def __init__(self,
path,
img_size=640,
batch_size=16,
augment=False,
hyp=None,
rect=False,
image_weights=False,
cache_images=False,
single_cls=False,
stride=32,
pad=0.0,
prefix=''):
self.img_size = img_size
self.augment = augment
self.hyp = hyp
self.image_weights = image_weights
self.rect = False if image_weights else rect
self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training)
self.mosaic_border = [-img_size // 2, -img_size // 2]
self.stride = stride
self.path = path
self.albumentations = Albumentations() if augment else None
try:
f = [] # image files
for p in path if isinstance(path, list) else [path]:
p = Path(p) # os-agnostic
if p.is_dir(): # dir
f += glob.glob(str(p / '**' / '*.*'), recursive=True)
# f = list(p.rglob('**/*.*')) # pathlib
elif p.is_file(): # file
with open(p, 'r') as t:
t = t.read().strip().splitlines()
parent = str(p.parent) + os.sep
f += [
x.replace('./', parent)
if x.startswith('./') else x for x in t
] # local to global path
# f += [p.parent / x.lstrip(os.sep) for x in t] # local to global path (pathlib)
else:
raise Exception(f'{prefix}{p} does not exist')
self.img_files = sorted([
x.replace('/', os.sep) for x in f
if x.split('.')[-1].lower() in img_formats
])
# self.img_files = sorted([x for x in f if x.suffix[1:].lower() in img_formats]) # pathlib
assert self.img_files, f'{prefix}No images found'
except Exception as e:
raise Exception(
f'{prefix}Error loading data from {path}: {e}\nSee {help_url}')
# Check cache
self.label_files = img2label_paths(self.img_files) # labels
cache_path = (p if p.is_file() else Path(
self.label_files[0]).parent).with_suffix('.cache')
try:
cache, exists = np.load(
cache_path, allow_pickle=True).item(), True # load dict
assert cache['version'] == 0.4 and cache['hash'] == get_hash(
self.label_files + self.img_files)
except:
cache, exists = self.cache_labels(cache_path,
prefix), False # cache
# Display cache
nf, nm, ne, nc, n = cache.pop(
'results') # found, missing, empty, corrupted, total
if exists:
d = f"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupted"
tqdm(None, desc=prefix + d, total=n,
initial=n) # display cache results
if cache['msgs']:
logging.info('\n'.join(cache['msgs'])) # display warnings
assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {help_url}'
# Read cache
[cache.pop(k) for k in ('hash', 'version', 'msgs')] # remove items
labels, shapes, self.segments = zip(*cache.values())
self.labels = list(labels)
self.shapes = np.array(shapes, dtype=np.float64)
self.img_files = list(cache.keys()) # update
self.label_files = img2label_paths(cache.keys()) # update
if single_cls:
for x in self.labels:
x[:, 0] = 0
n = len(shapes) # number of images
bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index
nb = bi[-1] + 1 # number of batches
self.batch = bi # batch index of image
self.n = n
self.indices = range(n)
# Rectangular Training
if self.rect:
# Sort by aspect ratio
s = self.shapes # wh
ar = s[:, 1] / s[:, 0] # aspect ratio
irect = ar.argsort()
self.img_files = [self.img_files[i] for i in irect]
self.label_files = [self.label_files[i] for i in irect]
self.labels = [self.labels[i] for i in irect]
self.shapes = s[irect] # wh
ar = ar[irect]
# Set training image shapes
shapes = [[1, 1]] * nb
for i in range(nb):
ari = ar[bi == i]
mini, maxi = ari.min(), ari.max()
if maxi < 1:
shapes[i] = [maxi, 1]
elif mini > 1:
shapes[i] = [1, 1 / mini]
self.batch_shapes = np.ceil(
np.array(shapes) * img_size / stride + pad).astype(
np.int) * stride
# Cache images into memory for faster training (WARNING: large datasets may exceed system RAM)
self.imgs = [None] * n
if cache_images:
gb = 0 # Gigabytes of cached images
self.img_hw0, self.img_hw = [None] * n, [None] * n
results = ThreadPool(num_threads).imap(lambda x: load_image(*x),
zip(repeat(self), range(n)))
pbar = tqdm(enumerate(results), total=n)
for i, x in pbar:
self.imgs[i], self.img_hw0[i], self.img_hw[
i] = x # img, hw_original, hw_resized = load_image(self, i)
gb += self.imgs[i].nbytes
pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB)'
pbar.close()
def __init__(self,
path,
img_size=640,
batch_size=16,
augment=False,
hyp=None,
rect=False,
image_weights=False,
cache_images=False,
single_cls=False,
stride=32,
pad=0.0,
prefix=''):
self.img_size = img_size
self.augment = augment
self.hyp = hyp
self.image_weights = image_weights
self.rect = False if image_weights else rect
self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training)
self.mosaic_border = [-img_size // 2, -img_size // 2]
self.stride = stride
self.path = path
self.albumentations = Albumentations() if augment else None
try:
f = [] # image files
for p in path if isinstance(path, list) else [path]:
p = Path(p) # os-agnostic
if p.is_dir(): # dir
f += glob.glob(str(p / '**' / '*.*'), recursive=True)
# f = list(p.rglob('*.*')) # pathlib
elif p.is_file(): # file
with open(p) as t:
t = t.read().strip().splitlines()
parent = str(p.parent) + os.sep
f += [
x.replace('./', parent)
if x.startswith('./') else x for x in t
] # local to global path
# f += [p.parent / x.lstrip(os.sep) for x in t] # local to global path (pathlib)
else:
raise Exception(f'{prefix}{p} does not exist')
self.img_files = sorted(
x.replace('/', os.sep) for x in f
if x.split('.')[-1].lower() in IMG_FORMATS)
# self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS]) # pathlib
assert self.img_files, f'{prefix}No images found'
except Exception as e:
raise Exception(
f'{prefix}Error loading data from {path}: {e}\nSee {HELP_URL}')
# Check cache
self.label_files = img2label_paths(self.img_files) # labels
cache_path = (p if p.is_file() else Path(
self.label_files[0]).parent).with_suffix('.cache')
try:
cache, exists = np.load(
cache_path, allow_pickle=True).item(), True # load dict
assert cache['version'] == self.cache_version # same version
assert cache['hash'] == get_hash(self.label_files +
self.img_files) # same hash
except Exception:
cache, exists = self.cache_labels(cache_path,
prefix), False # cache
# Display cache
nf, nm, ne, nc, n = cache.pop(
'results') # found, missing, empty, corrupt, total
if exists:
d = f"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupt"
tqdm(None, desc=prefix + d, total=n,
initial=n) # display cache results
if cache['msgs']:
LOGGER.info('\n'.join(cache['msgs'])) # display warnings
assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {HELP_URL}'
# Read cache
[cache.pop(k) for k in ('hash', 'version', 'msgs')] # remove items
labels, shapes, self.segments = zip(*cache.values())
self.labels = list(labels)
self.shapes = np.array(shapes, dtype=np.float64)
self.img_files = list(cache.keys()) # update
self.label_files = img2label_paths(cache.keys()) # update
n = len(shapes) # number of images
bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index
nb = bi[-1] + 1 # number of batches
self.batch = bi # batch index of image
self.n = n
self.indices = range(n)
# Update labels
include_class = [
] # filter labels to include only these classes (optional)
include_class_array = np.array(include_class).reshape(1, -1)
for i, (label, segment) in enumerate(zip(self.labels, self.segments)):
if include_class:
j = (label[:, 0:1] == include_class_array).any(1)
self.labels[i] = label[j]
if segment:
self.segments[i] = segment[j]
if single_cls: # single-class training, merge all classes into 0
self.labels[i][:, 0] = 0
if segment:
self.segments[i][:, 0] = 0
# Rectangular Training
if self.rect:
# Sort by aspect ratio
s = self.shapes # wh
ar = s[:, 1] / s[:, 0] # aspect ratio
irect = ar.argsort()
self.img_files = [self.img_files[i] for i in irect]
self.label_files = [self.label_files[i] for i in irect]
self.labels = [self.labels[i] for i in irect]
self.shapes = s[irect] # wh
ar = ar[irect]
# Set training image shapes
shapes = [[1, 1]] * nb
for i in range(nb):
ari = ar[bi == i]
mini, maxi = ari.min(), ari.max()
if maxi < 1:
shapes[i] = [maxi, 1]
elif mini > 1:
shapes[i] = [1, 1 / mini]
self.batch_shapes = np.ceil(
np.array(shapes) * img_size / stride + pad).astype(
np.int) * stride
# Cache images into RAM/disk for faster training (WARNING: large datasets may exceed system resources)
self.imgs, self.img_npy = [None] * n, [None] * n
if cache_images:
if cache_images == 'disk':
self.im_cache_dir = Path(
Path(self.img_files[0]).parent.as_posix() + '_npy')
self.img_npy = [
self.im_cache_dir / Path(f).with_suffix('.npy').name
for f in self.img_files
]
self.im_cache_dir.mkdir(parents=True, exist_ok=True)
gb = 0 # Gigabytes of cached images
self.img_hw0, self.img_hw = [None] * n, [None] * n
results = ThreadPool(NUM_THREADS).imap(self.load_image, range(n))
pbar = tqdm(enumerate(results), total=n)
for i, x in pbar:
if cache_images == 'disk':
if not self.img_npy[i].exists():
np.save(self.img_npy[i].as_posix(), x[0])
gb += self.img_npy[i].stat().st_size
else: # 'ram'
self.imgs[i], self.img_hw0[i], self.img_hw[
i] = x # im, hw_orig, hw_resized = load_image(self, i)
gb += self.imgs[i].nbytes
pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB {cache_images})'
pbar.close()
def __init__(self,
path,
img_size=640,
batch_size=16,
augment=False,
hyp=None,
rect=False,
image_weights=False,
cache_images=False,
single_cls=False,
stride=32,
pad=0.0,
prefix=''):
self.img_size = img_size
self.augment = augment
self.hyp = hyp
self.image_weights = image_weights
self.rect = False if image_weights else rect
self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training)
self.mosaic_border = [-img_size // 2, -img_size // 2]
self.stride = stride
self.path = path
# albumentations是图像数据增强库，这里Albumentations封装了一些基础的数据增强：Blur、MedianBlur、
# ToGray、CLAHE、RandomBrightnessContrast、RandomGamma、ImageCompression
self.albumentations = Albumentations() if augment else None
try:
f = [] # image files
for p in path if isinstance(path, list) else [path]:
p = Path(p) # os-agnostic
if p.is_dir(): # dir
f += glob.glob(str(p / '**' / '*.*'), recursive=True)
# f = list(p.rglob('*.*')) # pathlib
elif p.is_file(): # file
with open(p) as t:
t = t.read().strip().splitlines()
parent = str(p.parent) + os.sep
f += [x.replace('./', parent) if x.startswith('./') else x for x in t] # local to global path
# f += [p.parent / x.lstrip(os.sep) for x in t] # local to global path (pathlib)
else:
raise FileNotFoundError(f'{prefix}{p} does not exist')
self.im_files = sorted(x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS)
# self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS]) # pathlib
assert self.im_files, f'{prefix}No images found'
except Exception as e:
raise Exception(f'{prefix}Error loading data from {path}: {e}\nSee {HELP_URL}')
# Check cache
self.label_files = img2label_paths(self.im_files) # labels
cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache')
try:
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 Exception:
cache, exists = self.cache_labels(cache_path, prefix), False # run cache ops
# Display cache
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}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupt"
tqdm(None, desc=prefix + d, total=n, initial=n, bar_format=BAR_FORMAT) # display cache results
if cache['msgs']:
LOGGER.info('\n'.join(cache['msgs'])) # display warnings
assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {HELP_URL}'
# Read cache
[cache.pop(k) for k in ('hash', 'version', 'msgs')] # remove items
labels, shapes, self.segments = zip(*cache.values())
self.labels = list(labels)
self.shapes = np.array(shapes, dtype=np.float64)
# 根据cache的key(图片名)更新im_files列表；根据cache的values(label、shape、segments)更新标签
self.im_files = list(cache.keys()) # update
self.label_files = img2label_paths(cache.keys()) # update
n = len(shapes) # number of images
# 计算所有样本所属的batch批次索引
bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index
nb = bi[-1] + 1 # number of batches
self.batch = bi # batch index of image
self.n = n
self.indices = range(n) # 样本索引
# Update labels控制要学习的类别，include_class列表就是只包含这些类别，空就是不处理
include_class = [] # filter labels to include only these classes (optional)
include_class_array = np.array(include_class).reshape(1, -1)
for i, (label, segment) in enumerate(zip(self.labels, self.segments)):
if include_class:
j = (label[:, 0:1] == include_class_array).any(1)
self.labels[i] = label[j]
if segment:
self.segments[i] = segment[j]
if single_cls: # single-class training, merge all classes into 0
self.labels[i][:, 0] = 0
if segment:
self.segments[i][:, 0] = 0
# Rectangular Training
if self.rect:
# Sort by aspect ratio
s = self.shapes # wh
ar = s[:, 1] / s[:, 0] # aspect ratio高宽的比率
irect = ar.argsort()
self.im_files = [self.im_files[i] for i in irect]
self.label_files = [self.label_files[i] for i in irect]
self.labels = [self.labels[i] for i in irect]
self.shapes = s[irect] # wh
ar = ar[irect]
# Set training image shapes同一个batch设置同样的放缩比率
shapes = [[1, 1]] * nb
for i in range(nb):
ari = ar[bi == i]
mini, maxi = ari.min(), ari.max()
if maxi < 1:
shapes[i] = [maxi, 1]
elif mini > 1:
shapes[i] = [1, 1 / mini]
self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(np.int) * stride
# Cache images into RAM/disk for faster training (WARNING: large datasets may exceed system resources)
# 将图像缓存到RAM/磁盘中以加快训练（警告：大型数据集可能超过系统资源）
self.ims = [None] * n
self.npy_files = [Path(f).with_suffix('.npy') for f in self.im_files]
if cache_images:
gb = 0 # Gigabytes of cached images
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=BAR_FORMAT, disable=LOCAL_RANK > 0)
for i, x in pbar:
if cache_images == 'disk':
gb += 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)
gb += self.ims[i].nbytes
pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB {cache_images})'
pbar.close()
def __init__(self, annotation_lines, input_shape, random=True, train=True):
self.annotation_lines = annotation_lines
self.input_shape = input_shape
self.random = random
self.albumentations = Albumentations(self.input_shape, train)
