Chestnut

> Please follow these instructions in the compilation section: > > If your are using Volta GPUs, uncomment this [line](https://github.com/roytseng-tw/Detectron.pytorch/blob/master/lib/make.sh#L15) in lib/mask.sh and remember to postpend a backslash at the...

> I have finished the code for training Using Precomputed RPN Proposals. > [Detectron: Fast & Mask R-CNN Baselines Using Precomputed RPN Proposals](https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md#fast--mask-r-cnn-baselines-using-precomputed-rpn-proposals) > R-50-FPN 1x :33.7 > Use this...

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. Okay, Thanks for your kindly help. I saw your repository has many branches. I wonder which branch and commit should I merge...

> 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...

> Support single GPU and multi GPU testing on RPN proposals > > Do **not** support RPN only training. > Cases such as > > 1. training only the RPN...

> If you try to use `RoICrop` as a `ROI_XFROM_METHOD` it fails on the following line > [Detectron.pytorch/lib/modeling/model_builder.py](https://github.com/roytseng-tw/Detectron.pytorch/blob/dddeb6f4ff9fe14e122c26ec0ab5c1928027d8dc/lib/modeling/model_builder.py#L283) > > Line 283 in [dddeb6f](/roytseng-tw/Detectron.pytorch/commit/dddeb6f4ff9fe14e122c26ec0ab5c1928027d8dc) > > rois, bl_in.size()[2:], self.grid_size) >...