Top maskrcnn-benchmark issues

returned non-zero exit status 1. RuntimeError: _th_or not supported on CUDAType for Bool

ImportError: /usr/local/lib/python3.6/dist-packages/torchvision/_C.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZN3c1019UndefinedTensorImpl10_singletonE

RuntimeError: DataLoader worker (pid 16560) is killed by signal: Killed.

awaiting response

The detection accuracy of the R-50-FPN Faster R-CNN is lower than your report, confusing...

Cannot run multiple training processes simultaneously on same GPU server?

question

Training on new data with my own pretrained model - model fine tuning

awaiting response contributions welcome enhancement

RuntimeError: unable to open shared memory object </torch_29919_1396182366> in read-write mode

dependency bug

ImportError: .../maskrcnn-benchmark/maskrcnn_benchmark/_C.cpython-36m-x86_64-linux-gnu.so: undefined symbol: __cudaPopCallConfiguration

awaiting response

Why adding ground truth bbbox during training?

question

How to resume training with a different learning rate

question