Goutham
Goutham
So first we need to make a vocabulary of all the possible words?. Instead of making a vector of word indices (eg. [1,2,3,4,0] in the example), can I use the...
Same question here
Do you mean top 1000,2000,3000 like that?. Also, the accuracy scores correspond to the questions with these answers (those are in the vocabulary) or the entire dataset? Thanks
Hi, did you find any workaround for this issue? Thanks
Thanks for your fast response. I tried to replicate the results but, I am getting very poor values. Specifically, I trained the model by running "bash scripts/qvhl_pretrain.sh" with the pre-trained...
Sure, I will try. Thanks :)
Hi, I tried using parameter setting as you mentioned. But, I did not get much performance improvement. Specifically, I have initialised the UniVTG model using the pre-trained checkpoint from [here](https://drive.google.com/drive/folders/1eWpuTTBRaMoV4UsEteQHAf5t4dU7uwrl?usp=sharing)...
Sure, please find the attached file. Thanks [Archive.zip](https://github.com/showlab/UniVTG/files/13735246/Archive.zip)
Hi, the results are the best one.  I have checked the log file and seems like the checkpoint file is not loading. But,...