LTH14 / mage

A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About Post-training Evaluation

Neyleer opened this issue · comments

When reconstructing an image unconditionally, what operation is used to generate a different image, and is there only [C0] when the blank image is input to Encoder?

We use categorical sampling to generate different images. When a blank image is input to the encoder, [C0] as well as 256 [M] is input to the encoder (during generation).

Thank you