NetDissect icon indicating copy to clipboard operation
NetDissect copied to clipboard
verified publisher icon CSAILVision

Reproducing results

Open KrishnaTarun opened this issue 4 years ago • 1 comments

I'm trying to run resnet152 trained on ImageNet using the python wrapper provided in the repository with the standard settings but the results are not the same as in the paper. Any suggestions for that.

KrishnaTarun avatar Sep 02 '21 13:09 KrishnaTarun

Attached is the result for Resnet152 (Top) and Alexnet (Bottom) trained on ImageNet and Places 365 respectively. Both the models seem to detect only scenes and textures which is not the case if we observe Figure 7 in https://netdissect.csail.mit.edu/final-network-dissection.pdf. Selection_029 Selection_036

Any comments on this would be helpful. Thanks.

KrishnaTarun avatar Sep 06 '21 15:09 KrishnaTarun