Jiaheng Liu

Training error in VIDSTG.

16

  Have you met this error?

In this paper,  there are 44540 sequences in total after running "prepare_train_data.py". But I run this code, I got 45028 sequences.The number of training sequences is 40250 and validate...

I try to download the images using the script, but many images failed to download (maybe the network proxy). Thanks. Jiaheng.

Hi, this is a nice paper. I am looking forward to your code.

The question on the curve of Figure 3

14

Hi, this is a nice paper. How to generate different AR-Net models with different flops(i.e., the red curve in Fig 3)? Do you achieve this by selecting different loss weights...

Question on the train_net.sh

1

 What is the DATASET_SUFFIX? I have seen how to generate or use DATASET_SUFFIX. Thanks.