Skip to content

GitLab

Commit efd1bfe5 authored by Konstantin Lopuhin's avatar Konstantin Lopuhin Committed by Soumith Chintala
Browse files

Fix inception v3 input transform (#144) 

First dimension is batch size, channel is the second
parent 3549aefc
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 3 deletions
torchvision/models/inception.py
View file @ efd1bfe5
...@@ -70,9 +70,9 @@ class Inception3(nn.Module): ...@@ -70,9 +70,9 @@ class Inception3(nn.Module):
def forward(self, x): def forward(self, x):
if self.transform_input: if self.transform_input:
x = x.clone() x = x.clone()
x[0] = x[0] * (0.229 / 0.5) + (0.485 - 0.5) / 0.5 x[:, 0] = x[:, 0] * (0.229 / 0.5) + (0.485 - 0.5) / 0.5
x[1] = x[1] * (0.224 / 0.5) + (0.456 - 0.5) / 0.5 x[:, 1] = x[:, 1] * (0.224 / 0.5) + (0.456 - 0.5) / 0.5
x[2] = x[2] * (0.225 / 0.5) + (0.406 - 0.5) / 0.5 x[:, 2] = x[:, 2] * (0.225 / 0.5) + (0.406 - 0.5) / 0.5
# 299 x 299 x 3 # 299 x 299 x 3
x = self.Conv2d_1a_3x3(x) x = self.Conv2d_1a_3x3(x)
# 149 x 149 x 32 # 149 x 149 x 32
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment