RuntimeError: Attempting to deserialize object on CUDA device 2 but torch.cuda.device_count() is 1.

[anhminh3105]

Hi, I am trying to run the demo_yolov3_deepsort.py with the original_ckpt.t7 model but received this following error as it's not the case for the ckpt.t7 model, do you have any idea? RuntimeError: Attempting to deserialize object on CUDA device 2 but torch.cuda.device_count() is 1. Please use torch.load with map_location to map your storages to an existing device. I am doing this because I noticed that the tracking performance is not as good as the official implementation in TF. Specifically, the ID switching problem is more noticeable.

[Tandon-A]

@anhminh3105

Faced the same issue but was able to resolve it by using map_location while loading the weights:

checkpoint = torch.load("original_ckpt.t7", map_location='cuda:0')
net_dict = checkpoint['net_dict']
net.load_state_dict(net_dict)
net.eval()

Hope it helps!