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

Fixes #1797 by adding an init_weights keyword argument to Inception3 … #2420

Closed
wants to merge 1 commit into from
Closed

Fixes #1797 by adding an init_weights keyword argument to Inception3 … #2420

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
28 changes: 14 additions & 14 deletions torchvision/models/inception.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,7 +65,7 @@ def inception_v3(pretrained=False, progress=True, **kwargs):
class Inception3(nn.Module):

def __init__(self, num_classes=1000, aux_logits=True, transform_input=False,
inception_blocks=None):
inception_blocks=None, init_weights=True):
super(Inception3, self).__init__()
if inception_blocks is None:
inception_blocks = [
Expand Down Expand Up @@ -102,19 +102,19 @@ def __init__(self, num_classes=1000, aux_logits=True, transform_input=False,
self.Mixed_7b = inception_e(1280)
self.Mixed_7c = inception_e(2048)
self.fc = nn.Linear(2048, num_classes)

for m in self.modules():
if isinstance(m, nn.Conv2d) or isinstance(m, nn.Linear):
import scipy.stats as stats
stddev = m.stddev if hasattr(m, 'stddev') else 0.1
X = stats.truncnorm(-2, 2, scale=stddev)
values = torch.as_tensor(X.rvs(m.weight.numel()), dtype=m.weight.dtype)
values = values.view(m.weight.size())
with torch.no_grad():
m.weight.copy_(values)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
if init_weights:
for m in self.modules():
if isinstance(m, nn.Conv2d) or isinstance(m, nn.Linear):
import scipy.stats as stats
stddev = m.stddev if hasattr(m, 'stddev') else 0.1
X = stats.truncnorm(-2, 2, scale=stddev)
values = torch.as_tensor(X.rvs(m.weight.numel()), dtype=m.weight.dtype)
values = values.view(m.weight.size())
with torch.no_grad():
m.weight.copy_(values)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)

def _transform_input(self, x):
if self.transform_input:
Expand Down