IssacCyj

About ohem

4

`loss_c = log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1, 1))` I'm confused with this line of code. Why not using conf_data to select hard examples? What is this loss_c stand for?

moco on cifar dataset

1

Thanks for the great repo! I have a quick question, is there any specific reason not adding cifar&svhn datasets to the moco training script? like, it's not suitable or the...

Hi, thanks for the great work! I have a question about how to compute feature compactness as shown in Figure 6 in the original paper. What I did is to...

Implementation of category-agnostic task

3

Thanks for this great repo. It mentioned in the paper that you also used category-agnostic task. Is it implemented in this repo? I didn't find it but I was able...

It says in the prerequisite that you have to have an appointment scheduled, but I'm able to run it with the case where no appointment has been scheduled. Will it...

MSRVTT feature download link

4

Hi, Thanks for this great work! The file extraction password for downloading MSRVTT features from baiduyun is not correct. Can you update?