CSAILVision / CSAILVision/NetDissect

How to process the first conv layer in network?

Open
#23 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
455
Forks
114
PR merge metrics
No merged PRs in 30d

Description

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!

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.