ultralytics 8.0.12 - Hydra removal (#506)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Pronoy Mandal <lukex9442@gmail.com>
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
This commit is contained in:
Glenn Jocher
2023-01-21 00:45:19 +01:00
committed by GitHub
parent 6eec39162a
commit c5fccc3fc4
37 changed files with 395 additions and 469 deletions

View File

@ -29,7 +29,8 @@ from torch.utils.data import DataLoader, Dataset, dataloader, distributed
from tqdm import tqdm
from ultralytics.yolo.data.utils import check_dataset, unzip_file
from ultralytics.yolo.utils import DATASETS_DIR, LOGGER, NUM_THREADS, TQDM_BAR_FORMAT, is_colab, is_kaggle
from ultralytics.yolo.utils import (DATASETS_DIR, LOGGER, NUM_THREADS, TQDM_BAR_FORMAT, is_colab, is_dir_writeable,
is_kaggle)
from ultralytics.yolo.utils.checks import check_requirements, check_yaml
from ultralytics.yolo.utils.ops import clean_str, segments2boxes, xyn2xy, xywh2xyxy, xywhn2xyxy, xyxy2xywhn
from ultralytics.yolo.utils.torch_utils import torch_distributed_zero_first
@ -493,7 +494,7 @@ class LoadImagesAndLabels(Dataset):
cache, exists = np.load(cache_path, allow_pickle=True).item(), True # load dict
assert cache['version'] == self.cache_version # matches current version
assert cache['hash'] == get_hash(self.label_files + self.im_files) # identical hash
except (FileNotFoundError, AssertionError):
except (FileNotFoundError, AssertionError, AttributeError):
cache, exists = self.cache_labels(cache_path, prefix), False # run cache ops
# Display cache
@ -579,16 +580,17 @@ class LoadImagesAndLabels(Dataset):
b, gb = 0, 1 << 30 # bytes of cached images, bytes per gigabytes
self.im_hw0, self.im_hw = [None] * n, [None] * n
fcn = self.cache_images_to_disk if cache_images == 'disk' else self.load_image
results = ThreadPool(NUM_THREADS).imap(fcn, range(n))
pbar = tqdm(enumerate(results), total=n, bar_format=TQDM_BAR_FORMAT, disable=LOCAL_RANK > 0)
for i, x in pbar:
if cache_images == 'disk':
b += self.npy_files[i].stat().st_size
else: # 'ram'
self.ims[i], self.im_hw0[i], self.im_hw[i] = x # im, hw_orig, hw_resized = load_image(self, i)
b += self.ims[i].nbytes
pbar.desc = f'{prefix}Caching images ({b / gb:.1f}GB {cache_images})'
pbar.close()
with (Pool if n > 10000 else ThreadPool)(NUM_THREADS) as pool:
results = pool.imap(fcn, range(n))
pbar = tqdm(enumerate(results), total=n, bar_format=TQDM_BAR_FORMAT, disable=LOCAL_RANK > 0)
for i, x in pbar:
if cache_images == 'disk':
b += self.npy_files[i].stat().st_size
else: # 'ram'
self.ims[i], self.im_hw0[i], self.im_hw[i] = x # im, hw_orig, hw_resized = load_image(self, i)
b += self.ims[i].nbytes
pbar.desc = f'{prefix}Caching images ({b / gb:.1f}GB {cache_images})'
pbar.close()
def check_cache_ram(self, safety_margin=0.1, prefix=''):
# Check image caching requirements vs available memory
@ -612,11 +614,10 @@ class LoadImagesAndLabels(Dataset):
x = {} # dict
nm, nf, ne, nc, msgs = 0, 0, 0, 0, [] # number missing, found, empty, corrupt, messages
desc = f"{prefix}Scanning {path.parent / path.stem}..."
with Pool(NUM_THREADS) as pool:
pbar = tqdm(pool.imap(verify_image_label, zip(self.im_files, self.label_files, repeat(prefix))),
desc=desc,
total=len(self.im_files),
bar_format=TQDM_BAR_FORMAT)
total = len(self.im_files)
with (Pool if total > 10000 else ThreadPool)(NUM_THREADS) as pool:
results = pool.imap(verify_image_label, zip(self.im_files, self.label_files, repeat(prefix)))
pbar = tqdm(results, desc=desc, total=total, bar_format=TQDM_BAR_FORMAT)
for im_file, lb, shape, segments, nm_f, nf_f, ne_f, nc_f, msg in pbar:
nm += nm_f
nf += nf_f
@ -627,8 +628,8 @@ class LoadImagesAndLabels(Dataset):
if msg:
msgs.append(msg)
pbar.desc = f"{desc} {nf} images, {nm + ne} backgrounds, {nc} corrupt"
pbar.close()
pbar.close()
if msgs:
LOGGER.info('\n'.join(msgs))
if nf == 0:
@ -637,12 +638,12 @@ class LoadImagesAndLabels(Dataset):
x['results'] = nf, nm, ne, nc, len(self.im_files)
x['msgs'] = msgs # warnings
x['version'] = self.cache_version # cache version
try:
np.save(path, x) # save cache for next time
if is_dir_writeable(path.parent):
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}')
except Exception as e:
LOGGER.warning(f'{prefix}WARNING ⚠️ Cache directory {path.parent} is not writeable: {e}') # not writeable
else:
LOGGER.warning(f'{prefix}WARNING ⚠️ Cache directory {path.parent} is not writeable') # not writeable
return x
def __len__(self):
@ -1148,8 +1149,10 @@ class HUBDatasetStats():
continue
dataset = LoadImagesAndLabels(self.data[split]) # load dataset
desc = f'{split} images'
for _ in tqdm(ThreadPool(NUM_THREADS).imap(self._hub_ops, dataset.im_files), total=dataset.n, desc=desc):
pass
total = dataset.n
with (Pool if total > 10000 else ThreadPool)(NUM_THREADS) as pool:
for _ in tqdm(pool.imap(self._hub_ops, dataset.im_files), total=total, desc=desc):
pass
print(f'Done. All images saved to {self.im_dir}')
return self.im_dir