Skip to content

Fully convolutional version of all vgg models via constructor argument #184

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

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Fully convolutional version of all vgg models via constructor argument #184

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
78bd5a9
added convolutionalized version of all vgg models
warmspringwinds Jun 9, 2017
59e96e7
added convolutionalized version of all vgg models updated
warmspringwinds Jun 9, 2017
a5f5cc0
added convolutionalized version of all vgg models: typo
warmspringwinds Jun 9, 2017
6e272f5
added convolutionalized version of all vgg models: flake error correc…
warmspringwinds Jun 9, 2017
69ab2ff
added convolutionalized version of all vgg models: flake error correc…
warmspringwinds Jun 9, 2017
6267788
added convolutionalized version of all vgg models: flake error correc…
warmspringwinds Jun 9, 2017
29a1875
added convolutionalized version of all vgg models: flake error correc…
warmspringwinds Jun 9, 2017
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
16 changes: 14 additions & 2 deletions torchvision/models/vgg.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,9 +23,10 @@

class VGG(nn.Module):

def __init__(self, features, num_classes=1000):
def __init__(self, features, num_classes=1000, fully_conv=False):
super(VGG, self).__init__()
self.features = features
self.fully_conv = fully_conv
self.classifier = nn.Sequential(
nn.Linear(512 * 7 * 7, 4096),
nn.ReLU(True),
Expand All @@ -35,11 +36,22 @@ def __init__(self, features, num_classes=1000):
nn.Dropout(),
nn.Linear(4096, num_classes),
)
if fully_conv:
self.classifier = nn.Sequential(
nn.Conv2d(512, 4096, 7, 1, 3),
nn.ReLU(True),
nn.Dropout(),
nn.Conv2d(4096, 4096, 1),
nn.ReLU(True),
nn.Dropout(),
nn.Conv2d(4096, num_classes, 1)
)
self._initialize_weights()

def forward(self, x):
x = self.features(x)
x = x.view(x.size(0), -1)
if not self.fully_conv:
x = x.view(x.size(0), -1)
x = self.classifier(x)
return x

Expand Down