lichen/detecttracking
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add yolo v10 and modify pipeline

Browse Source
This commit is contained in:
王庆刚
2025-03-28 13:19:54 +08:00
parent 183299c06b
commit 798c596acc
471 changed files with 19109 additions and 7342 deletions
Download Patch File Download Diff File Expand all files Collapse all files

183
ultralytics/utils/callbacks/comet.py
View File

@ -4,20 +4,20 @@ from ultralytics.utils import LOGGER, RANK, SETTINGS, TESTS_RUNNING, ops
try:
assert not TESTS_RUNNING # do not log pytest
assert SETTINGS['comet'] is True # verify integration is enabled
assert SETTINGS["comet"] is True # verify integration is enabled
import comet_ml
assert hasattr(comet_ml, '__version__') # verify package is not directory
assert hasattr(comet_ml, "__version__") # verify package is not directory
import os
from pathlib import Path
# Ensures certain logging functions only run for supported tasks
COMET_SUPPORTED_TASKS = ['detect']
COMET_SUPPORTED_TASKS = ["detect"]
# Names of plots created by YOLOv8 that are logged to Comet
EVALUATION_PLOT_NAMES = 'F1_curve', 'P_curve', 'R_curve', 'PR_curve', 'confusion_matrix'
LABEL_PLOT_NAMES = 'labels', 'labels_correlogram'
EVALUATION_PLOT_NAMES = "F1_curve", "P_curve", "R_curve", "PR_curve", "confusion_matrix"
LABEL_PLOT_NAMES = "labels", "labels_correlogram"
_comet_image_prediction_count = 0
@ -26,37 +26,44 @@ except (ImportError, AssertionError):
def _get_comet_mode():
return os.getenv('COMET_MODE', 'online')
"""Returns the mode of comet set in the environment variables, defaults to 'online' if not set."""
return os.getenv("COMET_MODE", "online")
def _get_comet_model_name():
return os.getenv('COMET_MODEL_NAME', 'YOLOv8')
"""Returns the model name for Comet from the environment variable 'COMET_MODEL_NAME' or defaults to 'YOLOv8'."""
return os.getenv("COMET_MODEL_NAME", "YOLOv8")
def _get_eval_batch_logging_interval():
return int(os.getenv('COMET_EVAL_BATCH_LOGGING_INTERVAL', 1))
"""Get the evaluation batch logging interval from environment variable or use default value 1."""
return int(os.getenv("COMET_EVAL_BATCH_LOGGING_INTERVAL", 1))
def _get_max_image_predictions_to_log():
return int(os.getenv('COMET_MAX_IMAGE_PREDICTIONS', 100))
"""Get the maximum number of image predictions to log from the environment variables."""
return int(os.getenv("COMET_MAX_IMAGE_PREDICTIONS", 100))
def _scale_confidence_score(score):
scale = float(os.getenv('COMET_MAX_CONFIDENCE_SCORE', 100.0))
"""Scales the given confidence score by a factor specified in an environment variable."""
scale = float(os.getenv("COMET_MAX_CONFIDENCE_SCORE", 100.0))
return score * scale
def _should_log_confusion_matrix():
return os.getenv('COMET_EVAL_LOG_CONFUSION_MATRIX', 'false').lower() == 'true'
"""Determines if the confusion matrix should be logged based on the environment variable settings."""
return os.getenv("COMET_EVAL_LOG_CONFUSION_MATRIX", "false").lower() == "true"
def _should_log_image_predictions():
return os.getenv('COMET_EVAL_LOG_IMAGE_PREDICTIONS', 'true').lower() == 'true'
"""Determines whether to log image predictions based on a specified environment variable."""
return os.getenv("COMET_EVAL_LOG_IMAGE_PREDICTIONS", "true").lower() == "true"
def _get_experiment_type(mode, project_name):
"""Return an experiment based on mode and project name."""
if mode == 'offline':
if mode == "offline":
return comet_ml.OfflineExperiment(project_name=project_name)
return comet_ml.Experiment(project_name=project_name)
@ -68,18 +75,21 @@ def _create_experiment(args):
return
try:
comet_mode = _get_comet_mode()
_project_name = os.getenv('COMET_PROJECT_NAME', args.project)
_project_name = os.getenv("COMET_PROJECT_NAME", args.project)
experiment = _get_experiment_type(comet_mode, _project_name)
experiment.log_parameters(vars(args))
experiment.log_others({
'eval_batch_logging_interval': _get_eval_batch_logging_interval(),
'log_confusion_matrix_on_eval': _should_log_confusion_matrix(),
'log_image_predictions': _should_log_image_predictions(),
'max_image_predictions': _get_max_image_predictions_to_log(), })
experiment.log_other('Created from', 'yolov8')
experiment.log_others(
{
"eval_batch_logging_interval": _get_eval_batch_logging_interval(),
"log_confusion_matrix_on_eval": _should_log_confusion_matrix(),
"log_image_predictions": _should_log_image_predictions(),
"max_image_predictions": _get_max_image_predictions_to_log(),
}
)
experiment.log_other("Created from", "yolov8")
except Exception as e:
LOGGER.warning(f'WARNING ⚠️ Comet installed but not initialized correctly, not logging this run. {e}')
LOGGER.warning(f"WARNING ⚠️ Comet installed but not initialized correctly, not logging this run. {e}")
def _fetch_trainer_metadata(trainer):
@ -95,18 +105,14 @@ def _fetch_trainer_metadata(trainer):
save_interval = curr_epoch % save_period == 0
save_assets = save and save_period > 0 and save_interval and not final_epoch
return dict(
curr_epoch=curr_epoch,
curr_step=curr_step,
save_assets=save_assets,
final_epoch=final_epoch,
)
return dict(curr_epoch=curr_epoch, curr_step=curr_step, save_assets=save_assets, final_epoch=final_epoch)
def _scale_bounding_box_to_original_image_shape(box, resized_image_shape, original_image_shape, ratio_pad):
"""YOLOv8 resizes images during training and the label values
are normalized based on this resized shape. This function rescales the
bounding box labels to the original image shape.
"""
YOLOv8 resizes images during training and the label values are normalized based on this resized shape.
This function rescales the bounding box labels to the original image shape.
"""
resized_image_height, resized_image_width = resized_image_shape
@ -126,29 +132,32 @@ def _scale_bounding_box_to_original_image_shape(box, resized_image_shape, origin
def _format_ground_truth_annotations_for_detection(img_idx, image_path, batch, class_name_map=None):
"""Format ground truth annotations for detection."""
indices = batch['batch_idx'] == img_idx
bboxes = batch['bboxes'][indices]
indices = batch["batch_idx"] == img_idx
bboxes = batch["bboxes"][indices]
if len(bboxes) == 0:
LOGGER.debug(f'COMET WARNING: Image: {image_path} has no bounding boxes labels')
LOGGER.debug(f"COMET WARNING: Image: {image_path} has no bounding boxes labels")
return None
cls_labels = batch['cls'][indices].squeeze(1).tolist()
cls_labels = batch["cls"][indices].squeeze(1).tolist()
if class_name_map:
cls_labels = [str(class_name_map[label]) for label in cls_labels]
original_image_shape = batch['ori_shape'][img_idx]
resized_image_shape = batch['resized_shape'][img_idx]
ratio_pad = batch['ratio_pad'][img_idx]
original_image_shape = batch["ori_shape"][img_idx]
resized_image_shape = batch["resized_shape"][img_idx]
ratio_pad = batch["ratio_pad"][img_idx]
data = []
for box, label in zip(bboxes, cls_labels):
box = _scale_bounding_box_to_original_image_shape(box, resized_image_shape, original_image_shape, ratio_pad)
data.append({
'boxes': [box],
'label': f'gt_{label}',
'score': _scale_confidence_score(1.0), })
data.append(
{
"boxes": [box],
"label": f"gt_{label}",
"score": _scale_confidence_score(1.0),
}
)
return {'name': 'ground_truth', 'data': data}
return {"name": "ground_truth", "data": data}
def _format_prediction_annotations_for_detection(image_path, metadata, class_label_map=None):
@ -158,31 +167,34 @@ def _format_prediction_annotations_for_detection(image_path, metadata, class_lab
predictions = metadata.get(image_id)
if not predictions:
LOGGER.debug(f'COMET WARNING: Image: {image_path} has no bounding boxes predictions')
LOGGER.debug(f"COMET WARNING: Image: {image_path} has no bounding boxes predictions")
return None
data = []
for prediction in predictions:
boxes = prediction['bbox']
score = _scale_confidence_score(prediction['score'])
cls_label = prediction['category_id']
boxes = prediction["bbox"]
score = _scale_confidence_score(prediction["score"])
cls_label = prediction["category_id"]
if class_label_map:
cls_label = str(class_label_map[cls_label])
data.append({'boxes': [boxes], 'label': cls_label, 'score': score})
data.append({"boxes": [boxes], "label": cls_label, "score": score})
return {'name': 'prediction', 'data': data}
return {"name": "prediction", "data": data}
def _fetch_annotations(img_idx, image_path, batch, prediction_metadata_map, class_label_map):
"""Join the ground truth and prediction annotations if they exist."""
ground_truth_annotations = _format_ground_truth_annotations_for_detection(img_idx, image_path, batch,
class_label_map)
prediction_annotations = _format_prediction_annotations_for_detection(image_path, prediction_metadata_map,
class_label_map)
ground_truth_annotations = _format_ground_truth_annotations_for_detection(
img_idx, image_path, batch, class_label_map
)
prediction_annotations = _format_prediction_annotations_for_detection(
image_path, prediction_metadata_map, class_label_map
)
annotations = [
annotation for annotation in [ground_truth_annotations, prediction_annotations] if annotation is not None]
annotation for annotation in [ground_truth_annotations, prediction_annotations] if annotation is not None
]
return [annotations] if annotations else None
@ -190,8 +202,8 @@ def _create_prediction_metadata_map(model_predictions):
"""Create metadata map for model predictions by groupings them based on image ID."""
pred_metadata_map = {}
for prediction in model_predictions:
pred_metadata_map.setdefault(prediction['image_id'], [])
pred_metadata_map[prediction['image_id']].append(prediction)
pred_metadata_map.setdefault(prediction["image_id"], [])
pred_metadata_map[prediction["image_id"]].append(prediction)
return pred_metadata_map
@ -199,13 +211,9 @@ def _create_prediction_metadata_map(model_predictions):
def _log_confusion_matrix(experiment, trainer, curr_step, curr_epoch):
"""Log the confusion matrix to Comet experiment."""
conf_mat = trainer.validator.confusion_matrix.matrix
names = list(trainer.data['names'].values()) + ['background']
names = list(trainer.data["names"].values()) + ["background"]
experiment.log_confusion_matrix(
matrix=conf_mat,
labels=names,
max_categories=len(names),
epoch=curr_epoch,
step=curr_step,
matrix=conf_mat, labels=names, max_categories=len(names), epoch=curr_epoch, step=curr_step
)
@ -243,7 +251,7 @@ def _log_image_predictions(experiment, validator, curr_step):
if (batch_idx + 1) % batch_logging_interval != 0:
continue
image_paths = batch['im_file']
image_paths = batch["im_file"]
for img_idx, image_path in enumerate(image_paths):
if _comet_image_prediction_count >= max_image_predictions:
return
@ -267,28 +275,23 @@ def _log_image_predictions(experiment, validator, curr_step):
def _log_plots(experiment, trainer):
"""Logs evaluation plots and label plots for the experiment."""
plot_filenames = [trainer.save_dir / f'{plots}.png' for plots in EVALUATION_PLOT_NAMES]
plot_filenames = [trainer.save_dir / f"{plots}.png" for plots in EVALUATION_PLOT_NAMES]
_log_images(experiment, plot_filenames, None)
label_plot_filenames = [trainer.save_dir / f'{labels}.jpg' for labels in LABEL_PLOT_NAMES]
label_plot_filenames = [trainer.save_dir / f"{labels}.jpg" for labels in LABEL_PLOT_NAMES]
_log_images(experiment, label_plot_filenames, None)
def _log_model(experiment, trainer):
"""Log the best-trained model to Comet.ml."""
model_name = _get_comet_model_name()
experiment.log_model(
model_name,
file_or_folder=str(trainer.best),
file_name='best.pt',
overwrite=True,
)
experiment.log_model(model_name, file_or_folder=str(trainer.best), file_name="best.pt", overwrite=True)
def on_pretrain_routine_start(trainer):
"""Creates or resumes a CometML experiment at the start of a YOLO pre-training routine."""
experiment = comet_ml.get_global_experiment()
is_alive = getattr(experiment, 'alive', False)
is_alive = getattr(experiment, "alive", False)
if not experiment or not is_alive:
_create_experiment(trainer.args)
@ -300,17 +303,13 @@ def on_train_epoch_end(trainer):
return
metadata = _fetch_trainer_metadata(trainer)
curr_epoch = metadata['curr_epoch']
curr_step = metadata['curr_step']
curr_epoch = metadata["curr_epoch"]
curr_step = metadata["curr_step"]
experiment.log_metrics(
trainer.label_loss_items(trainer.tloss, prefix='train'),
step=curr_step,
epoch=curr_epoch,
)
experiment.log_metrics(trainer.label_loss_items(trainer.tloss, prefix="train"), step=curr_step, epoch=curr_epoch)
if curr_epoch == 1:
_log_images(experiment, trainer.save_dir.glob('train_batch*.jpg'), curr_step)
_log_images(experiment, trainer.save_dir.glob("train_batch*.jpg"), curr_step)
def on_fit_epoch_end(trainer):
@ -320,14 +319,15 @@ def on_fit_epoch_end(trainer):
return
metadata = _fetch_trainer_metadata(trainer)
curr_epoch = metadata['curr_epoch']
curr_step = metadata['curr_step']
save_assets = metadata['save_assets']
curr_epoch = metadata["curr_epoch"]
curr_step = metadata["curr_step"]
save_assets = metadata["save_assets"]
experiment.log_metrics(trainer.metrics, step=curr_step, epoch=curr_epoch)
experiment.log_metrics(trainer.lr, step=curr_step, epoch=curr_epoch)
if curr_epoch == 1:
from ultralytics.utils.torch_utils import model_info_for_loggers
experiment.log_metrics(model_info_for_loggers(trainer), step=curr_step, epoch=curr_epoch)
if not save_assets:
@ -347,8 +347,8 @@ def on_train_end(trainer):
return
metadata = _fetch_trainer_metadata(trainer)
curr_epoch = metadata['curr_epoch']
curr_step = metadata['curr_step']
curr_epoch = metadata["curr_epoch"]
curr_step = metadata["curr_step"]
plots = trainer.args.plots
_log_model(experiment, trainer)
@ -363,8 +363,13 @@ def on_train_end(trainer):
_comet_image_prediction_count = 0
callbacks = {
'on_pretrain_routine_start': on_pretrain_routine_start,
'on_train_epoch_end': on_train_epoch_end,
'on_fit_epoch_end': on_fit_epoch_end,
'on_train_end': on_train_end} if comet_ml else {}
callbacks = (
{
"on_pretrain_routine_start": on_pretrain_routine_start,
"on_train_epoch_end": on_train_epoch_end,
"on_fit_epoch_end": on_fit_epoch_end,
"on_train_end": on_train_end,
}
if comet_ml
else {}
)