question about the input img size about resnext.pytorch HOT 8 CLOSED

This model is made for CIFAR, which is (3, 32, 32), so the last avg pooling operation will not coincide for bigger input. You can just change it for .mean(-1).mean(-1). It will do the same as average pooling but without complaining about the image size.

from resnext.pytorch.

I can't get the point you say. Could you please explian it?
x = self.conv_1_3x3.forward(x)
x = F.relu(self.bn_1.forward(x), inplace=True)
x = self.stage_1.forward(x)
x = self.stage_2.forward(x)
x = self.stage_3.forward(x)
x = F.avg_pool2d(x, 8, 1)
x = x.view(-1, self.stages[3])
return self.classifier(x)

Do you mean the 'F.avg_pool2d(x,8,1)' ???

from resnext.pytorch.

Yes! Just change it by x.mean(3).mean(2)

from resnext.pytorch.

I replace the avg_pool with 'x=x.mean(-1).mean(-1)', but it doesn't work. Did I misunderstand your suggestion? BTW, the error shows that "cuda out of memory", and it shows the error in the stage_1.forward.

from resnext.pytorch.

Well, that's another matter. Can you try with batch_size = 1?

from resnext.pytorch.

It sill doesn't work!
the error is :
ValueError: Expected input batch_size (441) to match target batch_size (1).

from resnext.pytorch.

And I resize the img to (3,32,32) and it works.

from resnext.pytorch.

If you do:

model(image)
where image is of size (1, 3, 112, 112), it should work.

from resnext.pytorch.