xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update .pre-commit-config.yaml (#1026)

Browse Source
This commit is contained in:
Glenn Jocher
2023-02-17 22:26:40 +01:00
committed by GitHub
parent 9047d737f4
commit edd3ff1669
76 changed files with 928 additions and 935 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ultralytics/yolo/v8/detect/__init__.py
View File

@ -4,4 +4,4 @@ from .predict import DetectionPredictor, predict
from .train import DetectionTrainer, train
from .val import DetectionValidator, val
__all__ = ["DetectionPredictor", "predict", "DetectionTrainer", "train", "DetectionValidator", "val"]
__all__ = ['DetectionPredictor', 'predict', 'DetectionTrainer', 'train', 'DetectionValidator', 'val']

12
ultralytics/yolo/v8/detect/predict.py
View File

@ -37,7 +37,7 @@ class DetectionPredictor(BasePredictor):
def write_results(self, idx, results, batch):
p, im, im0 = batch
log_string = ""
log_string = ''
if len(im.shape) == 3:
im = im[None] # expand for batch dim
self.seen += 1
@ -69,7 +69,7 @@ class DetectionPredictor(BasePredictor):
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if self.args.save or self.args.save_crop or self.args.show: # Add bbox to image
c = int(cls) # integer class
name = f"id:{int(d.id.item())} {self.model.names[c]}" if d.id is not None else self.model.names[c]
name = f'id:{int(d.id.item())} {self.model.names[c]}' if d.id is not None else self.model.names[c]
label = None if self.args.hide_labels else (name if self.args.hide_conf else f'{name} {conf:.2f}')
self.annotator.box_label(d.xyxy.squeeze(), label, color=colors(c, True))
if self.args.save_crop:
@ -82,9 +82,9 @@ class DetectionPredictor(BasePredictor):
def predict(cfg=DEFAULT_CFG, use_python=False):
model = cfg.model or "yolov8n.pt"
source = cfg.source if cfg.source is not None else ROOT / "assets" if (ROOT / "assets").exists() \
else "https://ultralytics.com/images/bus.jpg"
model = cfg.model or 'yolov8n.pt'
source = cfg.source if cfg.source is not None else ROOT / 'assets' if (ROOT / 'assets').exists() \
else 'https://ultralytics.com/images/bus.jpg'
args = dict(model=model, source=source)
if use_python:
@ -95,5 +95,5 @@ def predict(cfg=DEFAULT_CFG, use_python=False):
predictor.predict_cli()
if __name__ == "__main__":
if __name__ == '__main__':
predict()

44
ultralytics/yolo/v8/detect/train.py
View File

@ -20,7 +20,7 @@ from ultralytics.yolo.utils.torch_utils import de_parallel
# BaseTrainer python usage
class DetectionTrainer(BaseTrainer):
def get_dataloader(self, dataset_path, batch_size, mode="train", rank=0):
def get_dataloader(self, dataset_path, batch_size, mode='train', rank=0):
# TODO: manage splits differently
# calculate stride - check if model is initialized
gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
@ -29,21 +29,21 @@ class DetectionTrainer(BaseTrainer):
batch_size=batch_size,
stride=gs,
hyp=vars(self.args),
augment=mode == "train",
augment=mode == 'train',
cache=self.args.cache,
pad=0 if mode == "train" else 0.5,
rect=self.args.rect or mode == "val",
pad=0 if mode == 'train' else 0.5,
rect=self.args.rect or mode == 'val',
rank=rank,
workers=self.args.workers,
close_mosaic=self.args.close_mosaic != 0,
prefix=colorstr(f'{mode}: '),
shuffle=mode == "train",
shuffle=mode == 'train',
seed=self.args.seed)[0] if self.args.v5loader else \
build_dataloader(self.args, batch_size, img_path=dataset_path, stride=gs, rank=rank, mode=mode,
rect=mode == "val", names=self.data['names'])[0]
rect=mode == 'val', names=self.data['names'])[0]
def preprocess_batch(self, batch):
batch["img"] = batch["img"].to(self.device, non_blocking=True).float() / 255
batch['img'] = batch['img'].to(self.device, non_blocking=True).float() / 255
return batch
def set_model_attributes(self):
@ -51,13 +51,13 @@ class DetectionTrainer(BaseTrainer):
# self.args.box *= 3 / nl # scale to layers
# self.args.cls *= self.data["nc"] / 80 * 3 / nl # scale to classes and layers
# self.args.cls *= (self.args.imgsz / 640) ** 2 * 3 / nl # scale to image size and layers
self.model.nc = self.data["nc"] # attach number of classes to model
self.model.names = self.data["names"] # attach class names to model
self.model.nc = self.data['nc'] # attach number of classes to model
self.model.names = self.data['names'] # attach class names to model
self.model.args = self.args # attach hyperparameters to model
# TODO: self.model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc
def get_model(self, cfg=None, weights=None, verbose=True):
model = DetectionModel(cfg, ch=3, nc=self.data["nc"], verbose=verbose and RANK == -1)
model = DetectionModel(cfg, ch=3, nc=self.data['nc'], verbose=verbose and RANK == -1)
if weights:
model.load(weights)
@ -75,12 +75,12 @@ class DetectionTrainer(BaseTrainer):
self.compute_loss = Loss(de_parallel(self.model))
return self.compute_loss(preds, batch)
def label_loss_items(self, loss_items=None, prefix="train"):
def label_loss_items(self, loss_items=None, prefix='train'):
"""
Returns a loss dict with labelled training loss items tensor
"""
# Not needed for classification but necessary for segmentation & detection
keys = [f"{prefix}/{x}" for x in self.loss_names]
keys = [f'{prefix}/{x}' for x in self.loss_names]
if loss_items is not None:
loss_items = [round(float(x), 5) for x in loss_items] # convert tensors to 5 decimal place floats
return dict(zip(keys, loss_items))
@ -92,12 +92,12 @@ class DetectionTrainer(BaseTrainer):
(4 + len(self.loss_names))) % ('Epoch', 'GPU_mem', *self.loss_names, 'Instances', 'Size')
def plot_training_samples(self, batch, ni):
plot_images(images=batch["img"],
batch_idx=batch["batch_idx"],
cls=batch["cls"].squeeze(-1),
bboxes=batch["bboxes"],
paths=batch["im_file"],
fname=self.save_dir / f"train_batch{ni}.jpg")
plot_images(images=batch['img'],
batch_idx=batch['batch_idx'],
cls=batch['cls'].squeeze(-1),
bboxes=batch['bboxes'],
paths=batch['im_file'],
fname=self.save_dir / f'train_batch{ni}.jpg')
def plot_metrics(self):
plot_results(file=self.csv) # save results.png
@ -169,7 +169,7 @@ class Loss:
anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)
# targets
targets = torch.cat((batch["batch_idx"].view(-1, 1), batch["cls"].view(-1, 1), batch["bboxes"]), 1)
targets = torch.cat((batch['batch_idx'].view(-1, 1), batch['cls'].view(-1, 1), batch['bboxes']), 1)
targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
gt_labels, gt_bboxes = targets.split((1, 4), 2) # cls, xyxy
mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
@ -201,8 +201,8 @@ class Loss:
def train(cfg=DEFAULT_CFG, use_python=False):
model = cfg.model or "yolov8n.pt"
data = cfg.data or "coco128.yaml" # or yolo.ClassificationDataset("mnist")
model = cfg.model or 'yolov8n.pt'
data = cfg.data or 'coco128.yaml' # or yolo.ClassificationDataset("mnist")
device = cfg.device if cfg.device is not None else ''
args = dict(model=model, data=data, device=device)
@ -214,5 +214,5 @@ def train(cfg=DEFAULT_CFG, use_python=False):
trainer.train()
if __name__ == "__main__":
if __name__ == '__main__':
train()

64
ultralytics/yolo/v8/detect/val.py
View File

@ -28,13 +28,13 @@ class DetectionValidator(BaseValidator):
self.niou = self.iouv.numel()
def preprocess(self, batch):
batch["img"] = batch["img"].to(self.device, non_blocking=True)
batch["img"] = (batch["img"].half() if self.args.half else batch["img"].float()) / 255
for k in ["batch_idx", "cls", "bboxes"]:
batch['img'] = batch['img'].to(self.device, non_blocking=True)
batch['img'] = (batch['img'].half() if self.args.half else batch['img'].float()) / 255
for k in ['batch_idx', 'cls', 'bboxes']:
batch[k] = batch[k].to(self.device)
nb = len(batch["img"])
self.lb = [torch.cat([batch["cls"], batch["bboxes"]], dim=-1)[batch["batch_idx"] == i]
nb = len(batch['img'])
self.lb = [torch.cat([batch['cls'], batch['bboxes']], dim=-1)[batch['batch_idx'] == i]
for i in range(nb)] if self.args.save_hybrid else [] # for autolabelling
return batch
@ -54,7 +54,7 @@ class DetectionValidator(BaseValidator):
self.stats = []
def get_desc(self):
return ('%22s' + '%11s' * 6) % ('Class', 'Images', 'Instances', 'Box(P', "R", "mAP50", "mAP50-95)")
return ('%22s' + '%11s' * 6) % ('Class', 'Images', 'Instances', 'Box(P', 'R', 'mAP50', 'mAP50-95)')
def postprocess(self, preds):
preds = ops.non_max_suppression(preds,
@ -69,11 +69,11 @@ class DetectionValidator(BaseValidator):
def update_metrics(self, preds, batch):
# Metrics
for si, pred in enumerate(preds):
idx = batch["batch_idx"] == si
cls = batch["cls"][idx]
bbox = batch["bboxes"][idx]
idx = batch['batch_idx'] == si
cls = batch['cls'][idx]
bbox = batch['bboxes'][idx]
nl, npr = cls.shape[0], pred.shape[0] # number of labels, predictions
shape = batch["ori_shape"][si]
shape = batch['ori_shape'][si]
correct_bboxes = torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device) # init
self.seen += 1
@ -88,16 +88,16 @@ class DetectionValidator(BaseValidator):
if self.args.single_cls:
pred[:, 5] = 0
predn = pred.clone()
ops.scale_boxes(batch["img"][si].shape[1:], predn[:, :4], shape,
ratio_pad=batch["ratio_pad"][si]) # native-space pred
ops.scale_boxes(batch['img'][si].shape[1:], predn[:, :4], shape,
ratio_pad=batch['ratio_pad'][si]) # native-space pred
# Evaluate
if nl:
height, width = batch["img"].shape[2:]
height, width = batch['img'].shape[2:]
tbox = ops.xywh2xyxy(bbox) * torch.tensor(
(width, height, width, height), device=self.device) # target boxes
ops.scale_boxes(batch["img"][si].shape[1:], tbox, shape,
ratio_pad=batch["ratio_pad"][si]) # native-space labels
ops.scale_boxes(batch['img'][si].shape[1:], tbox, shape,
ratio_pad=batch['ratio_pad'][si]) # native-space labels
labelsn = torch.cat((cls, tbox), 1) # native-space labels
correct_bboxes = self._process_batch(predn, labelsn)
# TODO: maybe remove these `self.` arguments as they already are member variable
@ -107,7 +107,7 @@ class DetectionValidator(BaseValidator):
# Save
if self.args.save_json:
self.pred_to_json(predn, batch["im_file"][si])
self.pred_to_json(predn, batch['im_file'][si])
# if self.args.save_txt:
# save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / f'{path.stem}.txt')
@ -120,7 +120,7 @@ class DetectionValidator(BaseValidator):
def print_results(self):
pf = '%22s' + '%11i' * 2 + '%11.3g' * len(self.metrics.keys) # print format
self.logger.info(pf % ("all", self.seen, self.nt_per_class.sum(), *self.metrics.mean_results()))
self.logger.info(pf % ('all', self.seen, self.nt_per_class.sum(), *self.metrics.mean_results()))
if self.nt_per_class.sum() == 0:
self.logger.warning(
f'WARNING ⚠️ no labels found in {self.args.task} set, can not compute metrics without labels')
@ -175,21 +175,21 @@ class DetectionValidator(BaseValidator):
shuffle=False,
seed=self.args.seed)[0] if self.args.v5loader else \
build_dataloader(self.args, batch_size, img_path=dataset_path, stride=gs, names=self.data['names'],
mode="val")[0]
mode='val')[0]
def plot_val_samples(self, batch, ni):
plot_images(batch["img"],
batch["batch_idx"],
batch["cls"].squeeze(-1),
batch["bboxes"],
paths=batch["im_file"],
fname=self.save_dir / f"val_batch{ni}_labels.jpg",
plot_images(batch['img'],
batch['batch_idx'],
batch['cls'].squeeze(-1),
batch['bboxes'],
paths=batch['im_file'],
fname=self.save_dir / f'val_batch{ni}_labels.jpg',
names=self.names)
def plot_predictions(self, batch, preds, ni):
plot_images(batch["img"],
plot_images(batch['img'],
*output_to_target(preds, max_det=15),
paths=batch["im_file"],
paths=batch['im_file'],
fname=self.save_dir / f'val_batch{ni}_pred.jpg',
names=self.names) # pred
@ -207,8 +207,8 @@ class DetectionValidator(BaseValidator):
def eval_json(self, stats):
if self.args.save_json and self.is_coco and len(self.jdict):
anno_json = self.data['path'] / "annotations/instances_val2017.json" # annotations
pred_json = self.save_dir / "predictions.json" # predictions
anno_json = self.data['path'] / 'annotations/instances_val2017.json' # annotations
pred_json = self.save_dir / 'predictions.json' # predictions
self.logger.info(f'\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...')
try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
check_requirements('pycocotools>=2.0.6')
@ -216,7 +216,7 @@ class DetectionValidator(BaseValidator):
from pycocotools.cocoeval import COCOeval # noqa
for x in anno_json, pred_json:
assert x.is_file(), f"{x} file not found"
assert x.is_file(), f'{x} file not found'
anno = COCO(str(anno_json)) # init annotations api
pred = anno.loadRes(str(pred_json)) # init predictions api (must pass string, not Path)
eval = COCOeval(anno, pred, 'bbox')
@ -232,8 +232,8 @@ class DetectionValidator(BaseValidator):
def val(cfg=DEFAULT_CFG, use_python=False):
model = cfg.model or "yolov8n.pt"
data = cfg.data or "coco128.yaml"
model = cfg.model or 'yolov8n.pt'
data = cfg.data or 'coco128.yaml'
args = dict(model=model, data=data)
if use_python:
@ -244,5 +244,5 @@ def val(cfg=DEFAULT_CFG, use_python=False):
validator(model=args['model'])
if __name__ == "__main__":
if __name__ == '__main__':
val()