Gunwoo Yong

Hi, I used BlipForConditionalGeneration from transformers for image captioning. I want to visualize the reason of generated caption (word by word) like GradCAM. I found a code from Albef (https://github.com/salesforce/ALBEF/blob/main/visualization.ipynb),...

BLIP Image Captioning GradCAM?

8

Hi, I used BlipForConditionalGeneration from transformers for image captioning. I want to visualize the reason of generated caption (word by word) like GradCAM. I found a code from Albef (https://github.com/salesforce/ALBEF/blob/main/visualization.ipynb),...

Hello, I have a question about KB_size during training. I found that during training, we can trace epoch-training loss graph as well as epoch-KB size graph. I observed that during...

Thank you for your hard work. Are there any available pre-trained linear adapters' weights that we can use without training? Also, can I use `train.py` for fine-tuning? Thanks,