-
Hi @baeseongsu, apologies for bothering you again, but I have a few detailed questions that I hope you can help me with.
1. What does "VQA grounding" refer to in section E.1.3?
2. Could you explai…
-
Hello
Thanks for your great work!
Is the code of the video-mamba-suite on EgoSchema released?
-
Hi,
Can you add the VQA fine-tuning function of BLIP2?
In the paper, when you fine-tune the VQA task, you will fine-tune the image encoder. When I use the `freeze_vit: False` command.
But I encoun…
zhl98 updated
1 month ago
-
When evaluating VQA benchmarks, the generation time for one question is tens of times slower than LLaVA inference. Intuitively it should be comparable to LLaVA. Do you have any ideas of the problem? T…
-
Hello, this error occurred when I wanted to train the model. How can I download this pth file?
/home/jinw/anaconda3/envs/KVQ/lib/python3.8/site-packages/torch/functional.py:504: UserWarning: torc…
ads2d updated
1 month ago
-
I would be very grateful if you could provide guidance on how I might obtain access to the MaRs-VQA dataset.
-
```
Not using distributed mode
[18:17:54.955532] job dir: /home/23031212503/projects/Flipped-VQA
[18:17:54.955618] Namespace(batch_size=1,
epochs=5,
accum_iter=4,
llama_model_path='./pretrained/…
-
🎉The finetuning(VQA/OCR/Grounding/Video) for Qwen2-VL-Chat series models has been supported, please check the documentation below for details:
# English
https://github.com/modelscope/ms-swift/blob/m…
-
Hi, how can I obtain VQA pairs for the DUDE dataset?
I searched for DUDE_loader on HuggingFace, but it seems they only have OCR, images, and PDFs for documents.
-
This is really great work! I ran it on the RAD-VQA dataset without pre-training and obtained lower accuracy rates: 39.1% for open questions, 65.4% for closed questions, and 54.9% overall. I would like…