def feature_visualization(x,
module_type,
stage,
n=32,
save_dir=Path('runs/detect/exp')):
"""
x: Features to be visualized
module_type: Module type
stage: Module stage within model
n: Maximum number of feature maps to plot
save_dir: Directory to save results
"""
if 'Detect' not in module_type:
batch, channels, height, width = x.shape # batch, channels, height, width
if height > 1 and width > 1:
f = save_dir / f"stage{stage}_{module_type.split('.')[-1]}_features.png" # filename
blocks = torch.chunk(
x[0].cpu(), channels,
dim=0) # select batch index 0, block by channels
n = min(n, channels) # number of plots
fig, ax = plt.subplots(math.ceil(n / 8), 8,
tight_layout=True) # 8 rows x n/8 cols
ax = ax.ravel()
plt.subplots_adjust(wspace=0.05, hspace=0.05)
for i in range(n):
ax[i].imshow(blocks[i].squeeze()) # cmap='gray'
ax[i].axis('off')
LOGGER.info(f'Saving {f}... ({n}/{channels})')
plt.savefig(f, dpi=300, bbox_inches='tight')
plt.close()
np.save(str(f.with_suffix('.npy')), x[0].cpu().numpy()) # npy save
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.'
)
def model_info(model, verbose=False, img_size=640):
# Model information. img_size may be int or list, i.e. img_size=640 or img_size=[640, 320]
n_p = sum(x.numel() for x in model.parameters()) # number parameters
n_g = sum(x.numel() for x in model.parameters()
if x.requires_grad) # number gradients
if verbose:
print(
f"{'layer':>5} {'name':>40} {'gradient':>9} {'parameters':>12} {'shape':>20} {'mu':>10} {'sigma':>10}"
)
for i, (name, p) in enumerate(model.named_parameters()):
name = name.replace('module_list.', '')
print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
(i, name, p.requires_grad, p.numel(), list(
p.shape), p.mean(), p.std()))
try: # FLOPs
from thop import profile
stride = max(int(model.stride.max()), 32) if hasattr(model,
'stride') else 32
img = torch.zeros((1, model.yaml.get('ch', 3), stride, stride),
device=next(model.parameters()).device) # input
flops = profile(deepcopy(model), inputs=(img, ),
verbose=False)[0] / 1E9 * 2 # stride GFLOPs
img_size = img_size if isinstance(
img_size, list) else [img_size, img_size] # expand if int/float
fs = ', %.1f GFLOPs' % (flops * img_size[0] / stride * img_size[1] /
stride) # 640x640 GFLOPs
except (ImportError, Exception):
fs = ''
LOGGER.info(
f"Model Summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}"
)
def plot_results(file='path/to/results.csv', dir=''):
# Plot training results.csv. Usage: from yolov5.utils.plots import *; plot_results('path/to/results.csv')
save_dir = Path(file).parent if file else Path(dir)
fig, ax = plt.subplots(2, 5, figsize=(12, 6), tight_layout=True)
ax = ax.ravel()
files = list(save_dir.glob('results*.csv'))
assert len(
files
), f'No results.csv files found in {save_dir.resolve()}, nothing to plot.'
for fi, f in enumerate(files):
try:
data = pd.read_csv(f)
s = [x.strip() for x in data.columns]
x = data.values[:, 0]
for i, j in enumerate([1, 2, 3, 4, 5, 8, 9, 10, 6, 7]):
y = data.values[:, j]
# y[y == 0] = np.nan # don't show zero values
ax[i].plot(x,
y,
marker='.',
label=f.stem,
linewidth=2,
markersize=8)
ax[i].set_title(s[j], fontsize=12)
# if j in [8, 9, 10]: # share train and val loss y axes
# ax[i].get_shared_y_axes().join(ax[i], ax[i - 5])
except Exception as e:
LOGGER.info(f'Warning: Plotting error for {f}: {e}')
ax[1].legend()
fig.savefig(save_dir / 'results.png', dpi=200)
plt.close()
def main(opt):
check_requirements(requirements=ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
if opt.task in ('train', 'val', 'test'): # run normally
run(**vars(opt))
elif opt.task == 'speed': # speed benchmarks
# python val.py --task speed --data coco.yaml --batch 1 --weights yolov5n.pt yolov5s.pt...
for w in opt.weights if isinstance(opt.weights, list) else [opt.weights]:
run(opt.data, weights=w, batch_size=opt.batch_size, imgsz=opt.imgsz, conf_thres=.25, iou_thres=.45,
device=opt.device, save_json=False)
elif opt.task == 'study': # run over a range of settings and save/plot
# python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n.pt yolov5s.pt...
x = list(range(256, 1536 + 128, 128)) # x axis (image sizes)
for w in opt.weights if isinstance(opt.weights, list) else [opt.weights]:
f = f'study_{Path(opt.data).stem}_{Path(w).stem}.txt' # filename to save to
y = [] # y axis
for i in x: # img-size
LOGGER.info(f'\nRunning {f} point {i}...')
r, _, t = run(opt.data, weights=w, batch_size=opt.batch_size, imgsz=i, conf_thres=opt.conf_thres,
iou_thres=opt.iou_thres, device=opt.device, save_json=opt.save_json)
y.append(r + t) # results and times
np.savetxt(f, y, fmt='%10.4g') # save
os.system('zip -r study.zip study_*.txt')
def __init__(self):
self.transform = None
try:
import albumentations as A
check_version(A.__version__, '1.0.3',
hard=True) # version requirement
self.transform = A.Compose([
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)
],
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 main(opt):
check_requirements(requirements=ROOT / 'requirements.txt',
exclude=('tensorboard', 'thop'))
if opt.task in ('train', 'val', 'test'): # run normally
if opt.conf_thres > 0.001: # https://github.com/ultralytics/yolov5/issues/1466
LOGGER.info(
f'WARNING: confidence threshold {opt.conf_thres} >> 0.001 will produce invalid mAP values.'
)
run(**vars(opt))
else:
weights = opt.weights if isinstance(opt.weights,
list) else [opt.weights]
opt.half = True # FP16 for fastest results
if opt.task == 'speed': # speed benchmarks
# python val.py --task speed --data coco.yaml --batch 1 --weights yolov5n.pt yolov5s.pt...
opt.conf_thres, opt.iou_thres, opt.save_json = 0.25, 0.45, False
for opt.weights in weights:
run(**vars(opt), plots=False)
elif opt.task == 'study': # speed vs mAP benchmarks
# python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n.pt yolov5s.pt...
for opt.weights in weights:
f = f'study_{Path(opt.data).stem}_{Path(opt.weights).stem}.txt' # filename to save to
x, y = list(range(256, 1536 + 128,
128)), [] # x axis (image sizes), y axis
for opt.imgsz in x: # img-size
LOGGER.info(f'\nRunning {f} --imgsz {opt.imgsz}...')
r, _, t = run(**vars(opt), plots=False)
y.append(r + t) # results and times
np.savetxt(f, y, fmt='%10.4g') # save
os.system('zip -r study.zip study_*.txt')
plot_val_study(x=x) # plot
def log_model(self, path, opt, epoch, fitness_score, best_model=False):
"""
Log the model checkpoint as W&B artifact
arguments:
path (Path) -- Path of directory containing the checkpoints
opt (namespace) -- Command line arguments for this run
epoch (int) -- Current epoch number
fitness_score (float) -- fitness score for current epoch
best_model (boolean) -- Boolean representing if the current checkpoint is the best yet.
"""
model_artifact = wandb.Artifact('run_' + wandb.run.id + '_model',
type='model',
metadata={
'original_url': str(path),
'epochs_trained': epoch + 1,
'save period': opt.save_period,
'project': opt.project,
'total_epochs': opt.epochs,
'fitness_score': fitness_score
})
model_artifact.add_file(str(path / 'last.pt'), name='last.pt')
wandb.log_artifact(model_artifact,
aliases=[
'latest', 'last',
'epoch ' + str(self.current_epoch),
'best' if best_model else ''
])
LOGGER.info(f"Saving model artifact on epoch {epoch + 1}")
def _print_biases(self):
m = self.model[-1] # Detect() module
for mi in m.m: # from
b = mi.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
LOGGER.info(
('%6g Conv2d.bias:' + '%10.3g' * 6) %
(mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
def select_device(device='', batch_size=None, newline=True):
# device = 'cpu' or '0' or '0,1,2,3'
s = f'YOLOv5 🚀 {git_describe() or date_modified()} torch {torch.__version__} ' # string
device = str(device).strip().lower().replace(
'cuda:', '') # to string, 'cuda:0' to '0'
cpu = device == 'cpu'
if cpu:
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
assert torch.cuda.is_available(
), f'CUDA unavailable, invalid device {device} requested' # check availability
cuda = not cpu and torch.cuda.is_available()
if cuda:
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: # 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 / 1024 ** 2:.0f}MiB)\n" # bytes to MB
else:
s += 'CPU\n'
if not newline:
s = s.rstrip()
LOGGER.info(s.encode().decode('ascii', 'ignore')
if platform.system() == 'Windows' else s) # emoji-safe
return torch.device('cuda:0' if cuda else 'cpu')
def __init__(self, model):
super().__init__()
LOGGER.info('Adding AutoShape... ')
copy_attr(self,
model,
include=('yaml', 'nc', 'hyp', 'names', 'stride', 'abc'),
exclude=()) # copy attributes
self.model = model.eval()
def check_anchor_order(m):
# Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary
a = m.anchors.prod(-1).view(-1) # anchor area
da = a[-1] - a[0] # delta a
ds = m.stride[-1] - m.stride[0] # delta s
if da.sign() != ds.sign(): # same order
LOGGER.info(f'{PREFIX}Reversing anchor order')
m.anchors[:] = m.anchors.flip(0)
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)
LOGGER.info(
f"{PREFIX}New anchors saved to model. Update model *.yaml to use these anchors in the future."
)
else:
LOGGER.info(
f"{PREFIX}Original anchors better than new anchors. Proceeding with original anchors."
)
def map_val_table_path(self):
"""
Map the validation dataset Table like name of file -> it's id in the W&B Table.
Useful for - referencing artifacts for evaluation.
"""
self.val_table_path_map = {}
LOGGER.info("Mapping dataset")
for i, data in enumerate(tqdm(self.val_table.data)):
self.val_table_path_map[data[3]] = data[0]
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
LOGGER.info('Fusing layers... ')
for m in self.model.modules():
if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
delattr(m, 'bn') # remove batchnorm
m.forward = m.forward_fuse # update forward
self.info()
return self
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 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)
try: # color histogram bars by class
[
y[2].patches[i].set_color([x / 255 for x in colors(i)])
for i in range(nc)
] # known issue #3195
except Exception:
pass
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 __init__(self, model):
super().__init__()
LOGGER.info('Adding AutoShape... ')
copy_attr(self,
model,
include=('yaml', 'nc', 'hyp', 'names', 'stride', 'abc'),
exclude=()) # copy attributes
self.dmb = isinstance(
model, DetectMultiBackend) # DetectMultiBackend() instance
self.pt = not self.dmb or model.pt # PyTorch model
self.model = model.eval()
def parse_model(d, ch): # 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 = 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 = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
c1, c2 = ch[f], args[0]
if c2 != no: # if not output
c2 = make_divisible(c2 * gw, 8)
args = [c1, c2, *args[1:]]
if m in [BottleneckCSP, C3, C3TR, C3Ghost]:
args.insert(2, n) # number of repeats
n = 1
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum(ch[x] for x in f)
elif m is Detect:
args.append([ch[x] for x in f])
if isinstance(args[1], int): # number of anchors
args[1] = [list(range(args[1] * 2))] * len(f)
elif m is Contract:
c2 = ch[f] * args[0] ** 2
elif m is Expand:
c2 = ch[f] // args[0] ** 2
else:
c2 = ch[f]
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 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}{n_:>3}{np:10.0f} {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_)
if i == 0:
ch = []
ch.append(c2)
return nn.Sequential(*layers), sorted(save)
def print_results(k, verbose=True):
k = k[np.argsort(k.prod(1))] # sort small to large
x, best = metric(k, wh0)
bpr, aat = (best > thr).float().mean(), (
x > thr).float().mean() * n # best possible recall, anch > thr
s = f'{PREFIX}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr\n' \
f'{PREFIX}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, ' \
f'past_thr={x[x > thr].mean():.3f}-mean: '
for i, x in enumerate(k):
s += '%i,%i, ' % (round(x[0]), round(x[1]))
if verbose:
LOGGER.info(s[:-2])
return k
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 main(opt, callbacks=Callbacks()):
# Checks
if RANK in [-1, 0]:
print_args(FILE.stem, opt)
check_git_status()
check_requirements(exclude=['thop'])
# Resume
if opt.resume and not check_wandb_resume(opt): # resume an interrupted run
ckpt = opt.resume if isinstance(
opt.resume,
str) else get_latest_run() # specified or most recent path
assert os.path.isfile(
ckpt), 'ERROR: --resume checkpoint does not exist'
with open(Path(ckpt).parent.parent / 'opt.yaml', errors='ignore') as f:
opt = argparse.Namespace(**yaml.safe_load(f)) # replace
opt.cfg, opt.weights, opt.resume = '', ckpt, True # reinstate
LOGGER.info(f'Resuming training from {ckpt}')
else:
opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = \
check_file(opt.data), check_yaml(opt.cfg), check_yaml(opt.hyp), str(opt.weights), str(opt.project) # checks
assert len(opt.cfg) or len(
opt.weights), 'either --cfg or --weights must be specified'
opt.save_dir = str(
increment_path(Path(opt.project) / opt.name,
exist_ok=opt.exist_ok))
# DDP mode
device = select_device(opt.device, batch_size=opt.batch_size)
if LOCAL_RANK != -1:
assert torch.cuda.device_count(
) > LOCAL_RANK, 'insufficient CUDA devices for DDP command'
assert opt.batch_size % WORLD_SIZE == 0, '--batch-size must be multiple of CUDA device count'
assert not opt.image_weights, '--image-weights argument is not compatible with DDP training'
torch.cuda.set_device(LOCAL_RANK)
device = torch.device('cuda', LOCAL_RANK)
dist.init_process_group(
backend="nccl" if dist.is_nccl_available() else "gloo")
# Train
train(opt.hyp, opt, device, callbacks)
if WORLD_SIZE > 1 and RANK == 0:
LOGGER.info('Destroying process group... ')
dist.destroy_process_group()
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] *= 0
cap.open(stream) # re-open stream if signal was lost
time.sleep(1 / self.fps[i]) # wait time
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
d = str(device).upper() # 'CUDA:0'
properties = torch.cuda.get_device_properties(device) # device properties
t = properties.total_memory / 1024**3 # (GiB)
r = torch.cuda.memory_reserved(device) / 1024**3 # (GiB)
a = torch.cuda.memory_allocated(device) / 1024**3 # (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 export_coreml(model, im, file, 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])
])
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 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)')
return f
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
except Exception as e:
LOGGER.info(f'{prefix} export failure: {e}')
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})
columns = ["epoch", "id", "ground truth", "prediction"]
columns.extend(self.data_dict['names'])
self.result_table = wandb.Table(columns)
self.result_artifact = wandb.Artifact(
"run_" + wandb.run.id + "_progress", "evaluation")
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)
