HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.0.239 Ultralytics Actions and hub-sdk adoption (#7431)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Burhan <62214284+Burhan-Q@users.noreply.github.com>
Co-authored-by: Kayzwer <68285002+Kayzwer@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2024-01-10 03:16:08 +01:00 • committed by GitHub
parent e795277391
commit fe27db2f6e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
139 changed files with 6870 additions and 5125 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ultralytics/models/yolo/detect/__init__.py
View file

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

14
ultralytics/models/yolo/detect/predict.py
View file

@ -22,12 +22,14 @@ class DetectionPredictor(BasePredictor):
def postprocess(self, preds, img, orig_imgs):
"""Post-processes predictions and returns a list of Results objects."""
preds = ops.non_max_suppression(preds,
self.args.conf,
self.args.iou,
agnostic=self.args.agnostic_nms,
max_det=self.args.max_det,
classes=self.args.classes)
preds = ops.non_max_suppression(
preds,
self.args.conf,
self.args.iou,
agnostic=self.args.agnostic_nms,
max_det=self.args.max_det,
classes=self.args.classes,
)
if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list
orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)

84
ultralytics/models/yolo/detect/train.py
View file

@ -30,7 +30,7 @@ class DetectionTrainer(BaseTrainer):
```
"""
def build_dataset(self, img_path, mode='train', batch=None):
def build_dataset(self, img_path, mode="train", batch=None):
"""
Build YOLO Dataset.
@ -40,33 +40,37 @@ class DetectionTrainer(BaseTrainer):
batch (int, optional): Size of batches, this is for `rect`. Defaults to None.
"""
gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, rect=mode == 'val', stride=gs)
return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, rect=mode == "val", stride=gs)
def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode='train'):
def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode="train"):
"""Construct and return dataloader."""
assert mode in ['train', 'val']
assert mode in ["train", "val"]
with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP
dataset = self.build_dataset(dataset_path, mode, batch_size)
shuffle = mode == 'train'
if getattr(dataset, 'rect', False) and shuffle:
shuffle = mode == "train"
if getattr(dataset, "rect", False) and shuffle:
LOGGER.warning("WARNING ⚠️ 'rect=True' is incompatible with DataLoader shuffle, setting shuffle=False")
shuffle = False
workers = self.args.workers if mode == 'train' else self.args.workers * 2
workers = self.args.workers if mode == "train" else self.args.workers * 2
return build_dataloader(dataset, batch_size, workers, shuffle, rank) # return dataloader
def preprocess_batch(self, batch):
"""Preprocesses a batch of images by scaling and converting to float."""
batch['img'] = batch['img'].to(self.device, non_blocking=True).float() / 255
batch["img"] = batch["img"].to(self.device, non_blocking=True).float() / 255
if self.args.multi_scale:
imgs = batch['img']
sz = (random.randrange(self.args.imgsz * 0.5, self.args.imgsz * 1.5 + self.stride) // self.stride *
self.stride) # size
imgs = batch["img"]
sz = (
random.randrange(self.args.imgsz * 0.5, self.args.imgsz * 1.5 + self.stride)
// self.stride
* self.stride
) # size
sf = sz / max(imgs.shape[2:]) # scale factor
if sf != 1:
ns = [math.ceil(x * sf / self.stride) * self.stride
for x in imgs.shape[2:]] # new shape (stretched to gs-multiple)
imgs = nn.functional.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)
batch['img'] = imgs
ns = [
math.ceil(x * sf / self.stride) * self.stride for x in imgs.shape[2:]
] # new shape (stretched to gs-multiple)
imgs = nn.functional.interpolate(imgs, size=ns, mode="bilinear", align_corners=False)
batch["img"] = imgs
return batch
def set_model_attributes(self):
@ -74,33 +78,32 @@ 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):
"""Return a YOLO detection model."""
model = DetectionModel(cfg, nc=self.data['nc'], verbose=verbose and RANK == -1)
model = DetectionModel(cfg, nc=self.data["nc"], verbose=verbose and RANK == -1)
if weights:
model.load(weights)
return model
def get_validator(self):
"""Returns a DetectionValidator for YOLO model validation."""
self.loss_names = 'box_loss', 'cls_loss', 'dfl_loss'
return yolo.detect.DetectionValidator(self.test_loader,
save_dir=self.save_dir,
args=copy(self.args),
_callbacks=self.callbacks)
self.loss_names = "box_loss", "cls_loss", "dfl_loss"
return yolo.detect.DetectionValidator(
self.test_loader, save_dir=self.save_dir, args=copy(self.args), _callbacks=self.callbacks
)
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))
@ -109,18 +112,25 @@ class DetectionTrainer(BaseTrainer):
def progress_string(self):
"""Returns a formatted string of training progress with epoch, GPU memory, loss, instances and size."""
return ('\n' + '%11s' *
(4 + len(self.loss_names))) % ('Epoch', 'GPU_mem', *self.loss_names, 'Instances', 'Size')
return ("\n" + "%11s" * (4 + len(self.loss_names))) % (
"Epoch",
"GPU_mem",
*self.loss_names,
"Instances",
"Size",
)
def plot_training_samples(self, batch, ni):
"""Plots training samples with their annotations."""
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',
on_plot=self.on_plot)
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",
on_plot=self.on_plot,
)
def plot_metrics(self):
"""Plots metrics from a CSV file."""
@ -128,6 +138,6 @@ class DetectionTrainer(BaseTrainer):
def plot_training_labels(self):
"""Create a labeled training plot of the YOLO model."""
boxes = np.concatenate([lb['bboxes'] for lb in self.train_loader.dataset.labels], 0)
cls = np.concatenate([lb['cls'] for lb in self.train_loader.dataset.labels], 0)
plot_labels(boxes, cls.squeeze(), names=self.data['names'], save_dir=self.save_dir, on_plot=self.on_plot)
boxes = np.concatenate([lb["bboxes"] for lb in self.train_loader.dataset.labels], 0)
cls = np.concatenate([lb["cls"] for lb in self.train_loader.dataset.labels], 0)
plot_labels(boxes, cls.squeeze(), names=self.data["names"], save_dir=self.save_dir, on_plot=self.on_plot)

180
ultralytics/models/yolo/detect/val.py
View file

@ -34,7 +34,7 @@ class DetectionValidator(BaseValidator):
self.nt_per_class = None
self.is_coco = False
self.class_map = None
self.args.task = 'detect'
self.args.task = "detect"
self.metrics = DetMetrics(save_dir=self.save_dir, on_plot=self.on_plot)
self.iouv = torch.linspace(0.5, 0.95, 10) # iou vector for mAP@0.5:0.95
self.niou = self.iouv.numel()
@ -42,25 +42,30 @@ class DetectionValidator(BaseValidator):
def preprocess(self, batch):
"""Preprocesses batch of images for YOLO training."""
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)
if self.args.save_hybrid:
height, width = batch['img'].shape[2:]
nb = len(batch['img'])
bboxes = batch['bboxes'] * torch.tensor((width, height, width, height), device=self.device)
self.lb = [
torch.cat([batch['cls'][batch['batch_idx'] == i], bboxes[batch['batch_idx'] == i]], dim=-1)
for i in range(nb)] if self.args.save_hybrid else [] # for autolabelling
height, width = batch["img"].shape[2:]
nb = len(batch["img"])
bboxes = batch["bboxes"] * torch.tensor((width, height, width, height), device=self.device)
self.lb = (
[
torch.cat([batch["cls"][batch["batch_idx"] == i], bboxes[batch["batch_idx"] == i]], dim=-1)
for i in range(nb)
]
if self.args.save_hybrid
else []
) # for autolabelling
return batch
def init_metrics(self, model):
"""Initialize evaluation metrics for YOLO."""
val = self.data.get(self.args.split, '') # validation path
self.is_coco = isinstance(val, str) and 'coco' in val and val.endswith(f'{os.sep}val2017.txt') # is COCO
val = self.data.get(self.args.split, "") # validation path
self.is_coco = isinstance(val, str) and "coco" in val and val.endswith(f"{os.sep}val2017.txt") # is COCO
self.class_map = converter.coco80_to_coco91_class() if self.is_coco else list(range(1000))
self.args.save_json |= self.is_coco and not self.training # run on final val if training COCO
self.names = model.names
@ -74,26 +79,28 @@ class DetectionValidator(BaseValidator):
def get_desc(self):
"""Return a formatted string summarizing class metrics of YOLO model."""
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):
"""Apply Non-maximum suppression to prediction outputs."""
return ops.non_max_suppression(preds,
self.args.conf,
self.args.iou,
labels=self.lb,
multi_label=True,
agnostic=self.args.single_cls,
max_det=self.args.max_det)
return ops.non_max_suppression(
preds,
self.args.conf,
self.args.iou,
labels=self.lb,
multi_label=True,
agnostic=self.args.single_cls,
max_det=self.args.max_det,
)
def _prepare_batch(self, si, batch):
"""Prepares a batch of images and annotations for validation."""
idx = batch['batch_idx'] == si
cls = batch['cls'][idx].squeeze(-1)
bbox = batch['bboxes'][idx]
ori_shape = batch['ori_shape'][si]
imgsz = batch['img'].shape[2:]
ratio_pad = batch['ratio_pad'][si]
idx = batch["batch_idx"] == si
cls = batch["cls"][idx].squeeze(-1)
bbox = batch["bboxes"][idx]
ori_shape = batch["ori_shape"][si]
imgsz = batch["img"].shape[2:]
ratio_pad = batch["ratio_pad"][si]
if len(cls):
bbox = ops.xywh2xyxy(bbox) * torch.tensor(imgsz, device=self.device)[[1, 0, 1, 0]] # target boxes
ops.scale_boxes(imgsz, bbox, ori_shape, ratio_pad=ratio_pad) # native-space labels
@ -103,8 +110,9 @@ class DetectionValidator(BaseValidator):
def _prepare_pred(self, pred, pbatch):
"""Prepares a batch of images and annotations for validation."""
predn = pred.clone()
ops.scale_boxes(pbatch['imgsz'], predn[:, :4], pbatch['ori_shape'],
ratio_pad=pbatch['ratio_pad']) # native-space pred
ops.scale_boxes(
pbatch["imgsz"], predn[:, :4], pbatch["ori_shape"], ratio_pad=pbatch["ratio_pad"]
) # native-space pred
return predn
def update_metrics(self, preds, batch):
@ -112,19 +120,21 @@ class DetectionValidator(BaseValidator):
for si, pred in enumerate(preds):
self.seen += 1
npr = len(pred)
stat = dict(conf=torch.zeros(0, device=self.device),
pred_cls=torch.zeros(0, device=self.device),
tp=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device))
stat = dict(
conf=torch.zeros(0, device=self.device),
pred_cls=torch.zeros(0, device=self.device),
tp=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device),
)
pbatch = self._prepare_batch(si, batch)
cls, bbox = pbatch.pop('cls'), pbatch.pop('bbox')
cls, bbox = pbatch.pop("cls"), pbatch.pop("bbox")
nl = len(cls)
stat['target_cls'] = cls
stat["target_cls"] = cls
if npr == 0:
if nl:
for k in self.stats.keys():
self.stats[k].append(stat[k])
# TODO: obb has not supported confusion_matrix yet.
if self.args.plots and self.args.task != 'obb':
if self.args.plots and self.args.task != "obb":
self.confusion_matrix.process_batch(detections=None, gt_bboxes=bbox, gt_cls=cls)
continue
@ -132,24 +142,24 @@ class DetectionValidator(BaseValidator):
if self.args.single_cls:
pred[:, 5] = 0
predn = self._prepare_pred(pred, pbatch)
stat['conf'] = predn[:, 4]
stat['pred_cls'] = predn[:, 5]
stat["conf"] = predn[:, 4]
stat["pred_cls"] = predn[:, 5]
# Evaluate
if nl:
stat['tp'] = self._process_batch(predn, bbox, cls)
stat["tp"] = self._process_batch(predn, bbox, cls)
# TODO: obb has not supported confusion_matrix yet.
if self.args.plots and self.args.task != 'obb':
if self.args.plots and self.args.task != "obb":
self.confusion_matrix.process_batch(predn, bbox, cls)
for k in self.stats.keys():
self.stats[k].append(stat[k])
# 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:
file = self.save_dir / 'labels' / f'{Path(batch["im_file"][si]).stem}.txt'
self.save_one_txt(predn, self.args.save_conf, pbatch['ori_shape'], file)
file = self.save_dir / "labels" / f'{Path(batch["im_file"][si]).stem}.txt'
self.save_one_txt(predn, self.args.save_conf, pbatch["ori_shape"], file)
def finalize_metrics(self, *args, **kwargs):
"""Set final values for metrics speed and confusion matrix."""
@ -159,19 +169,19 @@ class DetectionValidator(BaseValidator):
def get_stats(self):
"""Returns metrics statistics and results dictionary."""
stats = {k: torch.cat(v, 0).cpu().numpy() for k, v in self.stats.items()} # to numpy
if len(stats) and stats['tp'].any():
if len(stats) and stats["tp"].any():
self.metrics.process(**stats)
self.nt_per_class = np.bincount(stats['target_cls'].astype(int),
minlength=self.nc) # number of targets per class
self.nt_per_class = np.bincount(
stats["target_cls"].astype(int), minlength=self.nc
) # number of targets per class
return self.metrics.results_dict
def print_results(self):
"""Prints training/validation set metrics per class."""
pf = '%22s' + '%11i' * 2 + '%11.3g' * len(self.metrics.keys) # print format
LOGGER.info(pf % ('all', self.seen, self.nt_per_class.sum(), *self.metrics.mean_results()))
pf = "%22s" + "%11i" * 2 + "%11.3g" * len(self.metrics.keys) # print format
LOGGER.info(pf % ("all", self.seen, self.nt_per_class.sum(), *self.metrics.mean_results()))
if self.nt_per_class.sum() == 0:
LOGGER.warning(
f'WARNING ⚠️ no labels found in {self.args.task} set, can not compute metrics without labels')
LOGGER.warning(f"WARNING ⚠️ no labels found in {self.args.task} set, can not compute metrics without labels")
# Print results per class
if self.args.verbose and not self.training and self.nc > 1 and len(self.stats):
@ -180,10 +190,9 @@ class DetectionValidator(BaseValidator):
if self.args.plots:
for normalize in True, False:
self.confusion_matrix.plot(save_dir=self.save_dir,
names=self.names.values(),
normalize=normalize,
on_plot=self.on_plot)
self.confusion_matrix.plot(
save_dir=self.save_dir, names=self.names.values(), normalize=normalize, on_plot=self.on_plot
)
def _process_batch(self, detections, gt_bboxes, gt_cls):
"""
@ -201,7 +210,7 @@ class DetectionValidator(BaseValidator):
iou = box_iou(gt_bboxes, detections[:, :4])
return self.match_predictions(detections[:, 5], gt_cls, iou)
def build_dataset(self, img_path, mode='val', batch=None):
def build_dataset(self, img_path, mode="val", batch=None):
"""
Build YOLO Dataset.
@ -214,28 +223,32 @@ class DetectionValidator(BaseValidator):
def get_dataloader(self, dataset_path, batch_size):
"""Construct and return dataloader."""
dataset = self.build_dataset(dataset_path, batch=batch_size, mode='val')
dataset = self.build_dataset(dataset_path, batch=batch_size, mode="val")
return build_dataloader(dataset, batch_size, self.args.workers, shuffle=False, rank=-1) # return dataloader
def plot_val_samples(self, batch, ni):
"""Plot validation image samples."""
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,
on_plot=self.on_plot)
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,
on_plot=self.on_plot,
)
def plot_predictions(self, batch, preds, ni):
"""Plots predicted bounding boxes on input images and saves the result."""
plot_images(batch['img'],
*output_to_target(preds, max_det=self.args.max_det),
paths=batch['im_file'],
fname=self.save_dir / f'val_batch{ni}_pred.jpg',
names=self.names,
on_plot=self.on_plot) # pred
plot_images(
batch["img"],
*output_to_target(preds, max_det=self.args.max_det),
paths=batch["im_file"],
fname=self.save_dir / f"val_batch{ni}_pred.jpg",
names=self.names,
on_plot=self.on_plot,
) # pred
def save_one_txt(self, predn, save_conf, shape, file):
"""Save YOLO detections to a txt file in normalized coordinates in a specific format."""
@ -243,8 +256,8 @@ class DetectionValidator(BaseValidator):
for *xyxy, conf, cls in predn.tolist():
xywh = (ops.xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
with open(file, 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
with open(file, "a") as f:
f.write(("%g " * len(line)).rstrip() % line + "\n")
def pred_to_json(self, predn, filename):
"""Serialize YOLO predictions to COCO json format."""
@ -253,28 +266,31 @@ class DetectionValidator(BaseValidator):
box = ops.xyxy2xywh(predn[:, :4]) # xywh
box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner
for p, b in zip(predn.tolist(), box.tolist()):
self.jdict.append({
'image_id': image_id,
'category_id': self.class_map[int(p[5])],
'bbox': [round(x, 3) for x in b],
'score': round(p[4], 5)})
self.jdict.append(
{
"image_id": image_id,
"category_id": self.class_map[int(p[5])],
"bbox": [round(x, 3) for x in b],
"score": round(p[4], 5),
}
)
def eval_json(self, stats):
"""Evaluates YOLO output in JSON format and returns performance statistics."""
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
LOGGER.info(f'\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...')
anno_json = self.data["path"] / "annotations/instances_val2017.json" # annotations
pred_json = self.save_dir / "predictions.json" # predictions
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')
check_requirements("pycocotools>=2.0.6")
from pycocotools.coco import COCO # noqa
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')
eval = COCOeval(anno, pred, "bbox")
if self.is_coco:
eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files] # images to eval
eval.evaluate()
@ -282,5 +298,5 @@ class DetectionValidator(BaseValidator):
eval.summarize()
stats[self.metrics.keys[-1]], stats[self.metrics.keys[-2]] = eval.stats[:2] # update mAP50-95 and mAP50
except Exception as e:
LOGGER.warning(f'pycocotools unable to run: {e}')
LOGGER.warning(f"pycocotools unable to run: {e}")
return stats