-
Hi Joshua,
I tried to use chipQA to train and test its performance on a CSIQ-VQA database, which is a 480p resolution database.
1 - I run chipqa_yuv.py get the feature file
2 - I run python clean…
-
I use `generate` endpoint to do VQA task in Coca model, but got this error:
It seems that this issue will not happen in `beam_search` mode but appear in `top_k` or `top_p` mode.
Also, when I c…
-
VQA runtimeError with GPU
The command I entered：python demo_vqa.py with num_gpus=1 load_path="weights/vilt_vqa.ckpt"
 train , nominival
Start…
-
The Anaconda distribution currently includes ffmpeg v4.0, with support for the VQA decoder enabled:
```
(ffmpeg) $ conda search ffmpeg
Loading channels: done
# Name Version…
hartb updated
4 years ago
-
Hi, I notice that BLIP2 without LLM model (1st stage pretrained) can perform zero-shot vqa task.
Im curious which mechanism generates the answer of question . ITG or ITM?
Thanks
-
Hello, author.
Thank you for sharing your wonderful work.
While I was reproducing your code, I realized that 'main_v2.py' has not been updated yet unlike the implementation code you wrote in READ.…
-
Thank you for your excellent work!
I cannot reproduce your result when I'm fine-tuning BEiT3 following your guidance [get_started_for_vqav2.md](https://github.com/microsoft/unilm/blob/456511b24f5…
-
I tried to reproduce the finetuning results of BLIP2 FlanT5xl on VQAv2, but the results I got are far from those in the paper. I only got the highest accuracy of 76.58% while the paper is 81.55%, I wa…