ultralytics 8.0.126 Ray Tune refactoring (#3511)
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Glenn Jocher
GitHub
@ -33,6 +33,7 @@ import torch.cuda
|
||||
from tqdm import tqdm
|
||||
|
||||
from ultralytics import YOLO
|
||||
from ultralytics.yolo.cfg import TASK2DATA, TASK2METRIC
|
||||
from ultralytics.yolo.engine.exporter import export_formats
|
||||
from ultralytics.yolo.utils import LINUX, LOGGER, MACOS, ROOT, SETTINGS
|
||||
from ultralytics.yolo.utils.checks import check_requirements, check_yolo
|
||||
@ -96,6 +97,7 @@ def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt',
|
||||
emoji = '❎' # indicates export succeeded
|
||||
|
||||
# Predict
|
||||
assert model.task != 'pose' or i != 7, 'GraphDef Pose inference is not supported'
|
||||
assert i not in (9, 10), 'inference not supported' # Edge TPU and TF.js are unsupported
|
||||
assert i != 5 or platform.system() == 'Darwin', 'inference only supported on macOS>=10.13' # CoreML
|
||||
if not (ROOT / 'assets/bus.jpg').exists():
|
||||
@ -103,15 +105,8 @@ def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt',
|
||||
export.predict(ROOT / 'assets/bus.jpg', imgsz=imgsz, device=device, half=half)
|
||||
|
||||
# Validate
|
||||
if model.task == 'detect':
|
||||
data, key = 'coco8.yaml', 'metrics/mAP50-95(B)'
|
||||
elif model.task == 'segment':
|
||||
data, key = 'coco8-seg.yaml', 'metrics/mAP50-95(M)'
|
||||
elif model.task == 'classify':
|
||||
data, key = 'imagenet100', 'metrics/accuracy_top5'
|
||||
elif model.task == 'pose':
|
||||
data, key = 'coco8-pose.yaml', 'metrics/mAP50-95(P)'
|
||||
|
||||
data = TASK2DATA[model.task] # task to dataset, i.e. coco8.yaml for task=detect
|
||||
key = TASK2METRIC[model.task] # task to metric, i.e. metrics/mAP50-95(B) for task=detect
|
||||
results = export.val(data=data,
|
||||
batch=1,
|
||||
imgsz=imgsz,
|
||||
|
||||
@ -1,44 +1,120 @@
|
||||
# Ultralytics YOLO 🚀, AGPL-3.0 license
|
||||
from ultralytics.yolo.cfg import TASK2DATA, TASK2METRIC
|
||||
from ultralytics.yolo.utils import DEFAULT_CFG_DICT, LOGGER, NUM_THREADS
|
||||
|
||||
from ultralytics.yolo.utils import LOGGER
|
||||
|
||||
try:
|
||||
from ray import tune
|
||||
from ray.air import RunConfig, session # noqa
|
||||
from ray.air.integrations.wandb import WandbLoggerCallback # noqa
|
||||
from ray.tune.schedulers import ASHAScheduler # noqa
|
||||
from ray.tune.schedulers import AsyncHyperBandScheduler as AHB # noqa
|
||||
def run_ray_tune(model,
|
||||
space: dict = None,
|
||||
grace_period: int = 10,
|
||||
gpu_per_trial: int = None,
|
||||
max_samples: int = 10,
|
||||
**train_args):
|
||||
"""
|
||||
Runs hyperparameter tuning using Ray Tune.
|
||||
|
||||
except ImportError:
|
||||
LOGGER.info("Tuning hyperparameters requires ray/tune. Install using `pip install 'ray[tune]'`")
|
||||
tune = None
|
||||
Args:
|
||||
model (YOLO): Model to run the tuner on.
|
||||
space (dict, optional): The hyperparameter search space. Defaults to None.
|
||||
grace_period (int, optional): The grace period in epochs of the ASHA scheduler. Defaults to 10.
|
||||
gpu_per_trial (int, optional): The number of GPUs to allocate per trial. Defaults to None.
|
||||
max_samples (int, optional): The maximum number of trials to run. Defaults to 10.
|
||||
train_args (dict, optional): Additional arguments to pass to the `train()` method. Defaults to {}.
|
||||
|
||||
default_space = {
|
||||
# 'optimizer': tune.choice(['SGD', 'Adam', 'AdamW', 'NAdam', 'RAdam', 'RMSProp']),
|
||||
'lr0': tune.uniform(1e-5, 1e-1),
|
||||
'lrf': tune.uniform(0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf)
|
||||
'momentum': tune.uniform(0.6, 0.98), # SGD momentum/Adam beta1
|
||||
'weight_decay': tune.uniform(0.0, 0.001), # optimizer weight decay 5e-4
|
||||
'warmup_epochs': tune.uniform(0.0, 5.0), # warmup epochs (fractions ok)
|
||||
'warmup_momentum': tune.uniform(0.0, 0.95), # warmup initial momentum
|
||||
'box': tune.uniform(0.02, 0.2), # box loss gain
|
||||
'cls': tune.uniform(0.2, 4.0), # cls loss gain (scale with pixels)
|
||||
'hsv_h': tune.uniform(0.0, 0.1), # image HSV-Hue augmentation (fraction)
|
||||
'hsv_s': tune.uniform(0.0, 0.9), # image HSV-Saturation augmentation (fraction)
|
||||
'hsv_v': tune.uniform(0.0, 0.9), # image HSV-Value augmentation (fraction)
|
||||
'degrees': tune.uniform(0.0, 45.0), # image rotation (+/- deg)
|
||||
'translate': tune.uniform(0.0, 0.9), # image translation (+/- fraction)
|
||||
'scale': tune.uniform(0.0, 0.9), # image scale (+/- gain)
|
||||
'shear': tune.uniform(0.0, 10.0), # image shear (+/- deg)
|
||||
'perspective': tune.uniform(0.0, 0.001), # image perspective (+/- fraction), range 0-0.001
|
||||
'flipud': tune.uniform(0.0, 1.0), # image flip up-down (probability)
|
||||
'fliplr': tune.uniform(0.0, 1.0), # image flip left-right (probability)
|
||||
'mosaic': tune.uniform(0.0, 1.0), # image mixup (probability)
|
||||
'mixup': tune.uniform(0.0, 1.0), # image mixup (probability)
|
||||
'copy_paste': tune.uniform(0.0, 1.0)} # segment copy-paste (probability)
|
||||
Returns:
|
||||
(dict): A dictionary containing the results of the hyperparameter search.
|
||||
|
||||
task_metric_map = {
|
||||
'detect': 'metrics/mAP50-95(B)',
|
||||
'segment': 'metrics/mAP50-95(M)',
|
||||
'classify': 'metrics/accuracy_top1',
|
||||
'pose': 'metrics/mAP50-95(P)'}
|
||||
Raises:
|
||||
ModuleNotFoundError: If Ray Tune is not installed.
|
||||
"""
|
||||
if train_args is None:
|
||||
train_args = {}
|
||||
|
||||
try:
|
||||
from ray import tune
|
||||
from ray.air import RunConfig
|
||||
from ray.air.integrations.wandb import WandbLoggerCallback
|
||||
from ray.tune.schedulers import ASHAScheduler
|
||||
except ImportError:
|
||||
raise ModuleNotFoundError("Tuning hyperparameters requires Ray Tune. Install with: pip install 'ray[tune]'")
|
||||
|
||||
try:
|
||||
import wandb
|
||||
|
||||
assert hasattr(wandb, '__version__')
|
||||
except (ImportError, AssertionError):
|
||||
wandb = False
|
||||
|
||||
default_space = {
|
||||
# 'optimizer': tune.choice(['SGD', 'Adam', 'AdamW', 'NAdam', 'RAdam', 'RMSProp']),
|
||||
'lr0': tune.uniform(1e-5, 1e-1),
|
||||
'lrf': tune.uniform(0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf)
|
||||
'momentum': tune.uniform(0.6, 0.98), # SGD momentum/Adam beta1
|
||||
'weight_decay': tune.uniform(0.0, 0.001), # optimizer weight decay 5e-4
|
||||
'warmup_epochs': tune.uniform(0.0, 5.0), # warmup epochs (fractions ok)
|
||||
'warmup_momentum': tune.uniform(0.0, 0.95), # warmup initial momentum
|
||||
'box': tune.uniform(0.02, 0.2), # box loss gain
|
||||
'cls': tune.uniform(0.2, 4.0), # cls loss gain (scale with pixels)
|
||||
'hsv_h': tune.uniform(0.0, 0.1), # image HSV-Hue augmentation (fraction)
|
||||
'hsv_s': tune.uniform(0.0, 0.9), # image HSV-Saturation augmentation (fraction)
|
||||
'hsv_v': tune.uniform(0.0, 0.9), # image HSV-Value augmentation (fraction)
|
||||
'degrees': tune.uniform(0.0, 45.0), # image rotation (+/- deg)
|
||||
'translate': tune.uniform(0.0, 0.9), # image translation (+/- fraction)
|
||||
'scale': tune.uniform(0.0, 0.9), # image scale (+/- gain)
|
||||
'shear': tune.uniform(0.0, 10.0), # image shear (+/- deg)
|
||||
'perspective': tune.uniform(0.0, 0.001), # image perspective (+/- fraction), range 0-0.001
|
||||
'flipud': tune.uniform(0.0, 1.0), # image flip up-down (probability)
|
||||
'fliplr': tune.uniform(0.0, 1.0), # image flip left-right (probability)
|
||||
'mosaic': tune.uniform(0.0, 1.0), # image mixup (probability)
|
||||
'mixup': tune.uniform(0.0, 1.0), # image mixup (probability)
|
||||
'copy_paste': tune.uniform(0.0, 1.0)} # segment copy-paste (probability)
|
||||
|
||||
def _tune(config):
|
||||
"""
|
||||
Trains the YOLO model with the specified hyperparameters and additional arguments.
|
||||
|
||||
Args:
|
||||
config (dict): A dictionary of hyperparameters to use for training.
|
||||
|
||||
Returns:
|
||||
None.
|
||||
"""
|
||||
model._reset_callbacks()
|
||||
config.update(train_args)
|
||||
model.train(**config)
|
||||
|
||||
# Get search space
|
||||
if not space:
|
||||
space = default_space
|
||||
LOGGER.warning('WARNING ⚠️ search space not provided, using default search space.')
|
||||
|
||||
# Get dataset
|
||||
data = train_args.get('data', TASK2DATA[model.task])
|
||||
space['data'] = data
|
||||
if 'data' not in train_args:
|
||||
LOGGER.warning(f'WARNING ⚠️ data not provided, using default "data={data}".')
|
||||
|
||||
# Define the trainable function with allocated resources
|
||||
trainable_with_resources = tune.with_resources(_tune, {'cpu': NUM_THREADS, 'gpu': gpu_per_trial or 0})
|
||||
|
||||
# Define the ASHA scheduler for hyperparameter search
|
||||
asha_scheduler = ASHAScheduler(time_attr='epoch',
|
||||
metric=TASK2METRIC[model.task],
|
||||
mode='max',
|
||||
max_t=train_args.get('epochs') or DEFAULT_CFG_DICT['epochs'] or 100,
|
||||
grace_period=grace_period,
|
||||
reduction_factor=3)
|
||||
|
||||
# Define the callbacks for the hyperparameter search
|
||||
tuner_callbacks = [WandbLoggerCallback(project='YOLOv8-tune')] if wandb else []
|
||||
|
||||
# Create the Ray Tune hyperparameter search tuner
|
||||
tuner = tune.Tuner(trainable_with_resources,
|
||||
param_space=space,
|
||||
tune_config=tune.TuneConfig(scheduler=asha_scheduler, num_samples=max_samples),
|
||||
run_config=RunConfig(callbacks=tuner_callbacks, storage_path='./runs/tune'))
|
||||
|
||||
# Run the hyperparameter search
|
||||
tuner.fit()
|
||||
|
||||
# Return the results of the hyperparameter search
|
||||
return tuner.get_results()
|
||||
|
||||
Reference in New Issue
Block a user