vis_cam.py not work in timesformer

Branch

main branch (1.x version, such as v1.0.0, or dev-1.x branch)

Prerequisite

[X] I have searched Issues and Discussions but cannot get the expected help.
[X] I have read the documentation but cannot get the expected help.
[X] The bug has not been fixed in the latest version.

Environment

Pytorch version： 1.9.0+cu111 CUDA Version: 11.1

Describe the bug

this is one of orders i tried.

python tools/visualizations/vis_cam.py work_dirs/timesformer/answer1/timesformer.py \ work_dirs/timesformer/answer1/best_acc_top1_epoch_972.pth data/convengesoft/data1/train/007.avi \ --target-layer-name backbone/transformer_layers/layers/0/norms/0 \ --out-filename cam/cam.gif

I have tried to change all layers'name i can image,but nothing worked.

most errors like below:

Reproduces the problem - code sample

No response

Reproduces the problem - command or script

No response

Reproduces the problem - error message

No response

Additional information

I want to know how to fix the code or how to fix the order to get the answer plz help me /cry/cry

open-mmlab / mmaction2