陈崇彦
Hi, Could I ask where to download the trainval_ans2label.pkl file? Also, I would like to try Oscar + VizWiz on the VizWiz dataset, how could I process the original annotation...
Hi there, Could I know how to fine-tune a new dataset with a larger word dictionary? The current model has a 3129 size word/answer dictionary while ours expended the 3129...
Hi, Could I ask if the Oscar VQA task was updated for the use of VinVL image features? I have this concern for several reasons: (1)The script for finetuing VQA...
It seems that the VizWiz dataset released a new version while MMF is using the 2019 version. They have different image naming systems. Besides, will you adopt some new image...
Hi Yandong, thank you for sharing the code! Could I ask which Caffe version is needed? Thanks!
Could anyone share the pre-trained weights for the mixed model? Thank you so much!
Hi, Thank you for your excellent work. Could I ask if you could offer the fine-tuned model for segmentation? Also, how is the SIIM data from kaggle mapped to the...
Hi, thanks for the great work! I would like to evaluate visual chatgpt on some datasets... Is there any way to do that instead of using gradio? Such as directly...
Dear author, do you happen to know if the clipscore used here is different from the clipscore implemented in lightning AI https://lightning.ai/docs/torchmetrics/stable/multimodal/clip_score.html? The reason I am asking is because, with...