can't convert cuda:0 device type tensor to numpy

Question

As metioned in the title, I am getting this TyperError for the following code

I am using google collab and is set to GPU runtime type.

%%time
history = [evaluate(model, valid_dl)]
history

%%time
history += fit_OneCycle(epochs, max_lr, model, train_dl, valid_dl, 
                             grad_clip=grad_clip, 
                             weight_decay=1e-4, 
                             opt_func=opt_func)

def plot_losses(history):
    train_losses = [x.get('train_loss') for x in history]
    val_losses = [x['val_loss'] for x in history]
    plt.plot(train_losses, '-bx')
    plt.plot(val_losses, '-rx')
    plt.xlabel('epoch')
    plt.ylabel('loss')
    plt.legend(['Training', 'Validation'])
    plt.title('Loss vs. No. of epochs')

for the following line i am getting the error :-

plot_losses(history)

And i am getting the following error message:

AttributeError                            Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/matplotlib/cbook/__init__.py in index_of(y)
   1626     try:
-> 1627         return y.index.values, y.values
   1628     except AttributeError:

AttributeError: 'builtin_function_or_method' object has no attribute 'values'

During handling of the above exception, another exception occurred:

TypeError                                 Traceback (most recent call last)
----------------------------------9 frames------------------------------------------
<__array_function__ internals> in atleast_1d(*args, **kwargs)

/usr/local/lib/python3.7/dist-packages/torch/_tensor.py in __array__(self, dtype)
    676             return handle_torch_function(Tensor.__array__, (self,), self, dtype=dtype)
    677         if dtype is None:
--> 678             return self.numpy()
    679         else:
    680             return self.numpy().astype(dtype, copy=False)

TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.

Answer 1

The line of error is not shown here, however, you can replace the array (if it is an array) which you have with:

        Thearray.cpu().numpy()