Add verbose option to pytorch hub models (#2926)
* Add verbose and update print to logging * Fix positonal param * Revert auto formatting changes * Update hubconf.py Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
NanoCode012andGlenn Jocher authored and GitHub committed
1 parent
3665c0f59b
commit
c0d3f80544
3 files changed
+41
-38
No files matched your search
+28
-25
@@ -16,10 +16,9 @@ from utils.torch_utils import select_device
|
||||
|
||||
dependencies = ['torch', 'yaml']
|
||||
check_requirements(Path(__file__).parent / 'requirements.txt', exclude=('pycocotools', 'thop'))
|
||||
set_logging()
|
||||
|
||||
|
||||
def create(name, pretrained, channels, classes, autoshape):
|
||||
def create(name, pretrained, channels, classes, autoshape, verbose):
|
||||
"""Creates a specified YOLOv5 model
|
||||
|
||||
Arguments:
|
||||
@@ -32,6 +31,8 @@ def create(name, pretrained, channels, classes, autoshape):
|
||||
pytorch model
|
||||
"""
|
||||
try:
|
||||
set_logging(verbose=verbose)
|
||||
|
||||
cfg = list((Path(__file__).parent / 'models').rglob(f'{name}.yaml'))[0] # model.yaml path
|
||||
model = Model(cfg, channels, classes)
|
||||
if pretrained:
|
||||
@@ -55,7 +56,7 @@ def create(name, pretrained, channels, classes, autoshape):
|
||||
raise Exception(s) from e
|
||||
|
||||
|
||||
def custom(path_or_model='path/to/model.pt', autoshape=True):
|
||||
def custom(path_or_model='path/to/model.pt', autoshape=True, verbose=True):
|
||||
"""YOLOv5-custom model https://github.com/ultralytics/yolov5
|
||||
|
||||
Arguments (3 options):
|
||||
@@ -66,6 +67,8 @@ def custom(path_or_model='path/to/model.pt', autoshape=True):
|
||||
Returns:
|
||||
pytorch model
|
||||
"""
|
||||
set_logging(verbose=verbose)
|
||||
|
||||
model = torch.load(path_or_model) if isinstance(path_or_model, str) else path_or_model # load checkpoint
|
||||
if isinstance(model, dict):
|
||||
model = model['ema' if model.get('ema') else 'model'] # load model
|
||||
@@ -79,49 +82,49 @@ def custom(path_or_model='path/to/model.pt', autoshape=True):
|
||||
return hub_model.to(device)
|
||||
|
||||
|
||||
def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True):
|
||||
def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
|
||||
# YOLOv5-small model https://github.com/ultralytics/yolov5
|
||||
return create('yolov5s', pretrained, channels, classes, autoshape)
|
||||
return create('yolov5s', pretrained, channels, classes, autoshape, verbose)
|
||||
|
||||
|
||||
def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True):
|
||||
def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
|
||||
# YOLOv5-medium model https://github.com/ultralytics/yolov5
|
||||
return create('yolov5m', pretrained, channels, classes, autoshape)
|
||||
return create('yolov5m', pretrained, channels, classes, autoshape, verbose)
|
||||
|
||||
|
||||
def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True):
|
||||
def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
|
||||
# YOLOv5-large model https://github.com/ultralytics/yolov5
|
||||
return create('yolov5l', pretrained, channels, classes, autoshape)
|
||||
return create('yolov5l', pretrained, channels, classes, autoshape, verbose)
|
||||
|
||||
|
||||
def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True):
|
||||
def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
|
||||
# YOLOv5-xlarge model https://github.com/ultralytics/yolov5
|
||||
return create('yolov5x', pretrained, channels, classes, autoshape)
|
||||
return create('yolov5x', pretrained, channels, classes, autoshape, verbose)
|
||||
|
||||
|
||||
def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True):
|
||||
# YOLOv5-small model https://github.com/ultralytics/yolov5
|
||||
return create('yolov5s6', pretrained, channels, classes, autoshape)
|
||||
def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
|
||||
# YOLOv5-small-P6 model https://github.com/ultralytics/yolov5
|
||||
return create('yolov5s6', pretrained, channels, classes, autoshape, verbose)
|
||||
|
||||
|
||||
def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True):
|
||||
# YOLOv5-medium model https://github.com/ultralytics/yolov5
|
||||
return create('yolov5m6', pretrained, channels, classes, autoshape)
|
||||
def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
|
||||
# YOLOv5-medium-P6 model https://github.com/ultralytics/yolov5
|
||||
return create('yolov5m6', pretrained, channels, classes, autoshape, verbose)
|
||||
|
||||
|
||||
def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True):
|
||||
# YOLOv5-large model https://github.com/ultralytics/yolov5
|
||||
return create('yolov5l6', pretrained, channels, classes, autoshape)
|
||||
def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
|
||||
# YOLOv5-large-P6 model https://github.com/ultralytics/yolov5
|
||||
return create('yolov5l6', pretrained, channels, classes, autoshape, verbose)
|
||||
|
||||
|
||||
def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True):
|
||||
# YOLOv5-xlarge model https://github.com/ultralytics/yolov5
|
||||
return create('yolov5x6', pretrained, channels, classes, autoshape)
|
||||
def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True):
|
||||
# YOLOv5-xlarge-P6 model https://github.com/ultralytics/yolov5
|
||||
return create('yolov5x6', pretrained, channels, classes, autoshape, verbose)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
model = create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True) # pretrained example
|
||||
# model = custom(path_or_model='path/to/model.pt') # custom example
|
||||
model = create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True, verbose=True) # pretrained
|
||||
# model = custom(path_or_model='path/to/model.pt') # custom
|
||||
|
||||
# Verify inference
|
||||
import cv2
|
||||
|
||||
+11
-11
@@ -84,7 +84,7 @@ class Model(nn.Module):
|
||||
self.yaml['anchors'] = round(anchors) # override yaml value
|
||||
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
|
||||
self.names = [str(i) for i in range(self.yaml['nc'])] # default names
|
||||
# print([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
|
||||
# logger.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
|
||||
|
||||
# Build strides, anchors
|
||||
m = self.model[-1] # Detect()
|
||||
@@ -95,7 +95,7 @@ class Model(nn.Module):
|
||||
check_anchor_order(m)
|
||||
self.stride = m.stride
|
||||
self._initialize_biases() # only run once
|
||||
# print('Strides: %s' % m.stride.tolist())
|
||||
# logger.info('Strides: %s' % m.stride.tolist())
|
||||
|
||||
# Init weights, biases
|
||||
initialize_weights(self)
|
||||
@@ -134,13 +134,13 @@ class Model(nn.Module):
|
||||
for _ in range(10):
|
||||
_ = m(x)
|
||||
dt.append((time_synchronized() - t) * 100)
|
||||
print('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt[-1], m.type))
|
||||
logger.info('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt[-1], m.type))
|
||||
|
||||
x = m(x) # run
|
||||
y.append(x if m.i in self.save else None) # save output
|
||||
|
||||
if profile:
|
||||
print('%.1fms total' % sum(dt))
|
||||
logger.info('%.1fms total' % sum(dt))
|
||||
return x
|
||||
|
||||
def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
|
||||
@@ -157,15 +157,15 @@ class Model(nn.Module):
|
||||
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)
|
||||
print(('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
|
||||
logger.info(('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
|
||||
|
||||
# def _print_weights(self):
|
||||
# for m in self.model.modules():
|
||||
# if type(m) is Bottleneck:
|
||||
# print('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights
|
||||
# logger.info('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights
|
||||
|
||||
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
|
||||
print('Fusing layers... ')
|
||||
logger.info('Fusing layers... ')
|
||||
for m in self.model.modules():
|
||||
if type(m) is Conv and hasattr(m, 'bn'):
|
||||
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
|
||||
@@ -177,19 +177,19 @@ class Model(nn.Module):
|
||||
def nms(self, mode=True): # add or remove NMS module
|
||||
present = type(self.model[-1]) is NMS # last layer is NMS
|
||||
if mode and not present:
|
||||
print('Adding NMS... ')
|
||||
logger.info('Adding NMS... ')
|
||||
m = NMS() # module
|
||||
m.f = -1 # from
|
||||
m.i = self.model[-1].i + 1 # index
|
||||
self.model.add_module(name='%s' % m.i, module=m) # add
|
||||
self.eval()
|
||||
elif not mode and present:
|
||||
print('Removing NMS... ')
|
||||
logger.info('Removing NMS... ')
|
||||
self.model = self.model[:-1] # remove
|
||||
return self
|
||||
|
||||
def autoshape(self): # add autoShape module
|
||||
print('Adding autoShape... ')
|
||||
logger.info('Adding autoShape... ')
|
||||
m = autoShape(self) # wrap model
|
||||
copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=()) # copy attributes
|
||||
return m
|
||||
@@ -272,6 +272,6 @@ if __name__ == '__main__':
|
||||
# Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
|
||||
# from torch.utils.tensorboard import SummaryWriter
|
||||
# tb_writer = SummaryWriter('.')
|
||||
# print("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/")
|
||||
# logger.info("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/")
|
||||
# tb_writer.add_graph(torch.jit.trace(model, img, strict=False), []) # add model graph
|
||||
# tb_writer.add_image('test', img[0], dataformats='CWH') # add model to tensorboard
|
||||
+2
-2
@@ -32,10 +32,10 @@ cv2.setNumThreads(0) # prevent OpenCV from multithreading (incompatible with Py
|
||||
os.environ['NUMEXPR_MAX_THREADS'] = str(min(os.cpu_count(), 8)) # NumExpr max threads
|
||||
|
||||
|
||||
def set_logging(rank=-1):
|
||||
def set_logging(rank=-1, verbose=True):
|
||||
logging.basicConfig(
|
||||
format="%(message)s",
|
||||
level=logging.INFO if rank in [-1, 0] else logging.WARN)
|
||||
level=logging.INFO if (verbose and rank in [-1, 0]) else logging.WARN)
|
||||
|
||||
|
||||
def init_seeds(seed=0):
|
||||
|
||||
Reference in new issue
Block a user