[go: up one dir, main page]
Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

PyTorch 1.7.0 Compatibility Updates #1233

Merged
merged 2 commits into from
Oct 28, 2020
Merged

PyTorch 1.7.0 Compatibility Updates #1233

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cf0283a
torch 1.7.0 compatibility updates
glenn-jocher Oct 28, 2020
0362bbc
add inference verification
glenn-jocher Oct 28, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions hubconf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,3 +108,11 @@ def yolov5x(pretrained=False, channels=3, classes=80):

if __name__ == '__main__':
model = create(name='yolov5s', pretrained=True, channels=3, classes=80) # example
model = model.fuse().eval().autoshape() # for autoshaping of PIL/cv2/np inputs and NMS

# Verify inference
from PIL import Image

img = Image.open('inference/images/zidane.jpg')
y = model(img)
print(y[0].shape)
7 changes: 7 additions & 0 deletions models/experimental.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,6 +136,13 @@ def attempt_load(weights, map_location=None):
attempt_download(w)
model.append(torch.load(w, map_location=map_location)['model'].float().fuse().eval()) # load FP32 model

# Compatibility updates
for m in model.modules():
if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6]:
m.inplace = True # pytorch 1.7.0 compatibility
elif type(m) is Conv:
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility

if len(model) == 1:
return model[-1] # return model
else:
Expand Down
1 change: 0 additions & 1 deletion models/yolo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,6 @@ def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
print('Fusing layers... ')
for m in self.model.modules():
if type(m) is Conv and hasattr(m, 'bn'):
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatability
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
delattr(m, 'bn') # remove batchnorm
m.forward = m.fuseforward # update forward
Expand Down
2 changes: 1 addition & 1 deletion utils/torch_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,7 @@ def initialize_weights(model):
elif t is nn.BatchNorm2d:
m.eps = 1e-3
m.momentum = 0.03
elif t in [nn.LeakyReLU, nn.ReLU, nn.ReLU6]:
elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6]:
m.inplace = True


Expand Down