Kinan Halloum

Installing the post3 version instead of post2, i.e. http://download.pytorch.org/whl/cu80/torch-0.2.0.post3-cp27-cp27mu-manylinux1_x86_64.whl solved the problem for me.

So for those who are still lost. Here are a few clean steps to resolve the issue (you need to recompile your CUDA): 1. Got to the following page https://developer.nvidia.com/cuda-gpus...

So for those who are still lost. Here are a few clean steps to resolve the issue (you need to recompile your CUDA): 1. Got to the following page https://developer.nvidia.com/cuda-gpus...

@NatalyaSlepkova sorry for my late reply. The question has already been asked in the closed issues and one person suggested running the tracker as follow: python motchallenge_trainer.py --cnn_model resources/networks/mars-small128.pb which...