Xueyan Zou

Nice Repo!

6

This repo is really nice, performance on pascal voc could be reproduce using 2 gpus with batchsize=16.

I download this weight and share on google drive https://drive.google.com/open?id=19_PGrzARnJugSKULbTyRJ0txlI2UPvm6. 讲真，装百度网盘的时候真的超级怕被在系统里开个后门。

API application form doesn't work

1

https://[deepdataspace.com](https://deepdataspace.com/request_api)/request_api this link at least doesn't work in US now.

Does the author try diffusion models when aligning with the language model?

1

As for the question, I am very curious about the vision encoder with diffusion models, and how does this align with the semantic world.