ProText
ProText copied to clipboard
[CVPRW 2024] Official repository of paper titled "Learning to Prompt with Text Only Supervision for Vision-Language Models".
How to perform this method on a timm clip model? What should be changed so that the code works?
Dear Muhammad, I hope this message finds you well. I have been deeply engaged with your work on utilizing the CLIP model for visual tasks, and I am thoroughly impressed...
Hello, I hope this message finds you well. I am currently attempting to use the action category labels from the THUMOS14 dataset to train the ProText model, aiming to obtain...
Thanks for your excellent project, I'm trying to reproduce your code on other datasets, could you please tell me approximately how much the loss drops to on datasets such as...
Hi, have you tried to learn multiple text prompts during training?