Skip to content

Internal Imagenet normalisation for pretrained squeezenet models #785

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.

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

Closed
wants to merge 2 commits into from
Closed
Changes from all commits
Commits
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
11 changes: 10 additions & 1 deletion torchvision/models/squeezenet.py
Original file line number Diff line number Diff line change
Expand Up @@ -38,8 +38,9 @@ def forward(self, x):

class SqueezeNet(nn.Module):

def __init__(self, version=1.0, num_classes=1000):
def __init__(self, version=1.0, num_classes=1000, transform_input=False):
super(SqueezeNet, self).__init__()
self.transform_input = transform_input
if version not in [1.0, 1.1]:
raise ValueError("Unsupported SqueezeNet version {version}:"
"1.0 or 1.1 expected".format(version=version))
Expand Down Expand Up @@ -95,6 +96,14 @@ def __init__(self, version=1.0, num_classes=1000):
init.constant_(m.bias, 0)

def forward(self, x):

# imagenet normalisation
if self.transform_input:
x_ch0 = (torch.unsqueeze(x[:, 0], 1) - 0.485) / 0.229
x_ch1 = (torch.unsqueeze(x[:, 1], 1) - 0.456) / 0.224
x_ch2 = (torch.unsqueeze(x[:, 2], 1) - 0.406) / 0.225
x = torch.cat((x_ch0, x_ch1, x_ch2), 1)

x = self.features(x)
x = self.classifier(x)
return x.view(x.size(0), self.num_classes)
Expand Down