, y2 = boxes.T
|
||||
s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels)
|
||||
for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices
|
||||
x1b, y1b, x2b, y2b = boxes[i]
|
||||
bh, bw = y2b - y1b, x2b - x1b
|
||||
yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y
|
||||
x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh]
|
||||
im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b] # im4[ymin:ymax, xmin:xmax]
|
||||
labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0)
|
||||
|
||||
return im, labels
|
||||
|
||||
|
||||
def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
|
||||
"""Resize and pad image while meeting stride-multiple constraints."""
|
||||
shape = im.shape[:2] # current shape [height, width]
|
||||
if isinstance(new_shape, int):
|
||||
new_shape = (new_shape, new_shape)
|
||||
|
||||
# Scale ratio (new / old)
|
||||
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
|
||||
if not scaleup: # only scale down, do not scale up (for better val mAP)
|
||||
r = min(r, 1.0)
|
||||
|
||||
# Compute padding
|
||||
ratio = r, r # width, height ratios
|
||||
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
|
||||
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
|
||||
if auto: # minimum rectangle
|
||||
dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding
|
||||
elif scaleFill: # stretch
|
||||
dw, dh = 0.0, 0.0
|
||||
new_unpad = (new_shape[1], new_shape[0])
|
||||
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
|
||||
|
||||
dw /= 2 # divide padding into 2 sides
|
||||
dh /= 2
|
||||
|
||||
if shape[::-1] != new_unpad: # resize
|
||||
im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
|
||||
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
|
||||
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
|
||||
im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
|
||||
return im, ratio, (dw, dh)
|
||||
|
||||
|
||||
def random_perspective(im,
|
||||
targets=(),
|
||||
segments=(),
|
||||
degrees=10,
|
||||
translate=.1,
|
||||
scale=.1,
|
||||
shear=10,
|
||||
perspective=0.0,
|
||||
border=(0, 0)):
|
||||
# torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10))
|
||||
# targets = [cls, xyxy]
|
||||
|
||||
height = im.shape[0] + border[0] * 2 # shape(h,w,c)
|
||||
width = im.shape[1] + border[1] * 2
|
||||
|
||||
# Center
|
||||
C = np.eye(3)
|
||||
C[0, 2] = -im.shape[1] / 2 # x translation (pixels)
|
||||
C[1, 2] = -im.shape[0] / 2 # y translation (pixels)
|
||||
|
||||
# Perspective
|
||||
P = np.eye(3)
|
||||
P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y)
|
||||
P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x)
|
||||
|
||||
# Rotation and Scale
|
||||
R = np.eye(3)
|
||||
a = random.uniform(-degrees, degrees)
|
||||
# a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations
|
||||
s = random.uniform(1 - scale, 1 + scale)
|
||||
# s = 2 ** random.uniform(-scale, scale)
|
||||
R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
|
||||
|
||||
# Shear
|
||||
S = np.eye(3)
|
||||
S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg)
|
||||
S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg)
|
||||
|
||||
# Translation
|
||||
T = np.eye(3)
|
||||
T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels)
|
||||
T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels)
|
||||
|
||||
# Combined rotation matrix
|
||||
M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT
|
||||
if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed
|
||||
if perspective:
|
||||
im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114))
|
||||
else: # affine
|
||||
im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
|
||||
|
||||
# Visualize
|
||||
# import matplotlib.pyplot as plt
|
||||
# ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
|
||||
# ax[0].imshow(im[:, :, ::-1]) # base
|
||||
# ax[1].imshow(im2[:, :, ::-1]) # warped
|
||||
|
||||
# Transform label coordinates
|
||||
n = len(targets)
|
||||
if n:
|
||||
use_segments = any(x.any() for x in segments)
|
||||
new = np.zeros((n, 4))
|
||||
if use_segments: # warp segments
|
||||
segments = resample_segments(segments) # upsample
|
||||
for i, segment in enumerate(segments):
|
||||
xy = np.ones((len(segment), 3))
|
||||
xy[:, :2] = segment
|
||||
xy = xy @ M.T # transform
|
||||
xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2] # perspective rescale or affine
|
||||
|
||||
# Clip
|
||||
new[i] = segment2box(xy, width, height)
|
||||
|
||||
else: # warp boxes
|
||||
xy = np.ones((n * 4, 3))
|
||||
xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1
|
||||
xy = xy @ M.T # transform
|
||||
xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8) # perspective rescale or affine
|
||||
|
||||
# Create new boxes
|
||||
x = xy[:, [0, 2, 4, 6]]
|
||||
y = xy[:, [1, 3, 5, 7]]
|
||||
new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
|
||||
|
||||
# Clip
|
||||
new[:, [0, 2]] = new[:, [0, 2]].clip(0, width)
|
||||
new[:, [1, 3]] = new[:, [1, 3]].clip(0, height)
|
||||
|
||||
# Filter candidates
|
||||
i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10)
|
||||
targets = targets[i]
|
||||
targets[:, 1:5] = new[i]
|
||||
|
||||
return im, targets
|
||||
|
||||
|
||||
def copy_paste(im, labels, segments, p=0.5):
|
||||
"""Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy)."""
|
||||
n = len(segments)
|
||||
if p and n:
|
||||
h, w, c = im.shape # height, width, channels
|
||||
im_new = np.zeros(im.shape, np.uint8)
|
||||
|
||||
# Calculate ioa first then select indexes randomly
|
||||
boxes = np.stack([w - labels[:, 3], labels[:, 2], w - labels[:, 1], labels[:, 4]], axis=-1) # (n, 4)
|
||||
ioa = bbox_ioa(boxes, labels[:, 1:5]) # intersection over area
|
||||
indexes = np.nonzero((ioa < 0.30).all(1))[0] # (N, )
|
||||
n = len(indexes)
|
||||
for j in random.sample(list(indexes), k=round(p * n)):
|
||||
l, box, s = labels[j], boxes[j], segments[j]
|
||||
labels = np.concatenate((labels, [[l[0], *box]]), 0)
|
||||
segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1))
|
||||
cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (1, 1, 1), cv2.FILLED)
|
||||
|
||||
result = cv2.flip(im, 1) # augment segments (flip left-right)
|
||||
i = cv2.flip(im_new, 1).astype(bool)
|
||||
im[i] = result[i] # cv2.imwrite('debug.jpg', im) # debug
|
||||
|
||||
return im, labels, segments
|
||||
|
||||
|
||||
def cutout(im, labels, p=0.5):
|
||||
"""Applies image cutout augmentation https://arxiv.org/abs/1708.04552."""
|
||||
if random.random() < p:
|
||||
h, w = im.shape[:2]
|
||||
scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction
|
||||
for s in scales:
|
||||
mask_h = random.randint(1, int(h * s)) # create random masks
|
||||
mask_w = random.randint(1, int(w * s))
|
||||
|
||||
# Box
|
||||
xmin = max(0, random.randint(0, w) - mask_w // 2)
|
||||
ymin = max(0, random.randint(0, h) - mask_h // 2)
|
||||
xmax = min(w, xmin + mask_w)
|
||||
ymax = min(h, ymin + mask_h)
|
||||
|
||||
# Apply random color mask
|
||||
im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)]
|
||||
|
||||
# Return unobscured labels
|
||||
if len(labels) and s > 0.03:
|
||||
box = np.array([[xmin, ymin, xmax, ymax]], dtype=np.float32)
|
||||
ioa = bbox_ioa(box, xywhn2xyxy(labels[:, 1:5], w, h))[0] # intersection over area
|
||||
labels = labels[ioa < 0.60] # remove >60% obscured labels
|
||||
|
||||
return labels
|
||||
|
||||
|
||||
def mixup(im, labels, im2, labels2):
|
||||
"""Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf."""
|
||||
r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0
|
||||
im = (im * r + im2 * (1 - r)).astype(np.uint8)
|
||||
labels = np.concatenate((labels, labels2), 0)
|
||||
return im, labels
|
||||
|
||||
|
||||
def box_candidates(box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n)
|
||||
# Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
|
||||
w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
|
||||
w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
|
||||
ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps)) # aspect ratio
|
||||
return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr) # candidates
|
||||
|
||||
|
||||
def classify_albumentations(
|
||||
augment=True,
|
||||
size=224,
|
||||
scale=(0.08, 1.0),
|
||||
ratio=(0.75, 1.0 / 0.75), # 0.75, 1.33
|
||||
hflip=0.5,
|
||||
vflip=0.0,
|
||||
jitter=0.4,
|
||||
mean=IMAGENET_MEAN,
|
||||
std=IMAGENET_STD,
|
||||
auto_aug=False):
|
||||
# YOLOv5 classification Albumentations (optional, only used if package is installed)
|
||||
prefix = colorstr('albumentations: ')
|
||||
try:
|
||||
import albumentations as A
|
||||
from albumentations.pytorch import ToTensorV2
|
||||
check_version(A.__version__, '1.0.3', hard=True) # version requirement
|
||||
if augment: # Resize and crop
|
||||
T = [A.RandomResizedCrop(height=size, width=size, scale=scale, ratio=ratio)]
|
||||
if auto_aug:
|
||||
# TODO: implement AugMix, AutoAug & RandAug in albumentation
|
||||
LOGGER.info(f'{prefix}auto augmentations are currently not supported')
|
||||
else:
|
||||
if hflip > 0:
|
||||
T += [A.HorizontalFlip(p=hflip)]
|
||||
if vflip > 0:
|
||||
T += [A.VerticalFlip(p=vflip)]
|
||||
if jitter > 0:
|
||||
jitter = float(jitter)
|
||||
T += [A.ColorJitter(jitter, jitter, jitter, 0)] # brightness, contrast, satuaration, 0 hue
|
||||
else: # Use fixed crop for eval set (reproducibility)
|
||||
T = [A.SmallestMaxSize(max_size=size), A.CenterCrop(height=size, width=size)]
|
||||
T += [A.Normalize(mean=mean, std=std), ToTensorV2()] # Normalize and convert to Tensor
|
||||
LOGGER.info(prefix + ', '.join(f'{x}'.replace('always_apply=False, ', '') for x in T if x.p))
|
||||
return A.Compose(T)
|
||||
|
||||
except ImportError: # package not installed, skip
|
||||
LOGGER.warning(f'{prefix}⚠️ not found, install with `pip install albumentations` (recommended)')
|
||||
except Exception as e:
|
||||
LOGGER.info(f'{prefix}{e}')
|
||||
|
||||
|
||||
def classify_transforms(size=224):
|
||||
"""Transforms to apply if albumentations not installed."""
|
||||
assert isinstance(size, int), f'ERROR: classify_transforms size {size} must be integer, not (list, tuple)'
|
||||
# T.Compose([T.ToTensor(), T.Resize(size), T.CenterCrop(size), T.Normalize(IMAGENET_MEAN, IMAGENET_STD)])
|
||||
return T.Compose([CenterCrop(size), ToTensor(), T.Normalize(IMAGENET_MEAN, IMAGENET_STD)])
|
||||
|
||||
|
||||
class LetterBox:
|
||||
# YOLOv5 LetterBox class for image preprocessing, i.e. T.Compose([LetterBox(size), ToTensor()])
|
||||
def __init__(self, size=(640, 640), auto=False, stride=32):
|
||||
"""Resizes and crops an image to a specified size for YOLOv5 preprocessing."""
|
||||
super().__init__()
|
||||
self.h, self.w = (size, size) if isinstance(size, int) else size
|
||||
self.auto = auto # pass max size integer, automatically solve for short side using stride
|
||||
self.stride = stride # used with auto
|
||||
|
||||
def __call__(self, im): # im = np.array HWC
|
||||
imh, imw = im.shape[:2]
|
||||
r = min(self.h / imh, self.w / imw) # ratio of new/old
|
||||
h, w = round(imh * r), round(imw * r) # resized image
|
||||
hs, ws = (math.ceil(x / self.stride) * self.stride for x in (h, w)) if self.auto else self.h, self.w
|
||||
top, left = round((hs - h) / 2 - 0.1), round((ws - w) / 2 - 0.1)
|
||||
im_out = np.full((self.h, self.w, 3), 114, dtype=im.dtype)
|
||||
im_out[top:top + h, left:left + w] = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR)
|
||||
return im_out
|
||||
|
||||
|
||||
class CenterCrop:
|
||||
# YOLOv5 CenterCrop class for image preprocessing, i.e. T.Compose([CenterCrop(size), ToTensor()])
|
||||
def __init__(self, size=640):
|
||||
"""Converts input image into tensor for YOLOv5 processing."""
|
||||
super().__init__()
|
||||
self.h, self.w = (size, size) if isinstance(size, int) else size
|
||||
|
||||
def __call__(self, im): # im = np.array HWC
|
||||
imh, imw = im.shape[:2]
|
||||
m = min(imh, imw) # min dimension
|
||||
top, left = (imh - m) // 2, (imw - m) // 2
|
||||
return cv2.resize(im[top:top + m, left:left + m], (self.w, self.h), interpolation=cv2.INTER_LINEAR)
|
||||
|
||||
|
||||
class ToTensor:
|
||||
# YOLOv5 ToTensor class for image preprocessing, i.e. T.Compose([LetterBox(size), ToTensor()])
|
||||
def __init__(self, half=False):
|
||||
"""Initialize ToTensor class for YOLOv5 image preprocessing."""
|
||||
super().__init__()
|
||||
self.half = half
|
||||
|
||||
def __call__(self, im): # im = np.array HWC in BGR order
|
||||
im = np.ascontiguousarray(im.transpose((2, 0, 1))[::-1]) # HWC to CHW -> BGR to RGB -> contiguous
|
||||
im = torch.from_numpy(im) # to torch
|
||||
im = im.half() if self.half else im.float() # uint8 to fp16/32
|
||||
im /= 255.0 # 0-255 to 0.0-1.0
|
||||
return im
|
||||
1109
ultralytics/yolo/data/dataloaders/v5loader.py
Normal file
1109
ultralytics/yolo/data/dataloaders/v5loader.py
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user