mirrors
/
yolov5
mirror of https://github.com/ultralytics/yolov5.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Refactor collections and fstrings (#7821) 

* Update torch_utils.py

* Additional code refactoring

* tuples to sets

* Cleanup
pull/7823/head
Glenn Jocher 2022-05-15 16:38:26 +02:00 committed by GitHub
parent 3356f2609c
commit f00071416f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
9 changed files with 58 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
detect.py
View File

@ -160,15 +160,15 @@ def run(
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
with open(txt_path + '.txt', 'a') as f:
with open(f'{txt_path}.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if save_img or save_crop or view_img: # Add bbox to image
c = int(cls) # integer class
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
annotator.box_label(xyxy, label, color=colors(c, True))
if save_crop:
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
if save_crop:
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
# Stream results
im0 = annotator.result()

6
export.py
View File

@ -175,7 +175,7 @@ def export_openvino(model, im, file, half, prefix=colorstr('OpenVINO:')):
import openvino.inference_engine as ie
LOGGER.info(f'\n{prefix} starting export with openvino {ie.__version__}...')
f = str(file).replace('.pt', '_openvino_model' + os.sep)
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, shell=True)
@ -385,7 +385,7 @@ def export_edgetpu(keras_model, im, file, prefix=colorstr('Edge TPU:')):
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(cmd + ' >/dev/null', shell=True).returncode != 0:
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 (
@ -419,7 +419,7 @@ def export_tfjs(keras_model, im, file, prefix=colorstr('TensorFlow.js:')):
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
f_json = f'{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}'

16
train.py
View File

@ -88,7 +88,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# Loggers
data_dict = None
if RANK in [-1, 0]:
if RANK in {-1, 0}:
loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance
if loggers.wandb:
data_dict = loggers.wandb.data_dict
@ -181,7 +181,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf) # plot_lr_scheduler(optimizer, scheduler, epochs)
# EMA
ema = ModelEMA(model) if RANK in [-1, 0] else None
ema = ModelEMA(model) if RANK in {-1, 0} else None
# Resume
start_epoch, best_fitness = 0, 0.0
@ -238,7 +238,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
assert mlc < nc, f'Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}'
# Process 0
if RANK in [-1, 0]:
if RANK in {-1, 0}:
val_loader = create_dataloader(val_path,
imgsz,
batch_size // WORLD_SIZE * 2,
@ -320,7 +320,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
train_loader.sampler.set_epoch(epoch)
pbar = enumerate(train_loader)
LOGGER.info(('\n' + '%10s' * 7) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'labels', 'img_size'))
if RANK in (-1, 0):
if RANK in {-1, 0}:
pbar = tqdm(pbar, total=nb, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}') # progress bar
optimizer.zero_grad()
for i, (imgs, targets, paths, _) in pbar: # batch -------------------------------------------------------------
@ -369,7 +369,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
last_opt_step = ni
# Log
if RANK in (-1, 0):
if RANK in {-1, 0}:
mloss = (mloss * i + loss_items) / (i + 1) # update mean losses
mem = f'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G' # (GB)
pbar.set_description(('%10s' * 2 + '%10.4g' * 5) %
@ -383,7 +383,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
lr = [x['lr'] for x in optimizer.param_groups] # for loggers
scheduler.step()
if RANK in (-1, 0):
if RANK in {-1, 0}:
# mAP
callbacks.run('on_train_epoch_end', epoch=epoch)
ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'names', 'stride', 'class_weights'])
@ -444,7 +444,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# end epoch ----------------------------------------------------------------------------------------------------
# end training -----------------------------------------------------------------------------------------------------
if RANK in (-1, 0):
if RANK in {-1, 0}:
LOGGER.info(f'\n{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.')
for f in last, best:
if f.exists():
@ -522,7 +522,7 @@ def parse_opt(known=False):
def main(opt, callbacks=Callbacks()):
# Checks
if RANK in (-1, 0):
if RANK in {-1, 0}:
print_args(vars(opt))
check_git_status()
check_requirements(exclude=['thop'])

2
utils/autoanchor.py
View File

@ -104,7 +104,7 @@ def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen
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):
for x in k:
s += '%i,%i, ' % (round(x[0]), round(x[1]))
if verbose:
LOGGER.info(s[:-2])

17
utils/dataloaders.py
View File

@ -57,9 +57,7 @@ def exif_size(img):
s = img.size # (width, height)
try:
rotation = dict(img._getexif().items())[orientation]
if rotation == 6: # rotation 270
s = (s[1], s[0])
elif rotation == 8: # rotation 90
if rotation in [6, 8]: # rotation 270 or 90
s = (s[1], s[0])
except Exception:
pass
@ -156,7 +154,7 @@ class InfiniteDataLoader(dataloader.DataLoader):
return len(self.batch_sampler.sampler)
def __iter__(self):
for i in range(len(self)):
for _ in range(len(self)):
yield next(self.iterator)
@ -224,10 +222,9 @@ class LoadImages:
self.cap.release()
if self.count == self.nf: # last video
raise StopIteration
else:
path = self.files[self.count]
self.new_video(path)
ret_val, img0 = self.cap.read()
path = self.files[self.count]
self.new_video(path)
ret_val, img0 = self.cap.read()
self.frame += 1
s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: '
@ -390,7 +387,7 @@ class LoadStreams:
def img2label_paths(img_paths):
# Define label paths as a function of image paths
sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep # /images/, /labels/ substrings
sa, sb = f'{os.sep}images{os.sep}', f'{os.sep}labels{os.sep}' # /images/, /labels/ substrings
return [sb.join(x.rsplit(sa, 1)).rsplit('.', 1)[0] + '.txt' for x in img_paths]
@ -456,7 +453,7 @@ class LoadImagesAndLabels(Dataset):
# Display cache
nf, nm, ne, nc, n = cache.pop('results') # found, missing, empty, corrupt, total
if exists and LOCAL_RANK in (-1, 0):
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']:

2
utils/general.py
View File

@ -84,7 +84,7 @@ def set_logging(name=None, verbose=VERBOSE):
for h in logging.root.handlers:
logging.root.removeHandler(h) # remove all handlers associated with the root logger object
rank = int(os.getenv('RANK', -1)) # rank in world for Multi-GPU trainings
level = logging.INFO if (verbose and rank in (-1, 0)) else logging.WARNING
level = logging.INFO if verbose and rank in {-1, 0} else logging.WARNING
log = logging.getLogger(name)
log.setLevel(level)
handler = logging.StreamHandler()

4
utils/loggers/__init__.py
View File

@ -22,7 +22,7 @@ try:
import wandb
assert hasattr(wandb, '__version__') # verify package import not local dir
if pkg.parse_version(wandb.__version__) >= pkg.parse_version('0.12.2') and RANK in [0, -1]:
if pkg.parse_version(wandb.__version__) >= pkg.parse_version('0.12.2') and RANK in {0, -1}:
try:
wandb_login_success = wandb.login(timeout=30)
except wandb.errors.UsageError: # known non-TTY terminal issue
@ -176,7 +176,7 @@ class Loggers():
if not self.opt.evolve:
wandb.log_artifact(str(best if best.exists() else last),
type='model',
name='run_' + self.wandb.wandb_run.id + '_model',
name=f'run_{self.wandb.wandb_run.id}_model',
aliases=['latest', 'best', 'stripped'])
self.wandb.finish_run()

41
utils/metrics.py
View File

@ -55,32 +55,31 @@ def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names
i = pred_cls == c
n_l = nt[ci] # number of labels
n_p = i.sum() # number of predictions
if n_p == 0 or n_l == 0:
continue
else:
# Accumulate FPs and TPs
fpc = (1 - tp[i]).cumsum(0)
tpc = tp[i].cumsum(0)
# Recall
recall = tpc / (n_l + eps) # recall curve
r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases
# Accumulate FPs and TPs
fpc = (1 - tp[i]).cumsum(0)
tpc = tp[i].cumsum(0)
# Precision
precision = tpc / (tpc + fpc) # precision curve
p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1) # p at pr_score
# Recall
recall = tpc / (n_l + eps) # recall curve
r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases
# AP from recall-precision curve
for j in range(tp.shape[1]):
ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j])
if plot and j == 0:
py.append(np.interp(px, mrec, mpre)) # precision at mAP@0.5
# Precision
precision = tpc / (tpc + fpc) # precision curve
p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1) # p at pr_score
# AP from recall-precision curve
for j in range(tp.shape[1]):
ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j])
if plot and j == 0:
py.append(np.interp(px, mrec, mpre)) # precision at mAP@0.5
# Compute F1 (harmonic mean of precision and recall)
f1 = 2 * p * r / (p + r + eps)
names = [v for k, v in names.items() if k in unique_classes] # list: only classes that have data
names = {i: v for i, v in enumerate(names)} # to dict
names = dict(enumerate(names)) # to dict
if plot:
plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names)
plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1')
@ -314,7 +313,7 @@ def wh_iou(wh1, wh2):
# Plots ----------------------------------------------------------------------------------------------------------------
def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()):
def plot_pr_curve(px, py, ap, save_dir=Path('pr_curve.png'), names=()):
# Precision-recall curve
fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
py = np.stack(py, axis=1)
@ -331,11 +330,11 @@ def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()):
ax.set_xlim(0, 1)
ax.set_ylim(0, 1)
plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
fig.savefig(Path(save_dir), dpi=250)
fig.savefig(save_dir, dpi=250)
plt.close()
def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence', ylabel='Metric'):
def plot_mc_curve(px, py, save_dir=Path('mc_curve.png'), names=(), xlabel='Confidence', ylabel='Metric'):
# Metric-confidence curve
fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
@ -352,5 +351,5 @@ def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence'
ax.set_xlim(0, 1)
ax.set_ylim(0, 1)
plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
fig.savefig(Path(save_dir), dpi=250)
fig.savefig(save_dir, dpi=250)
plt.close()

27
utils/torch_utils.py
View File

@ -50,9 +50,9 @@ def device_count():
def select_device(device='', batch_size=0, newline=True):
# device = 'cpu' or '0' or '0,1,2,3'
# 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:', '') # to string, 'cuda:0' to '0'
device = str(device).strip().lower().replace('cuda:', '').replace('none', '') # to string, 'cuda:0' to '0'
cpu = device == 'cpu'
if cpu:
os.environ['CUDA_VISIBLE_DEVICES'] = '-1' # force torch.cuda.is_available() = False
@ -97,7 +97,8 @@ def profile(input, ops, n=10, device=None):
# profile(input, [m1, m2], n=100) # profile over 100 iterations
results = []
device = device or select_device()
if not isinstance(device, torch.device):
device = select_device(device)
print(f"{'Params':>12s}{'GFLOPs':>12s}{'GPU_mem (GB)':>14s}{'forward (ms)':>14s}{'backward (ms)':>14s}"
f"{'input':>24s}{'output':>24s}")
@ -127,9 +128,8 @@ def profile(input, ops, n=10, device=None):
tf += (t[1] - t[0]) * 1000 / n # ms per op forward
tb += (t[2] - t[1]) * 1000 / n # ms per op backward
mem = torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0 # (GB)
s_in = tuple(x.shape) if isinstance(x, torch.Tensor) else 'list'
s_out = tuple(y.shape) if isinstance(y, torch.Tensor) else 'list'
p = sum(list(x.numel() for x in m.parameters())) if isinstance(m, nn.Module) else 0 # parameters
s_in, s_out = (tuple(x.shape) if isinstance(x, torch.Tensor) else 'list' for x in (x, y)) # shapes
p = sum(x.numel() for x in m.parameters()) if isinstance(m, nn.Module) else 0 # parameters
print(f'{p:12}{flops:12.4g}{mem:>14.3f}{tf:14.4g}{tb:14.4g}{str(s_in):>24s}{str(s_out):>24s}')
results.append([p, flops, mem, tf, tb, s_in, s_out])
except Exception as e:
@ -227,7 +227,7 @@ def model_info(model, verbose=False, img_size=640):
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):
except Exception:
fs = ''
name = Path(model.yaml_file).stem.replace('yolov5', 'YOLOv5') if hasattr(model, 'yaml_file') else 'Model'
@ -238,13 +238,12 @@ def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416)
# Scales img(bs,3,y,x) by ratio constrained to gs-multiple
if ratio == 1.0:
return img
else:
h, w = img.shape[2:]
s = (int(h * ratio), int(w * ratio)) # new size
img = F.interpolate(img, size=s, mode='bilinear', align_corners=False) # resize
if not same_shape: # pad/crop img
h, w = (math.ceil(x * ratio / gs) * gs for x in (h, w))
return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447) # value = imagenet mean
h, w = img.shape[2:]
s = (int(h * ratio), int(w * ratio)) # new size
img = F.interpolate(img, size=s, mode='bilinear', align_corners=False) # resize
if not same_shape: # pad/crop img
h, w = (math.ceil(x * ratio / gs) * gs for x in (h, w))
return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447) # value = imagenet mean
def copy_attr(a, b, include=(), exclude=()):