CODEWITHSUNDEEP
pythonneural-networkcomputer-visionpytorch
FisNaN
FisNaN

Reputation: 2865

Pytorch: Converting a VGG model into a sequential model, but getting different outputs

Background: I'm working on an adversarial detector method which requires to access the outputs from each hidden layer. I loaded a pretrained VGG16 from torchvision.models.

To access the output from each hidden layer, I put it into a sequential model:

vgg16 = models.vgg16(pretrained=True)

vgg16_seq = nn.Sequential(*(
    list(list(vgg16.children())[0]) + 
    [nn.AdaptiveAvgPool2d((7, 7)), nn.Flatten()] + 
    list(list(vgg16.children())[2])))

Without nn.Flatten(), the forward method will complaint about dimensions don't match between mat1 and mat2.

I looked into the torchvision VGG implementation, it uses the [feature..., AvgPool, flatten, classifier...] structure. Since AdaptiveAvgPool2d layer and Flatten layer have no parameters, I assume this should work, but I have different outputs.

output1 = vgg16(X_small)
print(output1.size())
output2 = vgg16_seq(X_small)
print(output2.size())
torch.equal(output1, output2)

Problem: They are in the same dimension but different outputs.

torch.Size([32, 1000])
torch.Size([32, 1000])
False

I tested the outputs right after the AdaptiveAvgPool2d layer, the outputs are equal:

output1 = nn.Sequential(*list(vgg16.children())[:2])(X_small)
print(output1.size())
output2 = nn.Sequential(*list(vgg16_seq)[:32])(X_small)
print(output2.size())
torch.equal(output1, output2)

torch.Size([32, 512, 7, 7])
torch.Size([32, 512, 7, 7])
True

Can someone point out what went wrong? Thank you

Upvotes: 1

Views: 667

Answers (1)

Harshit Kumar
Harshit Kumar

Reputation: 12827

You need to call the eval mode before doing inference.

i.e.

vgg16.eval()
vgg16_seq.eval()

Upvotes: 1

Related Questions