New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Implement Transfer Learning API / Instructions #69
Comments
I did not get the question. You can always finetune the model on your own dataset by registering it in Detectron2. |
Sorry I wasn't clear. What I'm requesting is a feature similar to keras' I would like to use one of Mask2Formers pre-trained COCO models to learn features of smaller datasets. |
In PyTorch, you can freeze any parameter by setting its |
I will experiment with freezing different layers. If I have any success I'll make a PR. |
@lapp0 Where did you add the require_grad False to freeze the layers? And just from curiosity any results about freezing different layers? |
It would be helpful if we could piggy back on your library of pre-trained model for transfer learning. Perhaps this may be accomplished by freezing the first 6 (2L) of 9 layers of Mask2Formers transformer decoder.
Usage may look like this:
export DETECTRON2_DATASETS=/path/to/dir/containing/new/dataset
The text was updated successfully, but these errors were encountered: