Daniel Voigt Godoy - Deep Learning with PyTorch Step-by-Step A Beginner’s Guide-leanpub

back_to_numpy = x_train_tensor.numpy()
Output
TypeError: can't convert CUDA tensor to numpy. Use
Tensor.cpu() to copy the tensor to host memory first.
Unfortunately, Numpy cannot handle GPU tensors! You need to make them CPU
tensors first using cpu():
back_to_numpy = x_train_tensor.cpu().numpy()
So, to avoid this error, use first cpu() and then numpy(), even if you are using a CPU.
It follows the same principle of to(device): You can share your code with others
who may be using a GPU.
Creating Parameters
What distinguishes a tensor used for training data (or validation, or test)—like the
ones we’ve just created—from a tensor used as a (trainable) parameter / weight?
The latter requires the computation of its gradients, so we can update their values
(the parameters’ values, that is). That’s what the requires_grad=True argument is
good for. It tells PyTorch to compute gradients for us.
A tensor for a learnable parameter requires a gradient!
You may be tempted to create a simple tensor for a parameter and, later on, send it
to your chosen device, as we did with our data, right? Not so fast…
PyTorch | 81