Issues
- 1
Where can I download the video data?
#29 opened by greeksharifa - 0
- 1
How many GPUs are required for inference?
#2 opened by YoucanBaby - 1
Fine-tuned model checkpoints
#27 opened by tyleryzhu - 0
How can T5 model output options ABCDE directly?
#28 opened by msra-jqxu - 3
FileNotFoundError: [Errno 2] No such file or directory: '/nas-hdd/shoubin/pretrained_model/hub/checkpoints/qformer_loc.pth
#11 opened by ontheway-arch - 1
HF Spaces demo not working.
#26 opened by akshat-khare - 2
HF Spaces demo not working ?
#22 opened by jena-shreyas - 3
finetuning result is so bad when using my pretrained checkpoints on QVhighlights.
#9 opened by fake-warrior8 - 1
How to load the parameters of vit and t5?
#12 opened by zhl98 - 2
Problem on NextQA Inference
#18 opened by Franklee95 - 1
About Localizer
#21 opened by PolarisHsu - 0
Performance gets worse when using Localizer that has been self-refined on the QA dataset
#25 opened by PolarisHsu - 0
Problem during inference with VLEP
#24 opened - 0
- 2
The warning of missing keys
#17 opened by ontheway-arch - 1
- 6
- 1
Can you provide the file qformer_loc.pth?
#15 opened by ontheway-arch - 1
- 0
How to fintune on my own data?
#14 opened by zhl98 - 1
the results on STAR is lower than paper
#10 opened by LoverLost - 1
How to define answer_id?
#8 opened by junwenchen - 0
BLIP2 run scripts
#7 opened by xijun-cs - 5
- 1
Could you please provide a sample to show annotation files after processing?
#5 opened by aixiaodewugege - 2
There is a writing error in the paper
#3 opened by zchuz