search

Kevinz-code / CSRA

Official code of ICCV2021 paper "Residual Attention: A Simple but Effective Method for Multi-Label Recognition"
GNU Affero General Public License v3.0
209 stars 37 forks source link

some questions about val.py #10

Closed yangt1013 closed 2 years ago

yangt1013 commented 2 years ago

Thanks for sharing your code,I have som questions about your project. In val.py, the definitionation of follows was empty. parser.add_argument("--load_from", default="models_local/resnet101_voc07_head1_lam0.1_94.7.pth", type=str)

And I cannot find the saved model coding about this. How to use the val.py in your project? and explansion the model saved path clearly?

Kevinz-code commented 2 years ago

Hi, @yangt1013 You can refer to the Validation part in the README file. Specifically, the "resnet101_voc07_head1_lam0.1_94.7.pth" is resnet101 trained with our CSRA(Head=1, lambda=0.1). Download this model from our google drive and validate it.