convnet-aig

convnet-aig copied to clipboard

https://github.com/andreasveit/convnet-aig/blob/47633cd463f4ac92f05152d825b601f1e8bf09fe/gumbelmodule.py#L44 The `dim` here should be changed to `-1`?

iamhankai

Thanks for releasing the code! I have been reviewing how the Gumbel-Softmax[1] trick was used and both the paper and the code suggest that the "relevance scores are interpreted as...

atiorh

Nice work. I want to use your network in my own applications. I wonder if it is possible for you to provide the pre-trained AIG model on ImageNet ? It...

yangyu12

Which part of the computation has been reduced?

1

As stated in the paper, the proposed convnet-aig can reduce computational cost. But after checking the source codes, I found each layer must be executed. The way you skip a...

Vincent-Hoo

How can we decide whether to run a layer without actually running it?

shouldsee

Reproduce the results of the paper

6

Can this code reproduce the results of the paper？I got 24.61% top-1 error.

Goingqs

ValueError: expected 2D or 3D input (got 4D input)

2

Hello Andreas Veit: My PyTorch version is 4.0 , cuda is 9.0 and python is 3.5. I run the code, but I find this problem. ``` python train.py ``` problem:...

MrLinNing