search

facebookresearch / ov-seg

This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.
Other
689 stars 61 forks source link

The training process of ovseg #4

Closed kellyiss closed 1 year ago

kellyiss commented 1 year ago

Thanks for your amazing work!

Is the training of ovseg a two-stage pipeline? Where is the code for CLIP adaption?

Thanks

Jeff-LiangF commented 1 year ago

@kellyiss ,

Thanks for your interest in our work!

Yes, the training is two-stage. We are still working on cleaning the CLIP adaption code, please stay tuned!

dongbo811 commented 1 year ago

This is a very interesting work, when will the complete code be released?

algvr commented 1 year ago

Thanks a lot for this project! Do you happen to have any updates on the CLIP adaptation code? Thank you very much in advance!

goncayilmaz commented 1 year ago

Hello, it would be great if you could share the training of CLIP, is there any update on that?

Jeff-LiangF commented 1 year ago

Hi @kellyiss @dongbo811 @algvr @goncayilmaz ,

Sorry for the long delay, I have released the fine-tuning data of fine-tuning code in open clip training. Feel free to check it out.