Open dongjunhwang opened 2 years ago
Thank you for your attention on our work.
For your questions:
We set large_feature_map
is False for only for the resnet50 architecture on OpenImages dataset. For other cases, we set large_feature_map=True
.
Thank you for your question. We have checked it and found that we uploaded a wrong checkpoint for CUB-200 dataset on our google drive. Now, the right checkpoint has been already uploaded in our google drive ("dawsol_cub_res_update.tar"). You can re-download it and run with your shell setting (this setting is right).
great work. thank you for sharing this source. But i have a little question about the parameter of large feature map and boxaccv2 score in CUB dataset.
I found that
large_feature_map
parameter is False only the resnet50 architecture. Is that right settings?In CUB dataset, i evaluated to use the checkpoint that you opened in google drive. But the score is different to compare the paper.
The paper show the boxaccv2 score for CUB dataset to 71.35 in resnet backbone, but evaluation result is represented like this.
The other dataset have the right score, but only CUB datasets are wrong.
Shell setting is like below.
I want to reproduce this code only for evaluation, so it seems little important to me. Is that checkpoint have the right value?
Thanks.