Detectron.pytorch
Detectron.pytorch copied to clipboard
roytseng-tw
support RPN proposals testing
Support single GPU and multi GPU testing on RPN proposals
Do not support RPN only training. Cases such as
- training only the RPN branch
- training on pre-computed proposals
require restructuring model_builder.py quite a bit. @roytseng-tw you should call the shots
Hi, thanks for your work.
But I did not see these codes in the master branch?
This pull request is not merged. I see. How I can use them? Cause I want to generate the proposal from a mask rcnn trained model.
This pull request is not merged.
and then train the model from the precompute proposals.
https://stackoverflow.com/questions/6022302/how-to-apply-unmerged-upstream-pull-requests-from-other-forks-into-my-fork
Maybe this can help.
https://stackoverflow.com/questions/6022302/how-to-apply-unmerged-upstream-pull-requests-from-other-forks-into-my-fork
Maybe this can help.
Okay, Thanks for your kindly help. I saw your repository has many branches. I wonder which branch and commit should I merge to the roys' master branch will make the rpn-testing work?
I created a separate branch just for this pull request. It's called rpn-testing
I created a separate branch just for this pull request. It's called testing
I see.
Thanks again!
I created a separate branch just for this pull request. It's called rpn-testing
Hi, I wonder if the model can be trained with the precomputed proposals and just train the mask branch and not update the box branch?
This codebase does not support Fast-RCNN training (the one you described) or RPN-only training. Both require restructuring model_builder.py. I did not do this pull request since it is better for the author himself to decide on this.
Also, _compute_targets in roidb.py has a behavior difference compared to fast rcnn assignment policy regarding crowd. I would say it involves a bit of testing to make sure there is no bug.
Support single GPU and multi GPU testing on RPN proposals
Do not support RPN only training. Cases such as
- training only the RPN branch
- training on pre-computed proposals
require restructuring model_builder.py quite a bit. @roytseng-tw you should call the shots
Hi, I wonder if there we could test the bbox and mask by given proposals?
Thanks for your help in advance!
Some slight modifications will make it possible.
You might need to sprinkle a few more changes here and there down the road. But the spirit is true.