Ankle/yolov5_ZWgra
1
0 Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity

Update Actions with Lychee and GitHub Token (#12592)

Browse Source 
* Add Ultralytics Actions

* Auto-format by Ultralytics actions

* Update format.yml

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

---------

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Paula DerrengerUltralyticsAssistantGlenn Jocher
 authored and GitHub committed 2024-01-08 01:29:14 +01:00
1 parent f56355d321
commit ad97dc6a6d
47 files changed
+4217 -3462
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

utils/loggers/comet/__init__.py
+125 -118
View File
@@ -17,7 +17,7 @@ try:
# Project Configuration
config = comet_ml.config.get_config()
COMET_PROJECT_NAME = config.get_string(os.getenv('COMET_PROJECT_NAME'), 'comet.project_name', default='yolov5')
COMET_PROJECT_NAME = config.get_string(os.getenv("COMET_PROJECT_NAME"), "comet.project_name", default="yolov5")
except ImportError:
comet_ml = None
COMET_PROJECT_NAME = None
@@ -31,42 +31,40 @@ from utils.dataloaders import img2label_paths
from utils.general import check_dataset, scale_boxes, xywh2xyxy
from utils.metrics import box_iou
COMET_PREFIX = 'comet://'
COMET_PREFIX = "comet://"
COMET_MODE = os.getenv('COMET_MODE', 'online')
COMET_MODE = os.getenv("COMET_MODE", "online")
# Model Saving Settings
COMET_MODEL_NAME = os.getenv('COMET_MODEL_NAME', 'yolov5')
COMET_MODEL_NAME = os.getenv("COMET_MODEL_NAME", "yolov5")
# Dataset Artifact Settings
COMET_UPLOAD_DATASET = os.getenv('COMET_UPLOAD_DATASET', 'false').lower() == 'true'
COMET_UPLOAD_DATASET = os.getenv("COMET_UPLOAD_DATASET", "false").lower() == "true"
# Evaluation Settings
COMET_LOG_CONFUSION_MATRIX = (os.getenv('COMET_LOG_CONFUSION_MATRIX', 'true').lower() == 'true')
COMET_LOG_PREDICTIONS = os.getenv('COMET_LOG_PREDICTIONS', 'true').lower() == 'true'
COMET_MAX_IMAGE_UPLOADS = int(os.getenv('COMET_MAX_IMAGE_UPLOADS', 100))
COMET_LOG_CONFUSION_MATRIX = os.getenv("COMET_LOG_CONFUSION_MATRIX", "true").lower() == "true"
COMET_LOG_PREDICTIONS = os.getenv("COMET_LOG_PREDICTIONS", "true").lower() == "true"
COMET_MAX_IMAGE_UPLOADS = int(os.getenv("COMET_MAX_IMAGE_UPLOADS", 100))
# Confusion Matrix Settings
CONF_THRES = float(os.getenv('CONF_THRES', 0.001))
IOU_THRES = float(os.getenv('IOU_THRES', 0.6))
CONF_THRES = float(os.getenv("CONF_THRES", 0.001))
IOU_THRES = float(os.getenv("IOU_THRES", 0.6))
# Batch Logging Settings
COMET_LOG_BATCH_METRICS = (os.getenv('COMET_LOG_BATCH_METRICS', 'false').lower() == 'true')
COMET_BATCH_LOGGING_INTERVAL = os.getenv('COMET_BATCH_LOGGING_INTERVAL', 1)
COMET_PREDICTION_LOGGING_INTERVAL = os.getenv('COMET_PREDICTION_LOGGING_INTERVAL', 1)
COMET_LOG_PER_CLASS_METRICS = (os.getenv('COMET_LOG_PER_CLASS_METRICS', 'false').lower() == 'true')
COMET_LOG_BATCH_METRICS = os.getenv("COMET_LOG_BATCH_METRICS", "false").lower() == "true"
COMET_BATCH_LOGGING_INTERVAL = os.getenv("COMET_BATCH_LOGGING_INTERVAL", 1)
COMET_PREDICTION_LOGGING_INTERVAL = os.getenv("COMET_PREDICTION_LOGGING_INTERVAL", 1)
COMET_LOG_PER_CLASS_METRICS = os.getenv("COMET_LOG_PER_CLASS_METRICS", "false").lower() == "true"
RANK = int(os.getenv('RANK', -1))
RANK = int(os.getenv("RANK", -1))
to_pil = T.ToPILImage()
class CometLogger:
"""Log metrics, parameters, source code, models and much more
with Comet
"""
"""Log metrics, parameters, source code, models and much more with Comet."""
def __init__(self, opt, hyp, run_id=None, job_type='Training', **experiment_kwargs) -> None:
def __init__(self, opt, hyp, run_id=None, job_type="Training", **experiment_kwargs) -> None:
self.job_type = job_type
self.opt = opt
self.hyp = hyp
@@ -87,57 +85,58 @@ class CometLogger:
# Default parameters to pass to Experiment objects
self.default_experiment_kwargs = {
'log_code': False,
'log_env_gpu': True,
'log_env_cpu': True,
'project_name': COMET_PROJECT_NAME, }
"log_code": False,
"log_env_gpu": True,
"log_env_cpu": True,
"project_name": COMET_PROJECT_NAME,
}
self.default_experiment_kwargs.update(experiment_kwargs)
self.experiment = self._get_experiment(self.comet_mode, run_id)
self.experiment.set_name(self.opt.name)
self.data_dict = self.check_dataset(self.opt.data)
self.class_names = self.data_dict['names']
self.num_classes = self.data_dict['nc']
self.class_names = self.data_dict["names"]
self.num_classes = self.data_dict["nc"]
self.logged_images_count = 0
self.max_images = COMET_MAX_IMAGE_UPLOADS
if run_id is None:
self.experiment.log_other('Created from', 'YOLOv5')
self.experiment.log_other("Created from", "YOLOv5")
if not isinstance(self.experiment, comet_ml.OfflineExperiment):
workspace, project_name, experiment_id = self.experiment.url.split('/')[-3:]
workspace, project_name, experiment_id = self.experiment.url.split("/")[-3:]
self.experiment.log_other(
'Run Path',
f'{workspace}/{project_name}/{experiment_id}',
"Run Path",
f"{workspace}/{project_name}/{experiment_id}",
)
self.log_parameters(vars(opt))
self.log_parameters(self.opt.hyp)
self.log_asset_data(
self.opt.hyp,
name='hyperparameters.json',
metadata={'type': 'hyp-config-file'},
name="hyperparameters.json",
metadata={"type": "hyp-config-file"},
)
self.log_asset(
f'{self.opt.save_dir}/opt.yaml',
metadata={'type': 'opt-config-file'},
f"{self.opt.save_dir}/opt.yaml",
metadata={"type": "opt-config-file"},
)
self.comet_log_confusion_matrix = COMET_LOG_CONFUSION_MATRIX
if hasattr(self.opt, 'conf_thres'):
if hasattr(self.opt, "conf_thres"):
self.conf_thres = self.opt.conf_thres
else:
self.conf_thres = CONF_THRES
if hasattr(self.opt, 'iou_thres'):
if hasattr(self.opt, "iou_thres"):
self.iou_thres = self.opt.iou_thres
else:
self.iou_thres = IOU_THRES
self.log_parameters({'val_iou_threshold': self.iou_thres, 'val_conf_threshold': self.conf_thres})
self.log_parameters({"val_iou_threshold": self.iou_thres, "val_conf_threshold": self.conf_thres})
self.comet_log_predictions = COMET_LOG_PREDICTIONS
if self.opt.bbox_interval == -1:
self.comet_log_prediction_interval = (1 if self.opt.epochs < 10 else self.opt.epochs // 10)
self.comet_log_prediction_interval = 1 if self.opt.epochs < 10 else self.opt.epochs // 10
else:
self.comet_log_prediction_interval = self.opt.bbox_interval
@@ -147,30 +146,35 @@ class CometLogger:
self.comet_log_per_class_metrics = COMET_LOG_PER_CLASS_METRICS
self.experiment.log_others({
'comet_mode': COMET_MODE,
'comet_max_image_uploads': COMET_MAX_IMAGE_UPLOADS,
'comet_log_per_class_metrics': COMET_LOG_PER_CLASS_METRICS,
'comet_log_batch_metrics': COMET_LOG_BATCH_METRICS,
'comet_log_confusion_matrix': COMET_LOG_CONFUSION_MATRIX,
'comet_model_name': COMET_MODEL_NAME, })
self.experiment.log_others(
{
"comet_mode": COMET_MODE,
"comet_max_image_uploads": COMET_MAX_IMAGE_UPLOADS,
"comet_log_per_class_metrics": COMET_LOG_PER_CLASS_METRICS,
"comet_log_batch_metrics": COMET_LOG_BATCH_METRICS,
"comet_log_confusion_matrix": COMET_LOG_CONFUSION_MATRIX,
"comet_model_name": COMET_MODEL_NAME,
}
)
# Check if running the Experiment with the Comet Optimizer
if hasattr(self.opt, 'comet_optimizer_id'):
self.experiment.log_other('optimizer_id', self.opt.comet_optimizer_id)
self.experiment.log_other('optimizer_objective', self.opt.comet_optimizer_objective)
self.experiment.log_other('optimizer_metric', self.opt.comet_optimizer_metric)
self.experiment.log_other('optimizer_parameters', json.dumps(self.hyp))
if hasattr(self.opt, "comet_optimizer_id"):
self.experiment.log_other("optimizer_id", self.opt.comet_optimizer_id)
self.experiment.log_other("optimizer_objective", self.opt.comet_optimizer_objective)
self.experiment.log_other("optimizer_metric", self.opt.comet_optimizer_metric)
self.experiment.log_other("optimizer_parameters", json.dumps(self.hyp))
def _get_experiment(self, mode, experiment_id=None):
if mode == 'offline':
if mode == "offline":
if experiment_id is not None:
return comet_ml.ExistingOfflineExperiment(
previous_experiment=experiment_id,
**self.default_experiment_kwargs,
)
return comet_ml.OfflineExperiment(**self.default_experiment_kwargs, )
return comet_ml.OfflineExperiment(
**self.default_experiment_kwargs,
)
else:
try:
@@ -183,11 +187,13 @@ class CometLogger:
return comet_ml.Experiment(**self.default_experiment_kwargs)
except ValueError:
logger.warning('COMET WARNING: '
'Comet credentials have not been set. '
'Comet will default to offline logging. '
'Please set your credentials to enable online logging.')
return self._get_experiment('offline', experiment_id)
logger.warning(
"COMET WARNING: "
"Comet credentials have not been set. "
"Comet will default to offline logging. "
"Please set your credentials to enable online logging."
)
return self._get_experiment("offline", experiment_id)
return
@@ -211,12 +217,13 @@ class CometLogger:
return
model_metadata = {
'fitness_score': fitness_score[-1],
'epochs_trained': epoch + 1,
'save_period': opt.save_period,
'total_epochs': opt.epochs, }
"fitness_score": fitness_score[-1],
"epochs_trained": epoch + 1,
"save_period": opt.save_period,
"total_epochs": opt.epochs,
}
model_files = glob.glob(f'{path}/*.pt')
model_files = glob.glob(f"{path}/*.pt")
for model_path in model_files:
name = Path(model_path).name
@@ -232,14 +239,14 @@ class CometLogger:
with open(data_file) as f:
data_config = yaml.safe_load(f)
path = data_config.get('path')
path = data_config.get("path")
if path and path.startswith(COMET_PREFIX):
path = data_config['path'].replace(COMET_PREFIX, '')
path = data_config["path"].replace(COMET_PREFIX, "")
data_dict = self.download_dataset_artifact(path)
return data_dict
self.log_asset(self.opt.data, metadata={'type': 'data-config-file'})
self.log_asset(self.opt.data, metadata={"type": "data-config-file"})
return check_dataset(data_file)
@@ -255,8 +262,8 @@ class CometLogger:
filtered_detections = detections[mask]
filtered_labels = labelsn[mask]
image_id = path.split('/')[-1].split('.')[0]
image_name = f'{image_id}_curr_epoch_{self.experiment.curr_epoch}'
image_id = path.split("/")[-1].split(".")[0]
image_name = f"{image_id}_curr_epoch_{self.experiment.curr_epoch}"
if image_name not in self.logged_image_names:
native_scale_image = PIL.Image.open(path)
self.log_image(native_scale_image, name=image_name)
@@ -264,23 +271,21 @@ class CometLogger:
metadata = []
for cls, *xyxy in filtered_labels.tolist():
metadata.append({
'label': f'{self.class_names[int(cls)]}-gt',
'score': 100,
'box': {
'x': xyxy[0],
'y': xyxy[1],
'x2': xyxy[2],
'y2': xyxy[3]}, })
metadata.append(
{
"label": f"{self.class_names[int(cls)]}-gt",
"score": 100,
"box": {"x": xyxy[0], "y": xyxy[1], "x2": xyxy[2], "y2": xyxy[3]},
}
)
for *xyxy, conf, cls in filtered_detections.tolist():
metadata.append({
'label': f'{self.class_names[int(cls)]}',
'score': conf * 100,
'box': {
'x': xyxy[0],
'y': xyxy[1],
'x2': xyxy[2],
'y2': xyxy[3]}, })
metadata.append(
{
"label": f"{self.class_names[int(cls)]}",
"score": conf * 100,
"box": {"x": xyxy[0], "y": xyxy[1], "x2": xyxy[2], "y2": xyxy[3]},
}
)
self.metadata_dict[image_name] = metadata
self.logged_images_count += 1
@@ -307,7 +312,7 @@ class CometLogger:
return predn, labelsn
def add_assets_to_artifact(self, artifact, path, asset_path, split):
img_paths = sorted(glob.glob(f'{asset_path}/*'))
img_paths = sorted(glob.glob(f"{asset_path}/*"))
label_paths = img2label_paths(img_paths)
for image_file, label_file in zip(img_paths, label_paths):
@@ -317,33 +322,33 @@ class CometLogger:
artifact.add(
image_file,
logical_path=image_logical_path,
metadata={'split': split},
metadata={"split": split},
)
artifact.add(
label_file,
logical_path=label_logical_path,
metadata={'split': split},
metadata={"split": split},
)
except ValueError as e:
logger.error('COMET ERROR: Error adding file to Artifact. Skipping file.')
logger.error(f'COMET ERROR: {e}')
logger.error("COMET ERROR: Error adding file to Artifact. Skipping file.")
logger.error(f"COMET ERROR: {e}")
continue
return artifact
def upload_dataset_artifact(self):
dataset_name = self.data_dict.get('dataset_name', 'yolov5-dataset')
path = str((ROOT / Path(self.data_dict['path'])).resolve())
dataset_name = self.data_dict.get("dataset_name", "yolov5-dataset")
path = str((ROOT / Path(self.data_dict["path"])).resolve())
metadata = self.data_dict.copy()
for key in ['train', 'val', 'test']:
for key in ["train", "val", "test"]:
split_path = metadata.get(key)
if split_path is not None:
metadata[key] = split_path.replace(path, '')
metadata[key] = split_path.replace(path, "")
artifact = comet_ml.Artifact(name=dataset_name, artifact_type='dataset', metadata=metadata)
artifact = comet_ml.Artifact(name=dataset_name, artifact_type="dataset", metadata=metadata)
for key in metadata.keys():
if key in ['train', 'val', 'test']:
if key in ["train", "val", "test"]:
if isinstance(self.upload_dataset, str) and (key != self.upload_dataset):
continue
@@ -362,26 +367,27 @@ class CometLogger:
metadata = logged_artifact.metadata
data_dict = metadata.copy()
data_dict['path'] = artifact_save_dir
data_dict["path"] = artifact_save_dir
metadata_names = metadata.get('names')
metadata_names = metadata.get("names")
if isinstance(metadata_names, dict):
data_dict['names'] = {int(k): v for k, v in metadata.get('names').items()}
data_dict["names"] = {int(k): v for k, v in metadata.get("names").items()}
elif isinstance(metadata_names, list):
data_dict['names'] = {int(k): v for k, v in zip(range(len(metadata_names)), metadata_names)}
data_dict["names"] = {int(k): v for k, v in zip(range(len(metadata_names)), metadata_names)}
else:
raise "Invalid 'names' field in dataset yaml file. Please use a list or dictionary"
return self.update_data_paths(data_dict)
def update_data_paths(self, data_dict):
path = data_dict.get('path', '')
path = data_dict.get("path", "")
for split in ['train', 'val', 'test']:
for split in ["train", "val", "test"]:
if data_dict.get(split):
split_path = data_dict.get(split)
data_dict[split] = (f'{path}/{split_path}' if isinstance(split, str) else [
f'{path}/{x}' for x in split_path])
data_dict[split] = (
f"{path}/{split_path}" if isinstance(split, str) else [f"{path}/{x}" for x in split_path]
)
return data_dict
@@ -422,11 +428,11 @@ class CometLogger:
def on_train_end(self, files, save_dir, last, best, epoch, results):
if self.comet_log_predictions:
curr_epoch = self.experiment.curr_epoch
self.experiment.log_asset_data(self.metadata_dict, 'image-metadata.json', epoch=curr_epoch)
self.experiment.log_asset_data(self.metadata_dict, "image-metadata.json", epoch=curr_epoch)
for f in files:
self.log_asset(f, metadata={'epoch': epoch})
self.log_asset(f'{save_dir}/results.csv', metadata={'epoch': epoch})
self.log_asset(f, metadata={"epoch": epoch})
self.log_asset(f"{save_dir}/results.csv", metadata={"epoch": epoch})
if not self.opt.evolve:
model_path = str(best if best.exists() else last)
@@ -440,9 +446,9 @@ class CometLogger:
)
# Check if running Experiment with Comet Optimizer
if hasattr(self.opt, 'comet_optimizer_id'):
if hasattr(self.opt, "comet_optimizer_id"):
metric = results.get(self.opt.comet_optimizer_metric)
self.experiment.log_other('optimizer_metric_value', metric)
self.experiment.log_other("optimizer_metric_value", metric)
self.finish_run()
@@ -477,21 +483,22 @@ class CometLogger:
class_name = self.class_names[c]
self.experiment.log_metrics(
{
'mAP@.5': ap50[i],
'mAP@.5:.95': ap[i],
'precision': p[i],
'recall': r[i],
'f1': f1[i],
'true_positives': tp[i],
'false_positives': fp[i],
'support': nt[c], },
"mAP@.5": ap50[i],
"mAP@.5:.95": ap[i],
"precision": p[i],
"recall": r[i],
"f1": f1[i],
"true_positives": tp[i],
"false_positives": fp[i],
"support": nt[c],
},
prefix=class_name,
)
if self.comet_log_confusion_matrix:
epoch = self.experiment.curr_epoch
class_names = list(self.class_names.values())
class_names.append('background')
class_names.append("background")
num_classes = len(class_names)
self.experiment.log_confusion_matrix(
@@ -499,9 +506,9 @@ class CometLogger:
max_categories=num_classes,
labels=class_names,
epoch=epoch,
column_label='Actual Category',
row_label='Predicted Category',
file_name=f'confusion-matrix-epoch-{epoch}.json',
column_label="Actual Category",
row_label="Predicted Category",
file_name=f"confusion-matrix-epoch-{epoch}.json",
)
def on_fit_epoch_end(self, result, epoch):
utils/loggers/comet/comet_utils.py
+27 -27
View File
@@ -11,28 +11,28 @@ import yaml
logger = logging.getLogger(__name__)
COMET_PREFIX = 'comet://'
COMET_MODEL_NAME = os.getenv('COMET_MODEL_NAME', 'yolov5')
COMET_DEFAULT_CHECKPOINT_FILENAME = os.getenv('COMET_DEFAULT_CHECKPOINT_FILENAME', 'last.pt')
COMET_PREFIX = "comet://"
COMET_MODEL_NAME = os.getenv("COMET_MODEL_NAME", "yolov5")
COMET_DEFAULT_CHECKPOINT_FILENAME = os.getenv("COMET_DEFAULT_CHECKPOINT_FILENAME", "last.pt")
def download_model_checkpoint(opt, experiment):
model_dir = f'{opt.project}/{experiment.name}'
model_dir = f"{opt.project}/{experiment.name}"
os.makedirs(model_dir, exist_ok=True)
model_name = COMET_MODEL_NAME
model_asset_list = experiment.get_model_asset_list(model_name)
if len(model_asset_list) == 0:
logger.error(f'COMET ERROR: No checkpoints found for model name : {model_name}')
logger.error(f"COMET ERROR: No checkpoints found for model name : {model_name}")
return
model_asset_list = sorted(
model_asset_list,
key=lambda x: x['step'],
key=lambda x: x["step"],
reverse=True,
)
logged_checkpoint_map = {asset['fileName']: asset['assetId'] for asset in model_asset_list}
logged_checkpoint_map = {asset["fileName"]: asset["assetId"] for asset in model_asset_list}
resource_url = urlparse(opt.weights)
checkpoint_filename = resource_url.query
@@ -44,28 +44,28 @@ def download_model_checkpoint(opt, experiment):
checkpoint_filename = COMET_DEFAULT_CHECKPOINT_FILENAME
if asset_id is None:
logger.error(f'COMET ERROR: Checkpoint {checkpoint_filename} not found in the given Experiment')
logger.error(f"COMET ERROR: Checkpoint {checkpoint_filename} not found in the given Experiment")
return
try:
logger.info(f'COMET INFO: Downloading checkpoint {checkpoint_filename}')
logger.info(f"COMET INFO: Downloading checkpoint {checkpoint_filename}")
asset_filename = checkpoint_filename
model_binary = experiment.get_asset(asset_id, return_type='binary', stream=False)
model_download_path = f'{model_dir}/{asset_filename}'
with open(model_download_path, 'wb') as f:
model_binary = experiment.get_asset(asset_id, return_type="binary", stream=False)
model_download_path = f"{model_dir}/{asset_filename}"
with open(model_download_path, "wb") as f:
f.write(model_binary)
opt.weights = model_download_path
except Exception as e:
logger.warning('COMET WARNING: Unable to download checkpoint from Comet')
logger.warning("COMET WARNING: Unable to download checkpoint from Comet")
logger.exception(e)
def set_opt_parameters(opt, experiment):
"""Update the opts Namespace with parameters
from Comet's ExistingExperiment when resuming a run
"""
Update the opts Namespace with parameters from Comet's ExistingExperiment when resuming a run.
Args:
opt (argparse.Namespace): Namespace of command line options
@@ -75,9 +75,9 @@ def set_opt_parameters(opt, experiment):
resume_string = opt.resume
for asset in asset_list:
if asset['fileName'] == 'opt.yaml':
asset_id = asset['assetId']
asset_binary = experiment.get_asset(asset_id, return_type='binary', stream=False)
if asset["fileName"] == "opt.yaml":
asset_id = asset["assetId"]
asset_binary = experiment.get_asset(asset_id, return_type="binary", stream=False)
opt_dict = yaml.safe_load(asset_binary)
for key, value in opt_dict.items():
setattr(opt, key, value)
@@ -85,18 +85,18 @@ def set_opt_parameters(opt, experiment):
# Save hyperparameters to YAML file
# Necessary to pass checks in training script
save_dir = f'{opt.project}/{experiment.name}'
save_dir = f"{opt.project}/{experiment.name}"
os.makedirs(save_dir, exist_ok=True)
hyp_yaml_path = f'{save_dir}/hyp.yaml'
with open(hyp_yaml_path, 'w') as f:
hyp_yaml_path = f"{save_dir}/hyp.yaml"
with open(hyp_yaml_path, "w") as f:
yaml.dump(opt.hyp, f)
opt.hyp = hyp_yaml_path
def check_comet_weights(opt):
"""Downloads model weights from Comet and updates the
weights path to point to saved weights location
"""
Downloads model weights from Comet and updates the weights path to point to saved weights location.
Args:
opt (argparse.Namespace): Command Line arguments passed
@@ -113,7 +113,7 @@ def check_comet_weights(opt):
if opt.weights.startswith(COMET_PREFIX):
api = comet_ml.API()
resource = urlparse(opt.weights)
experiment_path = f'{resource.netloc}{resource.path}'
experiment_path = f"{resource.netloc}{resource.path}"
experiment = api.get(experiment_path)
download_model_checkpoint(opt, experiment)
return True
@@ -122,8 +122,8 @@ def check_comet_weights(opt):
def check_comet_resume(opt):
"""Restores run parameters to its original state based on the model checkpoint
and logged Experiment parameters.
"""
Restores run parameters to its original state based on the model checkpoint and logged Experiment parameters.
Args:
opt (argparse.Namespace): Command Line arguments passed
@@ -140,7 +140,7 @@ def check_comet_resume(opt):
if opt.resume.startswith(COMET_PREFIX):
api = comet_ml.API()
resource = urlparse(opt.resume)
experiment_path = f'{resource.netloc}{resource.path}'
experiment_path = f"{resource.netloc}{resource.path}"
experiment = api.get(experiment_path)
set_opt_parameters(opt, experiment)
download_model_checkpoint(opt, experiment)
utils/loggers/comet/hpo.py
+58 -56
View File
@@ -21,77 +21,79 @@ from utils.torch_utils import select_device
# Project Configuration
config = comet_ml.config.get_config()
COMET_PROJECT_NAME = config.get_string(os.getenv('COMET_PROJECT_NAME'), 'comet.project_name', default='yolov5')
COMET_PROJECT_NAME = config.get_string(os.getenv("COMET_PROJECT_NAME"), "comet.project_name", default="yolov5")
def get_args(known=False):
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='initial weights path')
parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch-low.yaml', help='hyperparameters path')
parser.add_argument('--epochs', type=int, default=300, help='total training epochs')
parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs, -1 for autobatch')
parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)')
parser.add_argument('--rect', action='store_true', help='rectangular training')
parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
parser.add_argument('--noval', action='store_true', help='only validate final epoch')
parser.add_argument('--noautoanchor', action='store_true', help='disable AutoAnchor')
parser.add_argument('--noplots', action='store_true', help='save no plot files')
parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
parser.add_argument('--cache', type=str, nargs='?', const='ram', help='--cache images in "ram" (default) or "disk"')
parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
parser.add_argument('--optimizer', type=str, choices=['SGD', 'Adam', 'AdamW'], default='SGD', help='optimizer')
parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)')
parser.add_argument('--project', default=ROOT / 'runs/train', help='save to project/name')
parser.add_argument('--name', default='exp', help='save to project/name')
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
parser.add_argument('--quad', action='store_true', help='quad dataloader')
parser.add_argument('--cos-lr', action='store_true', help='cosine LR scheduler')
parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)')
parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone=10, first3=0 1 2')
parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)')
parser.add_argument('--seed', type=int, default=0, help='Global training seed')
parser.add_argument('--local_rank', type=int, default=-1, help='Automatic DDP Multi-GPU argument, do not modify')
parser.add_argument("--weights", type=str, default=ROOT / "yolov5s.pt", help="initial weights path")
parser.add_argument("--cfg", type=str, default="", help="model.yaml path")
parser.add_argument("--data", type=str, default=ROOT / "data/coco128.yaml", help="dataset.yaml path")
parser.add_argument("--hyp", type=str, default=ROOT / "data/hyps/hyp.scratch-low.yaml", help="hyperparameters path")
parser.add_argument("--epochs", type=int, default=300, help="total training epochs")
parser.add_argument("--batch-size", type=int, default=16, help="total batch size for all GPUs, -1 for autobatch")
parser.add_argument("--imgsz", "--img", "--img-size", type=int, default=640, help="train, val image size (pixels)")
parser.add_argument("--rect", action="store_true", help="rectangular training")
parser.add_argument("--resume", nargs="?", const=True, default=False, help="resume most recent training")
parser.add_argument("--nosave", action="store_true", help="only save final checkpoint")
parser.add_argument("--noval", action="store_true", help="only validate final epoch")
parser.add_argument("--noautoanchor", action="store_true", help="disable AutoAnchor")
parser.add_argument("--noplots", action="store_true", help="save no plot files")
parser.add_argument("--evolve", type=int, nargs="?", const=300, help="evolve hyperparameters for x generations")
parser.add_argument("--bucket", type=str, default="", help="gsutil bucket")
parser.add_argument("--cache", type=str, nargs="?", const="ram", help='--cache images in "ram" (default) or "disk"')
parser.add_argument("--image-weights", action="store_true", help="use weighted image selection for training")
parser.add_argument("--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu")
parser.add_argument("--multi-scale", action="store_true", help="vary img-size +/- 50%%")
parser.add_argument("--single-cls", action="store_true", help="train multi-class data as single-class")
parser.add_argument("--optimizer", type=str, choices=["SGD", "Adam", "AdamW"], default="SGD", help="optimizer")
parser.add_argument("--sync-bn", action="store_true", help="use SyncBatchNorm, only available in DDP mode")
parser.add_argument("--workers", type=int, default=8, help="max dataloader workers (per RANK in DDP mode)")
parser.add_argument("--project", default=ROOT / "runs/train", help="save to project/name")
parser.add_argument("--name", default="exp", help="save to project/name")
parser.add_argument("--exist-ok", action="store_true", help="existing project/name ok, do not increment")
parser.add_argument("--quad", action="store_true", help="quad dataloader")
parser.add_argument("--cos-lr", action="store_true", help="cosine LR scheduler")
parser.add_argument("--label-smoothing", type=float, default=0.0, help="Label smoothing epsilon")
parser.add_argument("--patience", type=int, default=100, help="EarlyStopping patience (epochs without improvement)")
parser.add_argument("--freeze", nargs="+", type=int, default=[0], help="Freeze layers: backbone=10, first3=0 1 2")
parser.add_argument("--save-period", type=int, default=-1, help="Save checkpoint every x epochs (disabled if < 1)")
parser.add_argument("--seed", type=int, default=0, help="Global training seed")
parser.add_argument("--local_rank", type=int, default=-1, help="Automatic DDP Multi-GPU argument, do not modify")
# Weights & Biases arguments
parser.add_argument('--entity', default=None, help='W&B: Entity')
parser.add_argument('--upload_dataset', nargs='?', const=True, default=False, help='W&B: Upload data, "val" option')
parser.add_argument('--bbox_interval', type=int, default=-1, help='W&B: Set bounding-box image logging interval')
parser.add_argument('--artifact_alias', type=str, default='latest', help='W&B: Version of dataset artifact to use')
parser.add_argument("--entity", default=None, help="W&B: Entity")
parser.add_argument("--upload_dataset", nargs="?", const=True, default=False, help='W&B: Upload data, "val" option')
parser.add_argument("--bbox_interval", type=int, default=-1, help="W&B: Set bounding-box image logging interval")
parser.add_argument("--artifact_alias", type=str, default="latest", help="W&B: Version of dataset artifact to use")
# Comet Arguments
parser.add_argument('--comet_optimizer_config', type=str, help='Comet: Path to a Comet Optimizer Config File.')
parser.add_argument('--comet_optimizer_id', type=str, help='Comet: ID of the Comet Optimizer sweep.')
parser.add_argument('--comet_optimizer_objective', type=str, help="Comet: Set to 'minimize' or 'maximize'.")
parser.add_argument('--comet_optimizer_metric', type=str, help='Comet: Metric to Optimize.')
parser.add_argument('--comet_optimizer_workers',
type=int,
default=1,
help='Comet: Number of Parallel Workers to use with the Comet Optimizer.')
parser.add_argument("--comet_optimizer_config", type=str, help="Comet: Path to a Comet Optimizer Config File.")
parser.add_argument("--comet_optimizer_id", type=str, help="Comet: ID of the Comet Optimizer sweep.")
parser.add_argument("--comet_optimizer_objective", type=str, help="Comet: Set to 'minimize' or 'maximize'.")
parser.add_argument("--comet_optimizer_metric", type=str, help="Comet: Metric to Optimize.")
parser.add_argument(
"--comet_optimizer_workers",
type=int,
default=1,
help="Comet: Number of Parallel Workers to use with the Comet Optimizer.",
)
return parser.parse_known_args()[0] if known else parser.parse_args()
def run(parameters, opt):
hyp_dict = {k: v for k, v in parameters.items() if k not in ['epochs', 'batch_size']}
hyp_dict = {k: v for k, v in parameters.items() if k not in ["epochs", "batch_size"]}
opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok or opt.evolve))
opt.batch_size = parameters.get('batch_size')
opt.epochs = parameters.get('epochs')
opt.batch_size = parameters.get("batch_size")
opt.epochs = parameters.get("epochs")
device = select_device(opt.device, batch_size=opt.batch_size)
train(hyp_dict, opt, device, callbacks=Callbacks())
if __name__ == '__main__':
if __name__ == "__main__":
opt = get_args(known=True)
opt.weights = str(opt.weights)
@@ -99,7 +101,7 @@ if __name__ == '__main__':
opt.data = str(opt.data)
opt.project = str(opt.project)
optimizer_id = os.getenv('COMET_OPTIMIZER_ID')
optimizer_id = os.getenv("COMET_OPTIMIZER_ID")
if optimizer_id is None:
with open(opt.comet_optimizer_config) as f:
optimizer_config = json.load(f)
@@ -110,9 +112,9 @@ if __name__ == '__main__':
opt.comet_optimizer_id = optimizer.id
status = optimizer.status()
opt.comet_optimizer_objective = status['spec']['objective']
opt.comet_optimizer_metric = status['spec']['metric']
opt.comet_optimizer_objective = status["spec"]["objective"]
opt.comet_optimizer_metric = status["spec"]["metric"]
logger.info('COMET INFO: Starting Hyperparameter Sweep')
logger.info("COMET INFO: Starting Hyperparameter Sweep")
for parameter in optimizer.get_parameters():
run(parameter['parameters'], opt)
run(parameter["parameters"], opt)