Mask_RCNN_Pytorch
Mask_RCNN_Pytorch copied to clipboard
Mask R-CNN for object detection and instance segmentation on Pytorch
solved
my cuda version = 9.0 V 9.0.176 I run this code nvcc -c -o nms_kernel.cu.o nms_kernel.cu -x cu -Xcompiler -fPIC -arch=arch but I got this error nvcc fatal : value...
Hi, I notice you implement multiple batch training by looping every single image within a batch, as can be seen [here](https://github.com/jytime/Mask_RCNN_Pytorch/blob/master/model.py#L1722). Why not use PyTorch built-in multiple batch training scheme?
Hi!How to load and train cityscapes dataset? Cityscapes dataset has no bounding box, so how do you train it for detection? thanks.
(mrcnn) ubuntu@ubuntu-S2600IP:/develop/python/mrcnn/Mask_RCNN_Pytorch/roialign/roi_align$ python build.py Including CUDA code. /develop/python/mrcnn/Mask_RCNN_Pytorch/roialign/roi_align generating /tmp/tmpe3pzv2y7/_crop_and_resize.c setting the current directory to '/tmp/tmpe3pzv2y7' running build_ext building '_crop_and_resize' extension creating develop creating develop/python creating develop/python/mrcnn creating develop/python/mrcnn/Mask_RCNN_Pytorch creating...
  I encountered the above problems. TIA.