def cache_labels(self, path=Path('./labels.cache'), prefix=''):
# Cache dataset labels, check images and read shapes
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}' images and labels..."
with Pool(NUM_THREADS) as pool:
pbar = tqdm(pool.imap(verify_image_label, zip(self.img_files, self.label_files, repeat(prefix))),
desc=desc, total=len(self.img_files))
for im_file, lb, shape, segments, nm_f, nf_f, ne_f, nc_f, msg in pbar:
nm += nm_f
nf += nf_f
ne += ne_f
nc += nc_f
if im_file:
x[im_file] = [lb, shape, segments]
if msg:
msgs.append(msg)
pbar.desc = f"{desc}{nf} found, {nm} missing, {ne} empty, {nc} corrupt"
pbar.close()
if msgs:
LOGGER.info('\n'.join(msgs))
if nf == 0:
LOGGER.warning(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, len(self.img_files)
x['msgs'] = msgs # warnings
x['version'] = self.cache_version # cache version
try:
np.save(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
return x
def smart_optimizer(model,
name='Adam',
lr=0.001,
momentum=0.9,
weight_decay=1e-5):
# YOLOv5 3-param group optimizer: 0) weights with decay, 1) weights no decay, 2) biases no decay
g = [], [], [] # optimizer parameter groups
bn = tuple(v for k, v in nn.__dict__.items()
if 'Norm' in k) # normalization layers, i.e. BatchNorm2d()
for v in model.modules():
if hasattr(v, 'bias') and isinstance(v.bias,
nn.Parameter): # bias (no decay)
g[2].append(v.bias)
if isinstance(v, bn): # weight (no decay)
g[1].append(v.weight)
elif hasattr(v, 'weight') and isinstance(
v.weight, nn.Parameter): # weight (with decay)
g[0].append(v.weight)
if name == 'Adam':
optimizer = torch.optim.Adam(g[2], lr=lr,
betas=(momentum,
0.999)) # adjust beta1 to momentum
elif name == 'AdamW':
optimizer = torch.optim.AdamW(g[2],
lr=lr,
betas=(momentum, 0.999),
weight_decay=0.0)
elif name == 'RMSProp':
optimizer = torch.optim.RMSprop(g[2], lr=lr, momentum=momentum)
elif name == 'SGD':
optimizer = torch.optim.SGD(g[2],
lr=lr,
momentum=momentum,
nesterov=True)
else:
raise NotImplementedError(f'Optimizer {name} not implemented.')
optimizer.add_param_group({
'params': g[0],
'weight_decay': weight_decay
}) # add g0 with weight_decay
optimizer.add_param_group({
'params': g[1],
'weight_decay': 0.0
}) # add g1 (BatchNorm2d weights)
LOGGER.info(
f"{colorstr('optimizer:')} {type(optimizer).__name__} with parameter groups "
f"{len(g[1])} weight (no decay), {len(g[0])} weight, {len(g[2])} bias")
return optimizer
def export_edgetpu(file, prefix=colorstr('Edge TPU:')):
# YOLOv5 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/
try:
cmd = 'edgetpu_compiler --version'
help_url = 'https://coral.ai/docs/edgetpu/compiler/'
assert platform.system() == 'Linux', f'export only supported on Linux. See {help_url}'
if subprocess.run(f'{cmd} >/dev/null', shell=True).returncode != 0:
LOGGER.info(f'\n{prefix} export requires Edge TPU compiler. Attempting install from {help_url}')
sudo = subprocess.run('sudo --version >/dev/null', shell=True).returncode == 0 # sudo installed on system
for c in (
'curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -',
'echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list',
'sudo apt-get update', 'sudo apt-get install edgetpu-compiler'):
subprocess.run(c if sudo else c.replace('sudo ', ''), shell=True, check=True)
ver = subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().split()[-1]
LOGGER.info(f'\n{prefix} starting export with Edge TPU compiler {ver}...')
f = str(file).replace('.pt', '-int8_edgetpu.tflite') # Edge TPU model
f_tfl = str(file).replace('.pt', '-int8.tflite') # TFLite model
cmd = f"edgetpu_compiler -s -o {file.parent} {f_tfl}"
subprocess.run(cmd.split(), check=True)
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
return f
except Exception as e:
LOGGER.info(f'\n{prefix} export failure: {e}')
def parse_model(d, ch, model, imgsz): # model_dict, input_channels(3)
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
m_str = m
m = eval(m) if isinstance(m, str) else m # eval strings
for j, a in enumerate(args):
try:
args[j] = eval(a) if isinstance(a, str) else a # eval strings
except NameError:
pass
n = max(round(n * gd), 1) if n > 1 else n # depth gain
if m in [nn.Conv2d, Conv, Bottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP, C3, C3x]:
c1, c2 = ch[f], args[0]
c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
args = [c1, c2, *args[1:]]
if m in [BottleneckCSP, C3, C3x]:
args.insert(2, n)
n = 1
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum(ch[-1 if x == -1 else x + 1] for x in f)
elif m is Detect:
args.append([ch[x + 1] for x in f])
if isinstance(args[1], int): # number of anchors
args[1] = [list(range(args[1] * 2))] * len(f)
args.append(imgsz)
else:
c2 = ch[f]
tf_m = eval('TF' + m_str.replace('nn.', ''))
m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
else tf_m(*args, w=model.model[i]) # module
torch_m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
t = str(m)[8:-2].replace('__main__.', '') # module type
np = sum(x.numel() for x in torch_m_.parameters()) # number params
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
LOGGER.info(f'{i:>3}{str(f):>18}{str(n):>3}{np:>10} {t:<40}{str(args):<30}') # print
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
layers.append(m_)
ch.append(c2)
return keras.Sequential(layers), sorted(save)
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)): # model, channels, classes
super().__init__()
if isinstance(cfg, dict):
self.yaml = cfg # model dict
else: # is *.yaml
import yaml # for torch hub
self.yaml_file = Path(cfg).name
with open(cfg) as f:
self.yaml = yaml.load(f, Loader=yaml.FullLoader) # model dict
# Define model
if nc and nc != self.yaml['nc']:
LOGGER.info(f"Overriding {cfg} nc={self.yaml['nc']} with nc={nc}")
self.yaml['nc'] = nc # override yaml value
self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
def plot_labels(labels, names=(), save_dir=Path('')):
# plot dataset labels
LOGGER.info(f"Plotting labels to {save_dir / 'labels.jpg'}... ")
c, b = labels[:, 0], labels[:, 1:].transpose() # classes, boxes
nc = int(c.max() + 1) # number of classes
x = pd.DataFrame(b.transpose(), columns=['x', 'y', 'width', 'height'])
# seaborn correlogram
sn.pairplot(x,
corner=True,
diag_kind='auto',
kind='hist',
diag_kws=dict(bins=50),
plot_kws=dict(pmax=0.9))
plt.savefig(save_dir / 'labels_correlogram.jpg', dpi=200)
plt.close()
# matplotlib labels
matplotlib.use('svg') # faster
ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel()
y = ax[0].hist(c, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8)
# [y[2].patches[i].set_color([x / 255 for x in colors(i)]) for i in range(nc)] # update colors bug #3195
ax[0].set_ylabel('instances')
if 0 < len(names) < 30:
ax[0].set_xticks(range(len(names)))
ax[0].set_xticklabels(names, rotation=90, fontsize=10)
else:
ax[0].set_xlabel('classes')
sn.histplot(x, x='x', y='y', ax=ax[2], bins=50, pmax=0.9)
sn.histplot(x, x='width', y='height', ax=ax[3], bins=50, pmax=0.9)
# rectangles
labels[:, 1:3] = 0.5 # center
labels[:, 1:] = xywh2xyxy(labels[:, 1:]) * 2000
img = Image.fromarray(np.ones((2000, 2000, 3), dtype=np.uint8) * 255)
for cls, *box in labels[:1000]:
ImageDraw.Draw(img).rectangle(box, width=1,
outline=colors(cls)) # plot
ax[1].imshow(img)
ax[1].axis('off')
for a in [0, 1, 2, 3]:
for s in ['top', 'right', 'left', 'bottom']:
ax[a].spines[s].set_visible(False)
plt.savefig(save_dir / 'labels.jpg', dpi=200)
matplotlib.use('Agg')
plt.close()
def __call__(self, epoch, fitness):
if fitness >= self.best_fitness: # >= 0 to allow for early zero-fitness stage of training
self.best_epoch = epoch
self.best_fitness = fitness
delta = epoch - self.best_epoch # epochs without improvement
self.possible_stop = delta >= (self.patience - 1
) # possible stop may occur next epoch
stop = delta >= self.patience # stop training if patience exceeded
if stop:
LOGGER.info(
f'Stopping training early as no improvement observed in last {self.patience} epochs. '
f'Best results observed at epoch {self.best_epoch}, best model saved as best.pt.\n'
f'To update EarlyStopping(patience={self.patience}) pass a new patience value, '
f'i.e. `python train.py --patience 300` or use `--patience 0` to disable EarlyStopping.'
)
return stop
def update(self, i, cap, stream):
# Read stream `i` frames in daemon thread
n, f, read = 0, self.frames[i], 1 # frame number, frame array, inference every 'read' frame
while cap.isOpened() and n < f:
n += 1
# _, self.imgs[index] = cap.read()
cap.grab()
if n % read == 0:
success, im = cap.retrieve()
if success:
self.imgs[i] = im
else:
LOGGER.warning('WARNING: Video stream unresponsive, please check your IP camera connection.')
self.imgs[i] = np.zeros_like(self.imgs[i])
cap.open(stream) # re-open stream if signal was lost
time.sleep(0.0) # wait time
def create_dataloader(path,
imgsz,
batch_size,
stride,
single_cls=False,
hyp=None,
augment=False,
cache=False,
pad=0.0,
rect=False,
rank=-1,
workers=8,
image_weights=False,
quad=False,
prefix='',
shuffle=False):
if rect and shuffle:
LOGGER.warning('WARNING: --rect is incompatible with DataLoader shuffle, setting shuffle=False')
shuffle = False
with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP
dataset = LoadImagesAndLabels(
path,
imgsz,
batch_size,
augment=augment, # augmentation
hyp=hyp, # hyperparameters
rect=rect, # rectangular batches
cache_images=cache,
single_cls=single_cls,
stride=int(stride),
pad=pad,
image_weights=image_weights,
prefix=prefix)
batch_size = min(batch_size, len(dataset))
nd = torch.cuda.device_count() # number of CUDA devices
nw = min([os.cpu_count() // max(nd, 1), batch_size if batch_size > 1 else 0, workers]) # number of workers
sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle)
loader = DataLoader if image_weights else InfiniteDataLoader # only DataLoader allows for attribute updates
return loader(dataset,
batch_size=batch_size,
shuffle=shuffle and sampler is None,
num_workers=nw,
sampler=sampler,
pin_memory=True,
collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn), dataset
def check_and_upload_dataset(self, opt):
"""
Check if the dataset format is compatible and upload it as W&B artifact
arguments:
opt (namespace)-- Commandline arguments for current run
returns:
Updated dataset info dictionary where local dataset paths are replaced by WAND_ARFACT_PREFIX links.
"""
assert wandb, 'Install wandb to upload dataset'
config_path = self.log_dataset_artifact(
opt.data, opt.single_cls, 'YOLOv5'
if opt.project == 'runs/train' else Path(opt.project).stem)
LOGGER.info(f"Created dataset config file {config_path}")
with open(config_path, errors='ignore') as f:
wandb_data_dict = yaml.safe_load(f)
return wandb_data_dict
def select_device(device='', batch_size=0, newline=True):
# device = None or 'cpu' or 0 or '0' or '0,1,2,3'
s = f'YOLOv5 🚀 {git_describe() or file_date()} Python-{platform.python_version()} torch-{torch.__version__} '
device = str(device).strip().lower().replace('cuda:', '').replace(
'none', '') # to string, 'cuda:0' to '0'
cpu = device == 'cpu'
mps = device == 'mps' # Apple Metal Performance Shaders (MPS)
if cpu or mps:
os.environ[
'CUDA_VISIBLE_DEVICES'] = '-1' # force torch.cuda.is_available() = False
elif device: # non-cpu device requested
os.environ[
'CUDA_VISIBLE_DEVICES'] = device # set environment variable - must be before assert is_available()
assert torch.cuda.is_available() and torch.cuda.device_count() >= len(device.replace(',', '')), \
f"Invalid CUDA '--device {device}' requested, use '--device cpu' or pass valid CUDA device(s)"
if not (cpu
or mps) and torch.cuda.is_available(): # prefer GPU if available
devices = device.split(
','
) if device else '0' # range(torch.cuda.device_count()) # i.e. 0,1,6,7
n = len(devices) # device count
if n > 1 and batch_size > 0: # check batch_size is divisible by device_count
assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}'
space = ' ' * (len(s) + 1)
for i, d in enumerate(devices):
p = torch.cuda.get_device_properties(i)
s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / (1 << 20):.0f}MiB)\n" # bytes to MB
arg = 'cuda:0'
elif mps and getattr(torch,
'has_mps', False) and torch.backends.mps.is_available(
): # prefer MPS if available
s += 'MPS\n'
arg = 'mps'
else: # revert to CPU
s += 'CPU\n'
arg = 'cpu'
if not newline:
s = s.rstrip()
LOGGER.info(s.encode().decode('ascii', 'ignore')
if platform.system() == 'Windows' else s) # emoji-safe
return torch.device(arg)
def autobatch(model, imgsz=640, fraction=0.9, batch_size=16):
# Automatically estimate best batch size to use `fraction` of available CUDA memory
# Usage:
# import torch
# from utils.autobatch import autobatch
# model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False)
# print(autobatch(model))
prefix = colorstr('AutoBatch: ')
LOGGER.info(f'{prefix}Computing optimal batch size for --imgsz {imgsz}')
device = next(model.parameters()).device # get model device
if device.type == 'cpu':
LOGGER.info(
f'{prefix}CUDA not detected, using default CPU batch-size {batch_size}'
)
return batch_size
gb = 1 << 30 # bytes to GiB (1024 ** 3)
d = str(device).upper() # 'CUDA:0'
properties = torch.cuda.get_device_properties(device) # device properties
t = properties.total_memory / gb # (GiB)
r = torch.cuda.memory_reserved(device) / gb # (GiB)
a = torch.cuda.memory_allocated(device) / gb # (GiB)
f = t - (r + a) # free inside reserved
LOGGER.info(
f'{prefix}{d} ({properties.name}) {t:.2f}G total, {r:.2f}G reserved, {a:.2f}G allocated, {f:.2f}G free'
)
batch_sizes = [1, 2, 4, 8, 16]
try:
img = [torch.zeros(b, 3, imgsz, imgsz) for b in batch_sizes]
y = profile(img, model, n=3, device=device)
except Exception as e:
LOGGER.warning(f'{prefix}{e}')
y = [x[2] for x in y if x] # memory [2]
batch_sizes = batch_sizes[:len(y)]
p = np.polyfit(batch_sizes, y, deg=1) # first degree polynomial fit
b = int((f * fraction - p[1]) / p[0]) # y intercept (optimal batch size)
LOGGER.info(
f'{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%)'
)
return b
def check_anchors(dataset, model, thr=4.0, imgsz=640):
# Check anchor fit to data, recompute if necessary
m = model.module.model[-1] if hasattr(
model, 'module') else model.model[-1] # Detect()
shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
scale = np.random.uniform(0.9, 1.1,
size=(shapes.shape[0], 1)) # augment scale
wh = torch.tensor(
np.concatenate([
l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)
])).float() # wh
def metric(k): # compute metric
r = wh[:, None] / k[None]
x = torch.min(r, 1 / r).min(2)[0] # ratio metric
best = x.max(1)[0] # best_x
aat = (x > 1 / thr).float().sum(1).mean() # anchors above threshold
bpr = (best > 1 / thr).float().mean() # best possible recall
return bpr, aat
anchors = m.anchors.clone() * m.stride.to(m.anchors.device).view(
-1, 1, 1) # current anchors
bpr, aat = metric(anchors.cpu().view(-1, 2))
s = f'\n{PREFIX}{aat:.2f} anchors/target, {bpr:.3f} Best Possible Recall (BPR). '
if bpr > 0.98: # threshold to recompute
LOGGER.info(
emojis(f'{s}Current anchors are a good fit to dataset тЬЕ'))
else:
LOGGER.info(
emojis(
f'{s}Anchors are a poor fit to dataset тЪая╕П, attempting to improve...'
))
na = m.anchors.numel() // 2 # number of anchors
try:
anchors = kmean_anchors(dataset,
n=na,
img_size=imgsz,
thr=thr,
gen=1000,
verbose=False)
except Exception as e:
LOGGER.info(f'{PREFIX}ERROR: {e}')
new_bpr = metric(anchors)[0]
if new_bpr > bpr: # replace anchors
anchors = torch.tensor(anchors,
device=m.anchors.device).type_as(m.anchors)
m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(
m.anchors.device).view(-1, 1, 1) # loss
check_anchor_order(m)
s = f'{PREFIX}Done тЬЕ (optional: update model *.yaml to use these anchors in the future)'
else:
s = f'{PREFIX}Done тЪая╕П (original anchors better than new anchors, proceeding with original anchors)'
LOGGER.info(emojis(s))
def export_onnx(model, im, file, opset, train, dynamic, simplify, prefix=colorstr('ONNX:')):
# YOLOv5 ONNX export
try:
check_requirements(('onnx',))
import onnx
LOGGER.info(f'\n{prefix} starting export with onnx {onnx.__version__}...')
f = file.with_suffix('.onnx')
torch.onnx.export(model, im, f, verbose=False, opset_version=opset,
training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL,
do_constant_folding=not train,
input_names=['images'],
output_names=['output'],
dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'}, # shape(1,3,640,640)
'output': {0: 'batch', 1: 'anchors'} # shape(1,25200,85)
} if dynamic else None)
# Checks
model_onnx = onnx.load(f) # load onnx model
onnx.checker.check_model(model_onnx) # check onnx model
# LOGGER.info(onnx.helper.printable_graph(model_onnx.graph)) # print
# Simplify
if simplify:
try:
check_requirements(('onnx-simplifier',))
import onnxsim
LOGGER.info(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
model_onnx, check = onnxsim.simplify(
model_onnx,
dynamic_input_shape=dynamic,
input_shapes={'images': list(im.shape)} if dynamic else None)
assert check, 'assert check failed'
onnx.save(model_onnx, f)
except Exception as e:
LOGGER.info(f'{prefix} simplifier failure: {e}')
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
return f
except Exception as e:
LOGGER.info(f'{prefix} export failure: {e}')
def attempt_download(file, repo='ultralytics/yolov5'): # from utils.downloads import *; attempt_download()
# Attempt file download if does not exist
from utils.general import LOGGER
file = Path(str(file).strip().replace("'", ''))
if not file.exists():
# URL specified
name = Path(urllib.parse.unquote(str(file))).name # decode '%2F' to '/' etc.
if str(file).startswith(('http:/', 'https:/')): # download
url = str(file).replace(':/', '://') # Pathlib turns :// -> :/
file = name.split('?')[0] # parse authentication https://url.com/file.txt?auth...
if Path(file).is_file():
LOGGER.info(f'Found {url} locally at {file}') # file already exists
else:
safe_download(file=file, url=url, min_bytes=1E5)
return file
# GitHub assets
file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required)
try:
response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json() # github api
assets = [x['name'] for x in response['assets']] # release assets, i.e. ['yolov5s.pt', 'yolov5m.pt', ...]
tag = response['tag_name'] # i.e. 'v1.0'
except Exception: # fallback plan
assets = [
'yolov5n.pt', 'yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt', 'yolov5n6.pt', 'yolov5s6.pt',
'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt']
try:
tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1]
except Exception:
tag = 'v6.1' # current release
if name in assets:
url3 = 'https://drive.google.com/drive/folders/1EFQTEUeXWSFww0luse2jB9M1QNZQGwNl' # backup gdrive mirror
safe_download(
file,
url=f'https://github.com/{repo}/releases/download/{tag}/{name}',
url2=f'https://storage.googleapis.com/{repo}/{tag}/{name}', # backup url (optional)
min_bytes=1E5,
error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/{tag} or {url3}')
return str(file)
def __init__(self):
self.transform = None
try:
import albumentations as A
check_version(A.__version__, '1.0.3', hard=True) # version requirement
T = [
A.Blur(p=0.01),
A.MedianBlur(p=0.01),
A.ToGray(p=0.01),
A.CLAHE(p=0.01),
A.RandomBrightnessContrast(p=0.0),
A.RandomGamma(p=0.0),
A.ImageCompression(quality_lower=75, p=0.0)] # transforms
self.transform = A.Compose(T, bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels']))
LOGGER.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p))
except ImportError: # package not installed, skip
pass
except Exception as e:
LOGGER.info(colorstr('albumentations: ') + f'{e}')
def export_coreml(model, im, file, int8, half, prefix=colorstr('CoreML:')):
# YOLOv5 CoreML export
try:
check_requirements(('coremltools',))
import coremltools as ct
LOGGER.info(f'\n{prefix} starting export with coremltools {ct.__version__}...')
f = file.with_suffix('.mlmodel')
ts = torch.jit.trace(model, im, strict=False) # TorchScript model
ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=im.shape, scale=1 / 255, bias=[0, 0, 0])])
bits, mode = (8, 'kmeans_lut') if int8 else (16, 'linear') if half else (32, None)
if bits < 32:
if platform.system() == 'Darwin': # quantization only supported on macOS
with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=DeprecationWarning) # suppress numpy==1.20 float warning
ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode)
else:
print(f'{prefix} quantization only supported on macOS, skipping...')
ct_model.save(f)
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
return ct_model, f
except Exception as e:
LOGGER.info(f'\n{prefix} export failure: {e}')
return None, None
def test(
weights=ROOT / 'yolov5s.pt', # weights path
imgsz=640, # inference size (pixels)
batch_size=1, # batch size
data=ROOT / 'data/coco128.yaml', # dataset.yaml path
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
half=False, # use FP16 half-precision inference
test=False, # test exports only
pt_only=False, # test PyTorch only
):
y, t = [], time.time()
device = select_device(device)
for i, (name, f, suffix, gpu) in export.export_formats().iterrows(
): # index, (name, file, suffix, gpu-capable)
try:
w = weights if f == '-' else \
export.run(weights=weights, imgsz=[imgsz], include=[f], device=device, half=half)[-1] # weights
assert suffix in str(w), 'export failed'
y.append([name, True])
except Exception:
y.append([name, False]) # mAP, t_inference
# Print results
LOGGER.info('\n')
parse_opt()
notebook_init() # print system info
py = pd.DataFrame(y, columns=['Format', 'Export'])
LOGGER.info(f'\nExports complete ({time.time() - t:.2f}s)')
LOGGER.info(str(py))
return py
def export_openvino(model, file, half, prefix=colorstr('OpenVINO:')):
# YOLOv5 OpenVINO export
try:
check_requirements(
('openvino-dev', )
) # requires openvino-dev: https://pypi.org/project/openvino-dev/
import openvino.inference_engine as ie
LOGGER.info(
f'\n{prefix} starting export with openvino {ie.__version__}...')
f = str(file).replace('.pt', f'_openvino_model{os.sep}')
cmd = f"mo --input_model {file.with_suffix('.onnx')} --output_dir {f} --data_type {'FP16' if half else 'FP32'}"
subprocess.check_output(cmd.split()) # export
with open(Path(f) / file.with_suffix('.yaml').name, 'w') as g:
yaml.dump({
'stride': int(max(model.stride)),
'names': model.names
}, g) # add metadata.yaml
LOGGER.info(
f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
return f
except Exception as e:
LOGGER.info(f'\n{prefix} export failure: {e}')
def export_tfjs(keras_model, im, file, prefix=colorstr('TensorFlow.js:')):
# YOLOv5 TensorFlow.js export
try:
check_requirements(('tensorflowjs',))
import re
import tensorflowjs as tfjs
LOGGER.info(f'\n{prefix} starting export with tensorflowjs {tfjs.__version__}...')
f = str(file).replace('.pt', '_web_model') # js dir
f_pb = file.with_suffix('.pb') # *.pb path
f_json = f + '/model.json' # *.json path
cmd = f"tensorflowjs_converter --input_format=tf_frozen_model " \
f"--output_node_names='Identity,Identity_1,Identity_2,Identity_3' {f_pb} {f}"
subprocess.run(cmd, shell=True)
json = open(f_json).read()
with open(f_json, 'w') as j: # sort JSON Identity_* in ascending order
subst = re.sub(
r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, '
r'"Identity.?.?": {"name": "Identity.?.?"}, '
r'"Identity.?.?": {"name": "Identity.?.?"}, '
r'"Identity.?.?": {"name": "Identity.?.?"}}}',
r'{"outputs": {"Identity": {"name": "Identity"}, '
r'"Identity_1": {"name": "Identity_1"}, '
r'"Identity_2": {"name": "Identity_2"}, '
r'"Identity_3": {"name": "Identity_3"}}}',
json)
j.write(subst)
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
LOGGER.info(f'\n{prefix} export failure: {e}')
def export_torchscript(model, im, file, optimize, prefix=colorstr('TorchScript:')):
# YOLOv5 TorchScript model export
try:
LOGGER.info(f'\n{prefix} starting export with torch {torch.__version__}...')
f = file.with_suffix('.torchscript')
ts = torch.jit.trace(model, im, strict=False)
d = {"shape": im.shape, "stride": int(max(model.stride)), "names": model.names}
extra_files = {'config.txt': json.dumps(d)} # torch._C.ExtraFilesMap()
if optimize: # https://pytorch.org/tutorials/recipes/mobile_interpreter.html
optimize_for_mobile(ts)._save_for_lite_interpreter(str(f), _extra_files=extra_files)
else:
ts.save(str(f), _extra_files=extra_files)
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
return f
# print(f'\n{prefix} starting export with torch {torch.__version__}...')
# f = file.with_suffix('.torchscript.pt')
# fl = file.with_suffix('.torchscript.ptl')
# ts = torch.jit.trace(model, im, strict=False)
# # (optimize_for_mobile(ts) if optimize else ts).save(f)
# (optimize_for_mobile(ts) if optimize else ts)._save_for_lite_interpreter(str(fl))
# print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
LOGGER.info(f'{prefix} export failure: {e}')
def export_saved_model(model, im, file, dynamic,
tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
conf_thres=0.25, prefix=colorstr('TensorFlow saved_model:')):
# YOLOv5 TensorFlow saved_model export
keras_model = None
try:
import tensorflow as tf
from tensorflow import keras
from models.tf import TFDetect, TFModel
LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
f = str(file).replace('.pt', '_saved_model')
batch_size, ch, *imgsz = list(im.shape) # BCHW
tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
im = tf.zeros((batch_size, *imgsz, 3)) # BHWC order for TensorFlow
y = tf_model.predict(im, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
inputs = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
outputs = tf_model.predict(inputs, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
keras_model = keras.Model(inputs=inputs, outputs=outputs)
keras_model.trainable = False
keras_model.summary()
keras_model.save(f, save_format='tf')
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
LOGGER.info(f'\n{prefix} export failure: {e}')
return keras_model
def export_tflite(keras_model, im, file, int8, data, ncalib, prefix=colorstr('TensorFlow Lite:')):
# YOLOv5 TensorFlow Lite export
try:
import tensorflow as tf
from models.tf import representative_dataset_gen
LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
batch_size, ch, *imgsz = list(im.shape) # BCHW
f = str(file).replace('.pt', '-fp16.tflite')
converter = tf.lite.TFLiteConverter.from_keras_model(keras_model)
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS]
converter.target_spec.supported_types = [tf.float16]
converter.optimizations = [tf.lite.Optimize.DEFAULT]
if int8:
dataset = LoadImages(check_dataset(data)['train'], img_size=imgsz, auto=False) # representative data
converter.representative_dataset = lambda: representative_dataset_gen(dataset, ncalib)
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
converter.target_spec.supported_types = []
converter.inference_input_type = tf.uint8 # or tf.int8
converter.inference_output_type = tf.uint8 # or tf.int8
converter.experimental_new_quantizer = False
f = str(file).replace('.pt', '-int8.tflite')
tflite_model = converter.convert()
open(f, "wb").write(tflite_model)
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
LOGGER.info(f'\n{prefix} export failure: {e}')
def export_torchscript(model,
im,
file,
optimize,
prefix=colorstr('TorchScript:')):
# YOLOv5 TorchScript model export
try:
LOGGER.info(
f'\n{prefix} starting export with torch {torch.__version__}...')
f = file.with_suffix('.torchscript.pt')
ts = torch.jit.trace(model, im, strict=False)
d = {
"shape": im.shape,
"stride": int(max(model.stride)),
"names": model.names
}
extra_files = {'config.txt': json.dumps(d)} # torch._C.ExtraFilesMap()
(optimize_for_mobile(ts) if optimize else ts).save(
f, _extra_files=extra_files)
LOGGER.info(
f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
LOGGER.info(f'{prefix} export failure: {e}')
def export_pb(keras_model, im, file, prefix=colorstr('TensorFlow GraphDef:')):
# YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow
try:
import tensorflow as tf
from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
LOGGER.info(
f'\n{prefix} starting export with tensorflow {tf.__version__}...')
f = file.with_suffix('.pb')
m = tf.function(lambda x: keras_model(x)) # full model
m = m.get_concrete_function(
tf.TensorSpec(keras_model.inputs[0].shape,
keras_model.inputs[0].dtype))
frozen_func = convert_variables_to_constants_v2(m)
frozen_func.graph.as_graph_def()
tf.io.write_graph(graph_or_graph_def=frozen_func.graph,
logdir=str(f.parent),
name=f.name,
as_text=False)
LOGGER.info(
f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
LOGGER.info(f'\n{prefix} export failure: {e}')
def export_coreml(model, im, file, prefix=colorstr('CoreML:')):
# YOLOv5 CoreML export
ct_model = None
try:
check_requirements(('coremltools', ))
import coremltools as ct
LOGGER.info(
f'\n{prefix} starting export with coremltools {ct.__version__}...')
f = file.with_suffix('.mlmodel')
model.train() # CoreML exports should be placed in model.train() mode
ts = torch.jit.trace(model, im, strict=False) # TorchScript model
ct_model = ct.convert(ts,
inputs=[
ct.ImageType('image',
shape=im.shape,
scale=1 / 255,
bias=[0, 0, 0])
])
ct_model.save(f)
LOGGER.info(
f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
LOGGER.info(f'\n{prefix} export failure: {e}')
return ct_model
def run(
weights=ROOT / 'yolov5s.pt', # weights path
imgsz=640, # inference size (pixels)
batch_size=1, # batch size
data=ROOT / 'data/coco128.yaml', # dataset.yaml path
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
half=False, # use FP16 half-precision inference
):
y, t = [], time.time()
formats = export.export_formats()
device = select_device(device)
for i, (name, f, suffix, gpu) in formats.iterrows(
): # index, (name, file, suffix, gpu-capable)
try:
if device.type != 'cpu':
assert gpu, f'{name} inference not supported on GPU'
if f == '-':
w = weights # PyTorch format
else:
w = export.run(weights=weights,
imgsz=[imgsz],
include=[f],
device=device,
half=half)[-1] # all others
assert suffix in str(w), 'export failed'
result = val.run(data,
w,
batch_size,
imgsz,
plots=False,
device=device,
task='benchmark',
half=half)
metrics = result[
0] # metrics (mp, mr, map50, map, *losses(box, obj, cls))
speeds = result[2] # times (preprocess, inference, postprocess)
y.append([name, metrics[3], speeds[1]]) # mAP, t_inference
except Exception as e:
LOGGER.warning(f'WARNING: Benchmark failure for {name}: {e}')
y.append([name, None, None]) # mAP, t_inference
# Print results
LOGGER.info('\n')
parse_opt()
notebook_init() # print system info
py = pd.DataFrame(
y, columns=['Format', '[email protected]:0.95', 'Inference time (ms)'])
LOGGER.info(f'\nBenchmarks complete ({time.time() - t:.2f}s)')
LOGGER.info(str(py))
return py
def display(self,
pprint=False,
show=False,
save=False,
crop=False,
render=False,
save_dir=Path('')):
crops = []
for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string
if pred.shape[0]:
for c in pred[:, -1].unique():
n = (pred[:, -1] == c).sum() # detections per class
s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string
if show or save or render or crop:
annotator = Annotator(im, example=str(self.names))
for *box, conf, cls in reversed(
pred): # xyxy, confidence, class
label = f'{self.names[int(cls)]} {conf:.2f}'
if crop:
file = save_dir / 'crops' / self.names[int(
cls)] / self.files[i] if save else None
crops.append({
'box':
box,
'conf':
conf,
'cls':
cls,
'label':
label,
'im':
save_one_box(box, im, file=file, save=save)
})
else: # all others
annotator.box_label(box, label, color=colors(cls))
im = annotator.im
else:
s += '(no detections)'
im = Image.fromarray(im.astype(np.uint8)) if isinstance(
im, np.ndarray) else im # from np
if pprint:
LOGGER.info(s.rstrip(', '))
if show:
im.show(self.files[i]) # show
if save:
f = self.files[i]
im.save(save_dir / f) # save
if i == self.n - 1:
LOGGER.info(
f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}"
)
if render:
self.imgs[i] = np.asarray(im)
if crop:
if save:
LOGGER.info(f'Saved results to {save_dir}\n')
return crops
def end_epoch(self, best_result=False):
"""
commit the log_dict, model artifacts and Tables to W&B and flush the log_dict.
arguments:
best_result (boolean): Boolean representing if the result of this evaluation is best or not
"""
if self.wandb_run:
with all_logging_disabled():
if self.bbox_media_panel_images:
self.log_dict[
"BoundingBoxDebugger"] = self.bbox_media_panel_images
try:
wandb.log(self.log_dict)
except BaseException as e:
LOGGER.info(
f"An error occurred in wandb logger. The training will proceed without interruption. More info\n{e}"
)
self.wandb_run.finish()
self.wandb_run = None
self.log_dict = {}
self.bbox_media_panel_images = []
if self.result_artifact:
self.result_artifact.add(self.result_table, 'result')
wandb.log_artifact(self.result_artifact,
aliases=[
'latest', 'last',
'epoch ' + str(self.current_epoch),
('best' if best_result else '')
])
wandb.log({"evaluation": self.result_table})
self.result_table = wandb.Table([
"epoch", "id", "ground truth", "prediction",
"avg_confidence"
])
self.result_artifact = wandb.Artifact(
"run_" + wandb.run.id + "_progress", "evaluation")
def run(weights=ROOT / 'yolov5s.pt', # weights path
imgsz=(640, 640), # inference size h,w
batch_size=1, # batch size
dynamic=False, # dynamic batch size
):
# PyTorch model
im = torch.zeros((batch_size, 3, *imgsz)) # BCHW image
model = attempt_load(weights, map_location=torch.device('cpu'), inplace=True, fuse=False)
_ = model(im) # inference
model.info()
# TensorFlow model
im = tf.zeros((batch_size, *imgsz, 3)) # BHWC image
tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
_ = tf_model.predict(im) # inference
# Keras model
im = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im))
keras_model.summary()
LOGGER.info('PyTorch, TensorFlow and Keras models successfully verified.\nUse export.py for TF model export.')
