search

thaolmk54 / hcrn-videoqa

Implementation for the paper "Hierarchical Conditional Relation Networks for Video Question Answering" (Le et al., CVPR 2020, Oral)
Apache License 2.0
131 stars 26 forks source link

About the accuracy of tgif-qa #7

Closed Wanan-ni closed 4 years ago

Wanan-ni commented 4 years ago

Hi， I downloaded code、features、pre-trained models, but I got the accuracy of Count about 4.05/4.04/4.05 on test. When I train the model， I got 4.0639/4.0802/4.0599 on Count test and 0.7476/0.7454/0.7449 on Action test. I wonder if the parameters of configs/tgif_qa_xx.yml need to be adjusted, or I need do other settings.

thaolmk54 commented 4 years ago

Hi,

I'm sorry for the issue you got. I'm not really sure what is the problem here. I have asked someone to independently reproduce results from the pretrained models and pretty much it is similar to what in the paper.

As for the configuration files, I do think you need any adjustments. The issue you got possibly comes from the feature joining. Can you please remove the current features in your local storage then re-download and join them all together again to see if it helps? Also, please note that if you train the network yourself the results might vary a bit as PyTorch is not deterministic on different GPUs.

Wanan-ni commented 4 years ago

OK，I‘ll try again. Thanks a lot : )