Pytorch very slow to convert list of numpy arrays into tensors · Issue #13918 · pytorch/pytorch · GitHub
![can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first · Issue #2106 · ultralytics/yolov5 · GitHub can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first · Issue #2106 · ultralytics/yolov5 · GitHub](https://user-images.githubusercontent.com/13358789/106464060-1d74c100-64d3-11eb-850b-045270ea624d.png)
can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first · Issue #2106 · ultralytics/yolov5 · GitHub
![TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first - PyTorch Forums TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first - PyTorch Forums](https://discuss.pytorch.org/uploads/default/optimized/3X/1/4/14e3e9488bb390215450e2c84ae3f471f5dddefc_2_1024x271.png)