The usage of numpy() method does not function whenever the model is using gpu
for instance at line 54 : DP = detect_params[0].numpy()TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
The usage of numpy() method does not function whenever the model is using gpu
for instance at line 54 :
DP = detect_params[0].numpy()TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.is there a work around ?