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

212
ultralytics/data/dataset.py
View file

@ -18,7 +18,7 @@ from .base import BaseDataset
from .utils import HELP_URL, LOGGER, get_hash, img2label_paths, verify_image, verify_image_label
# Ultralytics dataset *.cache version, >= 1.0.0 for YOLOv8
DATASET_CACHE_VERSION = '1.0.3'
DATASET_CACHE_VERSION = "1.0.3"
class YOLODataset(BaseDataset):
@ -33,16 +33,16 @@ class YOLODataset(BaseDataset):
(torch.utils.data.Dataset): A PyTorch dataset object that can be used for training an object detection model.
"""
def __init__(self, *args, data=None, task='detect', **kwargs):
def __init__(self, *args, data=None, task="detect", **kwargs):
"""Initializes the YOLODataset with optional configurations for segments and keypoints."""
self.use_segments = task == 'segment'
self.use_keypoints = task == 'pose'
self.use_obb = task == 'obb'
self.use_segments = task == "segment"
self.use_keypoints = task == "pose"
self.use_obb = task == "obb"
self.data = data
assert not (self.use_segments and self.use_keypoints), 'Can not use both segments and keypoints.'
assert not (self.use_segments and self.use_keypoints), "Can not use both segments and keypoints."
super().__init__(*args, **kwargs)
def cache_labels(self, path=Path('./labels.cache')):
def cache_labels(self, path=Path("./labels.cache")):
"""
Cache dataset labels, check images and read shapes.
@ -51,19 +51,29 @@ class YOLODataset(BaseDataset):
Returns:
(dict): labels.
"""
x = {'labels': []}
x = {"labels": []}
nm, nf, ne, nc, msgs = 0, 0, 0, 0, [] # number missing, found, empty, corrupt, messages
desc = f'{self.prefix}Scanning {path.parent / path.stem}...'
desc = f"{self.prefix}Scanning {path.parent / path.stem}..."
total = len(self.im_files)
nkpt, ndim = self.data.get('kpt_shape', (0, 0))
nkpt, ndim = self.data.get("kpt_shape", (0, 0))
if self.use_keypoints and (nkpt <= 0 or ndim not in (2, 3)):
raise ValueError("'kpt_shape' in data.yaml missing or incorrect. Should be a list with [number of "
"keypoints, number of dims (2 for x,y or 3 for x,y,visible)], i.e. 'kpt_shape: [17, 3]'")
raise ValueError(
"'kpt_shape' in data.yaml missing or incorrect. Should be a list with [number of "
"keypoints, number of dims (2 for x,y or 3 for x,y,visible)], i.e. 'kpt_shape: [17, 3]'"
)
with ThreadPool(NUM_THREADS) as pool:
results = pool.imap(func=verify_image_label,
iterable=zip(self.im_files, self.label_files, repeat(self.prefix),
repeat(self.use_keypoints), repeat(len(self.data['names'])), repeat(nkpt),
repeat(ndim)))
results = pool.imap(
func=verify_image_label,
iterable=zip(
self.im_files,
self.label_files,
repeat(self.prefix),
repeat(self.use_keypoints),
repeat(len(self.data["names"])),
repeat(nkpt),
repeat(ndim),
),
)
pbar = TQDM(results, desc=desc, total=total)
for im_file, lb, shape, segments, keypoint, nm_f, nf_f, ne_f, nc_f, msg in pbar:
nm += nm_f
@ -71,7 +81,7 @@ class YOLODataset(BaseDataset):
ne += ne_f
nc += nc_f
if im_file:
x['labels'].append(
x["labels"].append(
dict(
im_file=im_file,
shape=shape,
@ -80,60 +90,63 @@ class YOLODataset(BaseDataset):
segments=segments,
keypoints=keypoint,
normalized=True,
bbox_format='xywh'))
bbox_format="xywh",
)
)
if msg:
msgs.append(msg)
pbar.desc = f'{desc} {nf} images, {nm + ne} backgrounds, {nc} corrupt'
pbar.desc = f"{desc} {nf} images, {nm + ne} backgrounds, {nc} corrupt"
pbar.close()
if msgs:
LOGGER.info('\n'.join(msgs))
LOGGER.info("\n".join(msgs))
if nf == 0:
LOGGER.warning(f'{self.prefix}WARNING ⚠️ No labels found in {path}. {HELP_URL}')
x['hash'] = get_hash(self.label_files + self.im_files)
x['results'] = nf, nm, ne, nc, len(self.im_files)
x['msgs'] = msgs # warnings
LOGGER.warning(f"{self.prefix}WARNING ⚠️ No labels found in {path}. {HELP_URL}")
x["hash"] = get_hash(self.label_files + self.im_files)
x["results"] = nf, nm, ne, nc, len(self.im_files)
x["msgs"] = msgs # warnings
save_dataset_cache_file(self.prefix, path, x)
return x
def get_labels(self):
"""Returns dictionary of labels for YOLO training."""
self.label_files = img2label_paths(self.im_files)
cache_path = Path(self.label_files[0]).parent.with_suffix('.cache')
cache_path = Path(self.label_files[0]).parent.with_suffix(".cache")
try:
cache, exists = load_dataset_cache_file(cache_path), True # attempt to load a *.cache file
assert cache['version'] == DATASET_CACHE_VERSION # matches current version
assert cache['hash'] == get_hash(self.label_files + self.im_files) # identical hash
assert cache["version"] == DATASET_CACHE_VERSION # matches current version
assert cache["hash"] == get_hash(self.label_files + self.im_files) # identical hash
except (FileNotFoundError, AssertionError, AttributeError):
cache, exists = self.cache_labels(cache_path), False # run cache ops
# Display cache
nf, nm, ne, nc, n = cache.pop('results') # found, missing, empty, corrupt, total
nf, nm, ne, nc, n = cache.pop("results") # found, missing, empty, corrupt, total
if exists and LOCAL_RANK in (-1, 0):
d = f'Scanning {cache_path}... {nf} images, {nm + ne} backgrounds, {nc} corrupt'
d = f"Scanning {cache_path}... {nf} images, {nm + ne} backgrounds, {nc} corrupt"
TQDM(None, desc=self.prefix + d, total=n, initial=n) # display results
if cache['msgs']:
LOGGER.info('\n'.join(cache['msgs'])) # display warnings
if cache["msgs"]:
LOGGER.info("\n".join(cache["msgs"])) # display warnings
# Read cache
[cache.pop(k) for k in ('hash', 'version', 'msgs')] # remove items
labels = cache['labels']
[cache.pop(k) for k in ("hash", "version", "msgs")] # remove items
labels = cache["labels"]
if not labels:
LOGGER.warning(f'WARNING ⚠️ No images found in {cache_path}, training may not work correctly. {HELP_URL}')
self.im_files = [lb['im_file'] for lb in labels] # update im_files
LOGGER.warning(f"WARNING ⚠️ No images found in {cache_path}, training may not work correctly. {HELP_URL}")
self.im_files = [lb["im_file"] for lb in labels] # update im_files
# Check if the dataset is all boxes or all segments
lengths = ((len(lb['cls']), len(lb['bboxes']), len(lb['segments'])) for lb in labels)
lengths = ((len(lb["cls"]), len(lb["bboxes"]), len(lb["segments"])) for lb in labels)
len_cls, len_boxes, len_segments = (sum(x) for x in zip(*lengths))
if len_segments and len_boxes != len_segments:
LOGGER.warning(
f'WARNING ⚠️ Box and segment counts should be equal, but got len(segments) = {len_segments}, '
f'len(boxes) = {len_boxes}. To resolve this only boxes will be used and all segments will be removed. '
'To avoid this please supply either a detect or segment dataset, not a detect-segment mixed dataset.')
f"WARNING ⚠️ Box and segment counts should be equal, but got len(segments) = {len_segments}, "
f"len(boxes) = {len_boxes}. To resolve this only boxes will be used and all segments will be removed. "
"To avoid this please supply either a detect or segment dataset, not a detect-segment mixed dataset."
)
for lb in labels:
lb['segments'] = []
lb["segments"] = []
if len_cls == 0:
LOGGER.warning(f'WARNING ⚠️ No labels found in {cache_path}, training may not work correctly. {HELP_URL}')
LOGGER.warning(f"WARNING ⚠️ No labels found in {cache_path}, training may not work correctly. {HELP_URL}")
return labels
def build_transforms(self, hyp=None):
@ -145,14 +158,17 @@ class YOLODataset(BaseDataset):
else:
transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), scaleup=False)])
transforms.append(
Format(bbox_format='xywh',
normalize=True,
return_mask=self.use_segments,
return_keypoint=self.use_keypoints,
return_obb=self.use_obb,
batch_idx=True,
mask_ratio=hyp.mask_ratio,
mask_overlap=hyp.overlap_mask))
Format(
bbox_format="xywh",
normalize=True,
return_mask=self.use_segments,
return_keypoint=self.use_keypoints,
return_obb=self.use_obb,
batch_idx=True,
mask_ratio=hyp.mask_ratio,
mask_overlap=hyp.overlap_mask,
)
)
return transforms
def close_mosaic(self, hyp):
@ -166,11 +182,11 @@ class YOLODataset(BaseDataset):
"""Custom your label format here."""
# NOTE: cls is not with bboxes now, classification and semantic segmentation need an independent cls label
# We can make it also support classification and semantic segmentation by add or remove some dict keys there.
bboxes = label.pop('bboxes')
segments = label.pop('segments', [])
keypoints = label.pop('keypoints', None)
bbox_format = label.pop('bbox_format')
normalized = label.pop('normalized')
bboxes = label.pop("bboxes")
segments = label.pop("segments", [])
keypoints = label.pop("keypoints", None)
bbox_format = label.pop("bbox_format")
normalized = label.pop("normalized")
# NOTE: do NOT resample oriented boxes
segment_resamples = 100 if self.use_obb else 1000
@ -180,7 +196,7 @@ class YOLODataset(BaseDataset):
segments = np.stack(resample_segments(segments, n=segment_resamples), axis=0)
else:
segments = np.zeros((0, segment_resamples, 2), dtype=np.float32)
label['instances'] = Instances(bboxes, segments, keypoints, bbox_format=bbox_format, normalized=normalized)
label["instances"] = Instances(bboxes, segments, keypoints, bbox_format=bbox_format, normalized=normalized)
return label
@staticmethod
@ -191,15 +207,15 @@ class YOLODataset(BaseDataset):
values = list(zip(*[list(b.values()) for b in batch]))
for i, k in enumerate(keys):
value = values[i]
if k == 'img':
if k == "img":
value = torch.stack(value, 0)
if k in ['masks', 'keypoints', 'bboxes', 'cls', 'segments', 'obb']:
if k in ["masks", "keypoints", "bboxes", "cls", "segments", "obb"]:
value = torch.cat(value, 0)
new_batch[k] = value
new_batch['batch_idx'] = list(new_batch['batch_idx'])
for i in range(len(new_batch['batch_idx'])):
new_batch['batch_idx'][i] += i # add target image index for build_targets()
new_batch['batch_idx'] = torch.cat(new_batch['batch_idx'], 0)
new_batch["batch_idx"] = list(new_batch["batch_idx"])
for i in range(len(new_batch["batch_idx"])):
new_batch["batch_idx"][i] += i # add target image index for build_targets()
new_batch["batch_idx"] = torch.cat(new_batch["batch_idx"], 0)
return new_batch
@ -219,7 +235,7 @@ class ClassificationDataset(torchvision.datasets.ImageFolder):
album_transforms (callable, optional): Albumentations transforms applied to the dataset if augment is True.
"""
def __init__(self, root, args, augment=False, cache=False, prefix=''):
def __init__(self, root, args, augment=False, cache=False, prefix=""):
"""
Initialize YOLO object with root, image size, augmentations, and cache settings.
@ -231,23 +247,28 @@ class ClassificationDataset(torchvision.datasets.ImageFolder):
"""
super().__init__(root=root)
if augment and args.fraction < 1.0: # reduce training fraction
self.samples = self.samples[:round(len(self.samples) * args.fraction)]
self.prefix = colorstr(f'{prefix}: ') if prefix else ''
self.cache_ram = cache is True or cache == 'ram'
self.cache_disk = cache == 'disk'
self.samples = self.samples[: round(len(self.samples) * args.fraction)]
self.prefix = colorstr(f"{prefix}: ") if prefix else ""
self.cache_ram = cache is True or cache == "ram"
self.cache_disk = cache == "disk"
self.samples = self.verify_images() # filter out bad images
self.samples = [list(x) + [Path(x[0]).with_suffix('.npy'), None] for x in self.samples] # file, index, npy, im
self.samples = [list(x) + [Path(x[0]).with_suffix(".npy"), None] for x in self.samples] # file, index, npy, im
scale = (1.0 - args.scale, 1.0) # (0.08, 1.0)
self.torch_transforms = classify_augmentations(size=args.imgsz,
scale=scale,
hflip=args.fliplr,
vflip=args.flipud,
erasing=args.erasing,
auto_augment=args.auto_augment,
hsv_h=args.hsv_h,
hsv_s=args.hsv_s,
hsv_v=args.hsv_v) if augment else classify_transforms(
size=args.imgsz, crop_fraction=args.crop_fraction)
self.torch_transforms = (
classify_augmentations(
size=args.imgsz,
scale=scale,
hflip=args.fliplr,
vflip=args.flipud,
erasing=args.erasing,
auto_augment=args.auto_augment,
hsv_h=args.hsv_h,
hsv_s=args.hsv_s,
hsv_v=args.hsv_v,
)
if augment
else classify_transforms(size=args.imgsz, crop_fraction=args.crop_fraction)
)
def __getitem__(self, i):
"""Returns subset of data and targets corresponding to given indices."""
@ -263,7 +284,7 @@ class ClassificationDataset(torchvision.datasets.ImageFolder):
# Convert NumPy array to PIL image
im = Image.fromarray(cv2.cvtColor(im, cv2.COLOR_BGR2RGB))
sample = self.torch_transforms(im)
return {'img': sample, 'cls': j}
return {"img": sample, "cls": j}
def __len__(self) -> int:
"""Return the total number of samples in the dataset."""
@ -271,19 +292,19 @@ class ClassificationDataset(torchvision.datasets.ImageFolder):
def verify_images(self):
"""Verify all images in dataset."""
desc = f'{self.prefix}Scanning {self.root}...'
path = Path(self.root).with_suffix('.cache') # *.cache file path
desc = f"{self.prefix}Scanning {self.root}..."
path = Path(self.root).with_suffix(".cache") # *.cache file path
with contextlib.suppress(FileNotFoundError, AssertionError, AttributeError):
cache = load_dataset_cache_file(path) # attempt to load a *.cache file
assert cache['version'] == DATASET_CACHE_VERSION # matches current version
assert cache['hash'] == get_hash([x[0] for x in self.samples]) # identical hash
nf, nc, n, samples = cache.pop('results') # found, missing, empty, corrupt, total
assert cache["version"] == DATASET_CACHE_VERSION # matches current version
assert cache["hash"] == get_hash([x[0] for x in self.samples]) # identical hash
nf, nc, n, samples = cache.pop("results") # found, missing, empty, corrupt, total
if LOCAL_RANK in (-1, 0):
d = f'{desc} {nf} images, {nc} corrupt'
d = f"{desc} {nf} images, {nc} corrupt"
TQDM(None, desc=d, total=n, initial=n)
if cache['msgs']:
LOGGER.info('\n'.join(cache['msgs'])) # display warnings
if cache["msgs"]:
LOGGER.info("\n".join(cache["msgs"])) # display warnings
return samples
# Run scan if *.cache retrieval failed
@ -298,13 +319,13 @@ class ClassificationDataset(torchvision.datasets.ImageFolder):
msgs.append(msg)
nf += nf_f
nc += nc_f
pbar.desc = f'{desc} {nf} images, {nc} corrupt'
pbar.desc = f"{desc} {nf} images, {nc} corrupt"
pbar.close()
if msgs:
LOGGER.info('\n'.join(msgs))
x['hash'] = get_hash([x[0] for x in self.samples])
x['results'] = nf, nc, len(samples), samples
x['msgs'] = msgs # warnings
LOGGER.info("\n".join(msgs))
x["hash"] = get_hash([x[0] for x in self.samples])
x["results"] = nf, nc, len(samples), samples
x["msgs"] = msgs # warnings
save_dataset_cache_file(self.prefix, path, x)
return samples
@ -312,6 +333,7 @@ class ClassificationDataset(torchvision.datasets.ImageFolder):
def load_dataset_cache_file(path):
"""Load an Ultralytics *.cache dictionary from path."""
import gc
gc.disable() # reduce pickle load time https://github.com/ultralytics/ultralytics/pull/1585
cache = np.load(str(path), allow_pickle=True).item() # load dict
gc.enable()
@ -320,15 +342,15 @@ def load_dataset_cache_file(path):
def save_dataset_cache_file(prefix, path, x):
"""Save an Ultralytics dataset *.cache dictionary x to path."""
x['version'] = DATASET_CACHE_VERSION # add cache version
x["version"] = DATASET_CACHE_VERSION # add cache version
if is_dir_writeable(path.parent):
if path.exists():
path.unlink() # remove *.cache file if exists
np.save(str(path), x) # save cache for next time
path.with_suffix('.cache.npy').rename(path) # remove .npy suffix
LOGGER.info(f'{prefix}New cache created: {path}')
path.with_suffix(".cache.npy").rename(path) # remove .npy suffix
LOGGER.info(f"{prefix}New cache created: {path}")
else:
LOGGER.warning(f'{prefix}WARNING ⚠️ Cache directory {path.parent} is not writeable, cache not saved.')
LOGGER.warning(f"{prefix}WARNING ⚠️ Cache directory {path.parent} is not writeable, cache not saved.")
# TODO: support semantic segmentation