def cache_labels(self, path=Path('./labels.cache'), prefix=''):
# Cache dataset labels, check images and read shapes
x = {} # dict
nm, nf, ne, nc = 0, 0, 0, 0 # number missing, found, empty, duplicate
pbar = tqdm(zip(self.img_files, self.label_files),
desc='Scanning images',
total=len(self.img_files))
for i, (im_file, lb_file) in enumerate(pbar):
try:
# verify images
im = Image.open(im_file)
im.verify() # PIL verify
shape = exif_size(im) # image size
segments = [] # instance segments
assert (shape[0] > 9) & (shape[1] >
9), f'image size {shape} <10 pixels'
assert im.format.lower(
) in img_formats, f'invalid image format {im.format}'
# verify labels
if os.path.isfile(lb_file):
nf += 1 # label found
with open(lb_file, 'r') as f:
l = [x.split() for x in f.read().strip().splitlines()]
if any([len(x) > 8 for x in l]): # is segment
classes = np.array([x[0] for x in l],
dtype=np.float32)
segments = [
np.array(x[1:],
dtype=np.float32).reshape(-1, 2)
for x in l
] # (cls, xy1...)
l = np.concatenate((classes.reshape(
-1, 1), segments2boxes(segments)),
1) # (cls, xywh)
l = np.array(l, dtype=np.float32)
if len(l):
assert l.shape[1] == 5, 'labels require 5 columns each'
assert (l >= 0).all(), 'negative labels'
assert (l[:, 1:] <= 1).all(
), 'non-normalized or out of bounds coordinate labels'
assert np.unique(
l,
axis=0).shape[0] == l.shape[0], 'duplicate labels'
else:
ne += 1 # label empty
l = np.zeros((0, 5), dtype=np.float32)
else:
nm += 1 # label missing
l = np.zeros((0, 5), dtype=np.float32)
x[im_file] = [l, shape, segments]
except Exception as e:
nc += 1
print(
f'{prefix}WARNING: Ignoring corrupted image and/or label {im_file}: {e}'
)
pbar.desc = f"{prefix}Scanning '{path.parent / path.stem}' for images and labels... " \
f"{nf} found, {nm} missing, {ne} empty, {nc} corrupted"
if nf == 0:
print(
f'{prefix}WARNING: No labels found in {path}. See {help_url}')
x['hash'] = get_hash(self.label_files + self.img_files)
x['results'] = nf, nm, ne, nc, i + 1
x['version'] = 0.1 # cache version
torch.save(x, path) # save for next time
logging.info(f'{prefix}New cache created: {path}')
return x
def verify_image_label(args):
# Verify one image-label pair
im_file, lb_file, prefix = args
nm, nf, ne, nc, msg, segments = 0, 0, 0, 0, '', [
] # number (missing, found, empty, corrupt), message, segments
try:
# verify images
im = Image.open(im_file)
im.verify() # PIL verify
shape = exif_size(im) # image size
assert (shape[0] > 9) & (shape[1] >
9), f'image size {shape} <10 pixels'
assert im.format.lower(
) in IMG_FORMATS, f'invalid image format {im.format}'
if im.format.lower() in ('jpg', 'jpeg'):
with open(im_file, 'rb') as f:
f.seek(-2, 2)
if f.read() != b'\xff\xd9': # corrupt JPEG
ImageOps.exif_transpose(Image.open(im_file)).save(
im_file, 'JPEG', subsampling=0, quality=100)
msg = f'{prefix}WARNING: {im_file}: corrupt JPEG restored and saved'
# verify labels
if os.path.isfile(lb_file):
nf = 1 # label found
with open(lb_file) as f:
lb = [
x.split() for x in f.read().strip().splitlines() if len(x)
]
if any(len(x) > 6 for x in lb): # is segment
classes = np.array([x[0] for x in lb], dtype=np.float32)
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:
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]}'
_, i = np.unique(lb, axis=0, return_index=True)
if len(i) < nl: # duplicate row check
lb = lb[i] # remove duplicates
if segments:
segments = segments[i]
msg = f'{prefix}WARNING: {im_file}: {nl - len(i)} duplicate labels removed'
else:
ne = 1 # label empty
lb = np.zeros((0, 5), dtype=np.float32)
else:
nm = 1 # label missing
lb = np.zeros((0, 5), dtype=np.float32)
return im_file, lb, shape, segments, nm, nf, ne, nc, msg
except Exception as e:
nc = 1
msg = f'{prefix}WARNING: {im_file}: ignoring corrupt image/label: {e}'
return [None, None, None, None, nm, nf, ne, nc, msg]
