Closed kamenrideraway closed 2 months ago
Hi, you can write a script and save the image features after your own image transformation. The structure of image features should be 3x240x240 (aligned with the input of the visual encoder).
Hi, you can write a script and save the image features after your own image transformation. The structure of image features should be 3x240x240 (aligned with the input of the visual encoder).
Thanks!
Originally posted by @Diana1026 in https://github.com/mala-lab/InCTRL/issues/7#issuecomment-2031421261 Thank you for this work.I want to test my own model,but I don't know exactly where should I use torch.save() to generate my own .pt file. And I don't know the structure of .pt file. Could you please give a more specific explaination? Thanks a lot.