What operation should be reverse to patch embed? #337

Unanswered

hadaev8 asked this question in General

hadaev8
Jan 4, 2021

https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vision_transformer.py#L146
I want to make a generative model on top of pretrained VIT
Should it be Conv2dtranspose?

Replies: 0 comments

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment