Detectron.pytorch icon indicating copy to clipboard operation
Detectron.pytorch copied to clipboard

A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

Results 100 Detectron.pytorch issues
Sort by recently updated
recently updated
newest added

I wanted to implement the non local module in the mask rcnn pipeline. I've already written it as a standalone module but I'm not sure how to include it in...

Quick Question about the Faster-RCNN model. In your code, regarding the Faster-RCNN model, how does the pre-trained model original come from? Did you train it within these code or convert...

Hi, In running json_dataset_rel.py, I faced the error of No module named utils!!! can you help please?

I add a non-local block to the backbone and train the network following "e2e_mask_rcnn_R-50-RPN_1x.yaml". However, I am not sure how to set the learning rate of the extra introduced non-local...

Hi all, I am trying to run simple inference of this code. As the author said, two ways are: (1) python tools/test_net.py --dataset coco2017 --cfg config/baselines/e2e_mask_rcnn_R-50-FPN_1x.yaml --load_ckpt {path/to/your/checkpoint} (2) python...

I compile the CUDA code, and meet a problem: cl : Command line warning D9002 : ignoring unknown option '-std=c99' _roi_crop.c C:\Program Files (x86)\Windows Kits\10\include\10.0.17763.0\ucrt\corecrt.h(10) : fatal error C1083: Cannot...

: not found make.sh: : not found make.sh: : not found: make.sh: : not found: make.sh: Warning: Extension name 'utils.cython_bbox' does not match fully qualified name 'lib.utils.cython_bbox' of 'utils/cython_bbox.pyx' Warning:...

### Expected results Successful Training ### Actual results ### Detailed steps to reproduce After Running the main and on completion of first epoch, I get an index out of range...

hi! I train keypoint using mask rcnn. If I use 'Adam' to train, I encounter the issue such as: ``` /home1/chuli/mask-rcnn.pytorch/lib/utils/boxes.py:226: RuntimeWarning: invalid value encountered in log targets_dh = wh...

### System information * Operating system: Ubuntu 18.04 * CUDA version: CUDA v10 * cuDNN version: cuDNN v7.3 * GPU models (for all devices if they are not all the...