Apply `ruff==0.9.0` formatting (#13486)
* Refactor code for speed and clarity * Auto-format by https://ultralytics.com/actions --------- Co-authored-by: UltralyticsAssistant <web@ultralytics.com>pull/13488/head
Glenn Jocher
GitHub
parent
6981c2742a
commit
86fd1ab270
|
|
@ -208,7 +208,7 @@ YOLOv5 has been designed to be super easy to get started and simple to learn. We
|
|||
<summary>Figure Notes</summary>
|
||||
|
||||
- **COCO AP val** denotes mAP@0.5:0.95 metric measured on the 5000-image [COCO val2017](http://cocodataset.org) dataset over various inference sizes from 256 to 1536.
|
||||
- **GPU Speed** measures average inference time per image on [COCO val2017](http://cocodataset.org) dataset using a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) V100 instance at batch-size 32.
|
||||
- **GPU Speed** measures average inference time per image on [COCO val2017](http://cocodataset.org) dataset using a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p4/) V100 instance at batch-size 32.
|
||||
- **EfficientDet** data from [google/automl](https://github.com/google/automl) at batch size 8.
|
||||
- **Reproduce** by `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt`
|
||||
|
||||
|
|
@ -235,7 +235,7 @@ YOLOv5 has been designed to be super easy to get started and simple to learn. We
|
|||
|
||||
- All checkpoints are trained to 300 epochs with default settings. Nano and Small models use [hyp.scratch-low.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-low.yaml) hyps, all others use [hyp.scratch-high.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-high.yaml).
|
||||
- **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset.<br>Reproduce by `python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65`
|
||||
- **Speed** averaged over COCO val images using a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) instance. NMS times (~1 ms/img) not included.<br>Reproduce by `python val.py --data coco.yaml --img 640 --task speed --batch 1`
|
||||
- **Speed** averaged over COCO val images using a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p4/) instance. NMS times (~1 ms/img) not included.<br>Reproduce by `python val.py --data coco.yaml --img 640 --task speed --batch 1`
|
||||
- **TTA** [Test Time Augmentation](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation/) includes reflection and scale augmentations.<br>Reproduce by `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment`
|
||||
|
||||
</details>
|
||||
|
|
|
|||
|
|
@ -207,7 +207,7 @@ YOLOv5 超级容易上手，简单易学。我们优先考虑现实世界的结
|
|||
<summary>图表笔记</summary>
|
||||
|
||||
- **COCO AP val** 表示 mAP@0.5:0.95 指标，在 [COCO val2017](http://cocodataset.org) 数据集的 5000 张图像上测得， 图像包含 256 到 1536 各种推理大小。
|
||||
- **显卡推理速度** 为在 [COCO val2017](http://cocodataset.org) 数据集上的平均推理时间，使用 [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) V100实例，batchsize 为 32 。
|
||||
- **显卡推理速度** 为在 [COCO val2017](http://cocodataset.org) 数据集上的平均推理时间，使用 [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p4/) V100实例，batchsize 为 32 。
|
||||
- **EfficientDet** 数据来自 [google/automl](https://github.com/google/automl) ， batchsize 为32。
|
||||
- **复现命令** 为 `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt`
|
||||
|
||||
|
|
@ -234,7 +234,7 @@ YOLOv5 超级容易上手，简单易学。我们优先考虑现实世界的结
|
|||
|
||||
- 所有模型都使用默认配置，训练 300 epochs。n和s模型使用 [hyp.scratch-low.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-low.yaml) ，其他模型都使用 [hyp.scratch-high.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-high.yaml) 。
|
||||
- \*\*mAP<sup>val</sup>\*\*在单模型单尺度上计算，数据集使用 [COCO val2017](http://cocodataset.org) 。<br>复现命令 `python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65`
|
||||
- **推理速度**在 COCO val 图像总体时间上进行平均得到，测试环境使用[AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/)实例。 NMS 时间 (大约 1 ms/img) 不包括在内。<br>复现命令 `python val.py --data coco.yaml --img 640 --task speed --batch 1`
|
||||
- **推理速度**在 COCO val 图像总体时间上进行平均得到，测试环境使用[AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p4/)实例。 NMS 时间 (大约 1 ms/img) 不包括在内。<br>复现命令 `python val.py --data coco.yaml --img 640 --task speed --batch 1`
|
||||
- **TTA** [测试时数据增强](https://docs.ultralytics.com/yolov5/tutorials/test_time_augmentation/) 包括反射和尺度变换。<br>复现命令 `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment`
|
||||
|
||||
</details>
|
||||
|
|
|
|||
|
|
@ -192,7 +192,7 @@ def run(
|
|||
vid_writer[i].write(im0)
|
||||
|
||||
# Print time (inference-only)
|
||||
LOGGER.info(f"{s}{dt[1].dt * 1E3:.1f}ms")
|
||||
LOGGER.info(f"{s}{dt[1].dt * 1e3:.1f}ms")
|
||||
|
||||
# Print results
|
||||
t = tuple(x.t / seen * 1e3 for x in dt) # speeds per image
|
||||
|
|
|
|||
|
|
@ -201,10 +201,10 @@ def train(opt, device):
|
|||
scaler = amp.GradScaler(enabled=cuda)
|
||||
val = test_dir.stem # 'val' or 'test'
|
||||
LOGGER.info(
|
||||
f'Image sizes {imgsz} train, {imgsz} test\n'
|
||||
f'Using {nw * WORLD_SIZE} dataloader workers\n'
|
||||
f"Image sizes {imgsz} train, {imgsz} test\n"
|
||||
f"Using {nw * WORLD_SIZE} dataloader workers\n"
|
||||
f"Logging results to {colorstr('bold', save_dir)}\n"
|
||||
f'Starting {opt.model} training on {data} dataset with {nc} classes for {epochs} epochs...\n\n'
|
||||
f"Starting {opt.model} training on {data} dataset with {nc} classes for {epochs} epochs...\n\n"
|
||||
f"{'Epoch':>10}{'GPU_mem':>10}{'train_loss':>12}{f'{val}_loss':>12}{'top1_acc':>12}{'top5_acc':>12}"
|
||||
)
|
||||
for epoch in range(epochs): # loop over the dataset multiple times
|
||||
|
|
@ -290,13 +290,13 @@ def train(opt, device):
|
|||
# Train complete
|
||||
if RANK in {-1, 0} and final_epoch:
|
||||
LOGGER.info(
|
||||
f'\nTraining complete ({(time.time() - t0) / 3600:.3f} hours)'
|
||||
f"\nTraining complete ({(time.time() - t0) / 3600:.3f} hours)"
|
||||
f"\nResults saved to {colorstr('bold', save_dir)}"
|
||||
f'\nPredict: python classify/predict.py --weights {best} --source im.jpg'
|
||||
f'\nValidate: python classify/val.py --weights {best} --data {data_dir}'
|
||||
f'\nExport: python export.py --weights {best} --include onnx'
|
||||
f"\nPredict: python classify/predict.py --weights {best} --source im.jpg"
|
||||
f"\nValidate: python classify/val.py --weights {best} --data {data_dir}"
|
||||
f"\nExport: python export.py --weights {best} --include onnx"
|
||||
f"\nPyTorch Hub: model = torch.hub.load('ultralytics/yolov5', 'custom', '{best}')"
|
||||
f'\nVisualize: https://netron.app\n'
|
||||
f"\nVisualize: https://netron.app\n"
|
||||
)
|
||||
|
||||
# Plot examples
|
||||
|
|
|
|||
|
|
@ -309,7 +309,7 @@ def run(
|
|||
vid_writer[i].write(im0)
|
||||
|
||||
# Print time (inference-only)
|
||||
LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
|
||||
LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1e3:.1f}ms")
|
||||
|
||||
# Print results
|
||||
t = tuple(x.t / seen * 1e3 for x in dt) # speeds per image
|
||||
|
|
|
|||
|
|
@ -1471,12 +1471,12 @@ def run(
|
|||
else ""
|
||||
)
|
||||
LOGGER.info(
|
||||
f'\nExport complete ({time.time() - t:.1f}s)'
|
||||
f"\nExport complete ({time.time() - t:.1f}s)"
|
||||
f"\nResults saved to {colorstr('bold', file.parent.resolve())}"
|
||||
f"\nDetect: python {dir / ('detect.py' if det else 'predict.py')} --weights {f[-1]} {h}"
|
||||
f"\nValidate: python {dir / 'val.py'} --weights {f[-1]} {h}"
|
||||
f"\nPyTorch Hub: model = torch.hub.load('ultralytics/yolov5', 'custom', '{f[-1]}') {s}"
|
||||
f'\nVisualize: https://netron.app'
|
||||
f"\nVisualize: https://netron.app"
|
||||
)
|
||||
return f # return list of exported files/dirs
|
||||
|
||||
|
|
|
|||
|
|
@ -245,7 +245,7 @@ def run(
|
|||
vid_writer[i].write(im0)
|
||||
|
||||
# Print time (inference-only)
|
||||
LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
|
||||
LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1e3:.1f}ms")
|
||||
|
||||
# Print results
|
||||
t = tuple(x.t / seen * 1e3 for x in dt) # speeds per image
|
||||
|
|
|
|||
|
|
@ -325,10 +325,10 @@ def train(hyp, opt, device, callbacks):
|
|||
compute_loss = ComputeLoss(model, overlap=overlap) # init loss class
|
||||
# callbacks.run('on_train_start')
|
||||
LOGGER.info(
|
||||
f'Image sizes {imgsz} train, {imgsz} val\n'
|
||||
f'Using {train_loader.num_workers * WORLD_SIZE} dataloader workers\n'
|
||||
f"Image sizes {imgsz} train, {imgsz} val\n"
|
||||
f"Using {train_loader.num_workers * WORLD_SIZE} dataloader workers\n"
|
||||
f"Logging results to {colorstr('bold', save_dir)}\n"
|
||||
f'Starting training for {epochs} epochs...'
|
||||
f"Starting training for {epochs} epochs..."
|
||||
)
|
||||
for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------
|
||||
# callbacks.run('on_train_epoch_start')
|
||||
|
|
@ -405,7 +405,7 @@ def train(hyp, opt, device, callbacks):
|
|||
# Log
|
||||
if RANK in {-1, 0}:
|
||||
mloss = (mloss * i + loss_items) / (i + 1) # update mean losses
|
||||
mem = f"{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G" # (GB)
|
||||
mem = f"{torch.cuda.memory_reserved() / 1e9 if torch.cuda.is_available() else 0:.3g}G" # (GB)
|
||||
pbar.set_description(
|
||||
("%11s" * 2 + "%11.4g" * 6)
|
||||
% (f"{epoch}/{epochs - 1}", mem, *mloss, targets.shape[0], imgs.shape[-1])
|
||||
|
|
@ -740,9 +740,9 @@ def main(opt, callbacks=Callbacks()):
|
|||
# Plot results
|
||||
plot_evolve(evolve_csv)
|
||||
LOGGER.info(
|
||||
f'Hyperparameter evolution finished {opt.evolve} generations\n'
|
||||
f"Hyperparameter evolution finished {opt.evolve} generations\n"
|
||||
f"Results saved to {colorstr('bold', save_dir)}\n"
|
||||
f'Usage example: $ python train.py --hyp {evolve_yaml}'
|
||||
f"Usage example: $ python train.py --hyp {evolve_yaml}"
|
||||
)
|
||||
|
||||
|
||||
|
|
|
|||
12
train.py
12
train.py
|
|
@ -357,10 +357,10 @@ def train(hyp, opt, device, callbacks):
|
|||
compute_loss = ComputeLoss(model) # init loss class
|
||||
callbacks.run("on_train_start")
|
||||
LOGGER.info(
|
||||
f'Image sizes {imgsz} train, {imgsz} val\n'
|
||||
f'Using {train_loader.num_workers * WORLD_SIZE} dataloader workers\n'
|
||||
f"Image sizes {imgsz} train, {imgsz} val\n"
|
||||
f"Using {train_loader.num_workers * WORLD_SIZE} dataloader workers\n"
|
||||
f"Logging results to {colorstr('bold', save_dir)}\n"
|
||||
f'Starting training for {epochs} epochs...'
|
||||
f"Starting training for {epochs} epochs..."
|
||||
)
|
||||
for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------
|
||||
callbacks.run("on_train_epoch_start")
|
||||
|
|
@ -434,7 +434,7 @@ def train(hyp, opt, device, callbacks):
|
|||
# Log
|
||||
if RANK in {-1, 0}:
|
||||
mloss = (mloss * i + loss_items) / (i + 1) # update mean losses
|
||||
mem = f"{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G" # (GB)
|
||||
mem = f"{torch.cuda.memory_reserved() / 1e9 if torch.cuda.is_available() else 0:.3g}G" # (GB)
|
||||
pbar.set_description(
|
||||
("%11s" * 2 + "%11.4g" * 5)
|
||||
% (f"{epoch}/{epochs - 1}", mem, *mloss, targets.shape[0], imgs.shape[-1])
|
||||
|
|
@ -880,9 +880,9 @@ def main(opt, callbacks=Callbacks()):
|
|||
# Plot results
|
||||
plot_evolve(evolve_csv)
|
||||
LOGGER.info(
|
||||
f'Hyperparameter evolution finished {opt.evolve} generations\n'
|
||||
f"Hyperparameter evolution finished {opt.evolve} generations\n"
|
||||
f"Results saved to {colorstr('bold', save_dir)}\n"
|
||||
f'Usage example: $ python train.py --hyp {evolve_yaml}'
|
||||
f"Usage example: $ python train.py --hyp {evolve_yaml}"
|
||||
)
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -197,15 +197,7 @@ def random_perspective(
|
|||
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:
|
||||
if n := len(targets):
|
||||
use_segments = any(x.any() for x in segments) and len(segments) == n
|
||||
new = np.zeros((n, 4))
|
||||
if use_segments: # warp segments
|
||||
|
|
|
|||
|
|
@ -356,8 +356,7 @@ class LoadImages:
|
|||
else:
|
||||
self.cap = None
|
||||
assert self.nf > 0, (
|
||||
f"No images or videos found in {p}. "
|
||||
f"Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}"
|
||||
f"No images or videos found in {p}. Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}"
|
||||
)
|
||||
|
||||
def __iter__(self):
|
||||
|
|
@ -713,8 +712,8 @@ class LoadImagesAndLabels(Dataset):
|
|||
cache = mem_required * (1 + safety_margin) < mem.available # to cache or not to cache, that is the question
|
||||
if not cache:
|
||||
LOGGER.info(
|
||||
f'{prefix}{mem_required / gb:.1f}GB RAM required, '
|
||||
f'{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, '
|
||||
f"{prefix}{mem_required / gb:.1f}GB RAM required, "
|
||||
f"{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, "
|
||||
f"{'caching images ✅' if cache else 'not caching images ⚠️'}"
|
||||
)
|
||||
return cache
|
||||
|
|
@ -774,8 +773,7 @@ class LoadImagesAndLabels(Dataset):
|
|||
index = self.indices[index] # linear, shuffled, or image_weights
|
||||
|
||||
hyp = self.hyp
|
||||
mosaic = self.mosaic and random.random() < hyp["mosaic"]
|
||||
if mosaic:
|
||||
if mosaic := self.mosaic and random.random() < hyp["mosaic"]:
|
||||
# Load mosaic
|
||||
img, labels = self.load_mosaic(index)
|
||||
shapes = None
|
||||
|
|
@ -1162,8 +1160,7 @@ def verify_image_label(args):
|
|||
segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in lb] # (cls, xy1...)
|
||||
lb = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1) # (cls, xywh)
|
||||
lb = np.array(lb, dtype=np.float32)
|
||||
nl = len(lb)
|
||||
if nl:
|
||||
if nl := len(lb):
|
||||
assert lb.shape[1] == 5, f"labels require 5 columns, {lb.shape[1]} columns detected"
|
||||
assert (lb >= 0).all(), f"negative label values {lb[lb < 0]}"
|
||||
assert (lb[:, 1:] <= 1).all(), f"non-normalized or out of bounds coordinates {lb[:, 1:][lb[:, 1:] > 1]}"
|
||||
|
|
|
|||
|
|
@ -173,8 +173,7 @@ def user_config_dir(dir="Ultralytics", env_var="YOLOV5_CONFIG_DIR"):
|
|||
"""Returns user configuration directory path, preferring environment variable `YOLOV5_CONFIG_DIR` if set, else OS-
|
||||
specific.
|
||||
"""
|
||||
env = os.getenv(env_var)
|
||||
if env:
|
||||
if env := os.getenv(env_var):
|
||||
path = Path(env) # use environment variable
|
||||
else:
|
||||
cfg = {"Windows": "AppData/Roaming", "Linux": ".config", "Darwin": "Library/Application Support"} # 3 OS dirs
|
||||
|
|
@ -496,9 +495,9 @@ def check_file(file, suffix=""):
|
|||
assert Path(file).exists() and Path(file).stat().st_size > 0, f"File download failed: {url}" # check
|
||||
return file
|
||||
elif file.startswith("clearml://"): # ClearML Dataset ID
|
||||
assert (
|
||||
"clearml" in sys.modules
|
||||
), "ClearML is not installed, so cannot use ClearML dataset. Try running 'pip install clearml'."
|
||||
assert "clearml" in sys.modules, (
|
||||
"ClearML is not installed, so cannot use ClearML dataset. Try running 'pip install clearml'."
|
||||
)
|
||||
return file
|
||||
else: # search
|
||||
files = []
|
||||
|
|
|
|||
|
|
@ -41,11 +41,9 @@ def construct_dataset(clearml_info_string):
|
|||
with open(yaml_filenames[0]) as f:
|
||||
dataset_definition = yaml.safe_load(f)
|
||||
|
||||
assert set(
|
||||
dataset_definition.keys()
|
||||
).issuperset(
|
||||
{"train", "test", "val", "nc", "names"}
|
||||
), "The right keys were not found in the yaml file, make sure it at least has the following keys: ('train', 'test', 'val', 'nc', 'names')"
|
||||
assert set(dataset_definition.keys()).issuperset({"train", "test", "val", "nc", "names"}), (
|
||||
"The right keys were not found in the yaml file, make sure it at least has the following keys: ('train', 'test', 'val', 'nc', 'names')"
|
||||
)
|
||||
|
||||
data_dict = {
|
||||
"train": (
|
||||
|
|
|
|||
|
|
@ -88,14 +88,12 @@ class CometLogger:
|
|||
self.upload_dataset = self.opt.upload_dataset or COMET_UPLOAD_DATASET
|
||||
self.resume = self.opt.resume
|
||||
|
||||
# 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,
|
||||
}
|
||||
self.default_experiment_kwargs.update(experiment_kwargs)
|
||||
} | experiment_kwargs
|
||||
self.experiment = self._get_experiment(self.comet_mode, run_id)
|
||||
self.experiment.set_name(self.opt.name)
|
||||
|
||||
|
|
|
|||
|
|
@ -18,7 +18,7 @@ if str(ROOT) not in sys.path:
|
|||
RANK = int(os.getenv("RANK", -1))
|
||||
DEPRECATION_WARNING = (
|
||||
f"{colorstr('wandb')}: WARNING ⚠️ wandb is deprecated and will be removed in a future release. "
|
||||
f'See supported integrations at https://github.com/ultralytics/yolov5#integrations.'
|
||||
f"See supported integrations at https://github.com/ultralytics/yolov5#integrations."
|
||||
)
|
||||
|
||||
try:
|
||||
|
|
|
|||
|
|
@ -148,8 +148,7 @@ class ComputeLoss:
|
|||
b, a, gj, gi = indices[i] # image, anchor, gridy, gridx
|
||||
tobj = torch.zeros(pi.shape[:4], dtype=pi.dtype, device=self.device) # target obj
|
||||
|
||||
n = b.shape[0] # number of targets
|
||||
if n:
|
||||
if n := b.shape[0]:
|
||||
# pxy, pwh, _, pcls = pi[b, a, gj, gi].tensor_split((2, 4, 5), dim=1) # faster, requires torch 1.8.0
|
||||
pxy, pwh, _, pcls = pi[b, a, gj, gi].split((2, 2, 1, self.nc), 1) # target-subset of predictions
|
||||
|
||||
|
|
@ -175,10 +174,6 @@ class ComputeLoss:
|
|||
t[range(n), tcls[i]] = self.cp
|
||||
lcls += self.BCEcls(pcls, t) # BCE
|
||||
|
||||
# Append targets to text file
|
||||
# with open('targets.txt', 'a') as file:
|
||||
# [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)]
|
||||
|
||||
obji = self.BCEobj(pi[..., 4], tobj)
|
||||
lobj += obji * self.balance[i] # obj loss
|
||||
if self.autobalance:
|
||||
|
|
|
|||
|
|
@ -69,16 +69,8 @@ def random_perspective(
|
|||
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)
|
||||
new_segments = []
|
||||
if n:
|
||||
if n := len(targets):
|
||||
new = np.zeros((n, 4))
|
||||
segments = resample_segments(segments) # upsample
|
||||
for i, segment in enumerate(segments):
|
||||
|
|
|
|||
|
|
@ -132,9 +132,7 @@ class LoadImagesAndLabelsAndMasks(LoadImagesAndLabels): # for training/testing
|
|||
index = self.indices[index] # linear, shuffled, or image_weights
|
||||
|
||||
hyp = self.hyp
|
||||
mosaic = self.mosaic and random.random() < hyp["mosaic"]
|
||||
masks = []
|
||||
if mosaic:
|
||||
if mosaic := self.mosaic and random.random() < hyp["mosaic"]:
|
||||
# Load mosaic
|
||||
img, labels, segments = self.load_mosaic(index)
|
||||
shapes = None
|
||||
|
|
@ -180,6 +178,7 @@ class LoadImagesAndLabelsAndMasks(LoadImagesAndLabels): # for training/testing
|
|||
)
|
||||
|
||||
nl = len(labels) # number of labels
|
||||
masks = []
|
||||
if nl:
|
||||
labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1e-3)
|
||||
if self.overlap:
|
||||
|
|
|
|||
|
|
@ -61,8 +61,7 @@ class ComputeLoss:
|
|||
b, a, gj, gi = indices[i] # image, anchor, gridy, gridx
|
||||
tobj = torch.zeros(pi.shape[:4], dtype=pi.dtype, device=self.device) # target obj
|
||||
|
||||
n = b.shape[0] # number of targets
|
||||
if n:
|
||||
if n := b.shape[0]:
|
||||
pxy, pwh, _, pcls, pmask = pi[b, a, gj, gi].split((2, 2, 1, self.nc, nm), 1) # subset of predictions
|
||||
|
||||
# Box regression
|
||||
|
|
|
|||
|
|
@ -121,9 +121,9 @@ def select_device(device="", batch_size=0, newline=True):
|
|||
os.environ["CUDA_VISIBLE_DEVICES"] = "-1" # force torch.cuda.is_available() = False
|
||||
elif device: # non-cpu device requested
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = device # set environment variable - must be before assert is_available()
|
||||
assert torch.cuda.is_available() and torch.cuda.device_count() >= len(
|
||||
device.replace(",", "")
|
||||
), f"Invalid CUDA '--device {device}' requested, use '--device cpu' or pass valid CUDA device(s)"
|
||||
assert torch.cuda.is_available() and torch.cuda.device_count() >= len(device.replace(",", "")), (
|
||||
f"Invalid CUDA '--device {device}' requested, use '--device cpu' or pass valid CUDA device(s)"
|
||||
)
|
||||
|
||||
if not cpu and not mps and torch.cuda.is_available(): # prefer GPU if available
|
||||
devices = device.split(",") if device else "0" # range(torch.cuda.device_count()) # i.e. 0,1,6,7
|
||||
|
|
@ -380,7 +380,7 @@ def smart_optimizer(model, name="Adam", lr=0.001, momentum=0.9, decay=1e-5):
|
|||
optimizer.add_param_group({"params": g[1], "weight_decay": 0.0}) # add g1 (BatchNorm2d weights)
|
||||
LOGGER.info(
|
||||
f"{colorstr('optimizer:')} {type(optimizer).__name__}(lr={lr}) with parameter groups "
|
||||
f'{len(g[1])} weight(decay=0.0), {len(g[0])} weight(decay={decay}), {len(g[2])} bias'
|
||||
f"{len(g[1])} weight(decay=0.0), {len(g[0])} weight(decay={decay}), {len(g[2])} bias"
|
||||
)
|
||||
return optimizer
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue