Giters

CSAILVision / NetDissect

Network Dissection http://netdissect.csail.mit.edu for quantifying interpretability of deep CNNs.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How to process the first conv layer in network?

Gchinanty opened this issue · comments

commented

LAYERS is set to "features" in the default rundissect_pytorch.sh, and after run rundissect_pytorch.sh, I will see the visualized results about the all 256 units from probes/pytorch_alexnet_imagenet/features.html.
My question is if I want to see the scores of the first conv layer in network(such as alexnet) with 64 units, what should I do.
If I need to make some changes to LAYERS in rundissect_pytorch.sh or do something else?
I would be appreciate if the author could clear my confusion.
THANKS!