Can't call numpy() on Tensor that requires grad - Value error

[Kullanicikukla61]

My plot function givees that error: RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead.
I searched problem and find that: use that "y_pred = y_pred.detach().numpy()" before call function. This leads this: error: ValueError: x and y must be the same size.
I searched discussions. However did not understand anything.
(I updated my code according to course materials but did not changed anyting)
(restart run all is the same.)

def plot_prediction(train_data = x_train,
                    train_labels= y_train,
                    test_data= x_test,
                    test_labels= y_test,
                    predictions= None):
  plt.figure(figsize=(10,7))

  plt.scatter(train_data,train_labels,c="b",s=4,label="Training label")
  plt.scatter(test_data,test_labels,c="g",s=4,label="Test label")

  if predictions is not None:
    plt.scatter(test_data, predictions, c="r", s=4, label="predictions")

  plt.legend(prop={"size":14} )



torch.manual_seed(42)

epochs = 1
train_loss_values = []
test_loss_values = []
epoch_count = []


for epoch in range(epochs):
  model0.train()
  y_pred= model0(x_train)        #forward pass
  loss = loss_fn(y_pred,y_train)      #calculate loss
  optimizer.zero_grad()             # optimeze to zero gradient
  loss.backward()                  #backpropogation according to parameters
  optimizer.step()                # step optimizer
  model0.eval()
  with torch.inference_mode():
    test_pred = model0(x_test)

    test_loss = loss_fn(test_pred,y_test.type(torch.float))

    if epoch % 10 == 0:
      epoch_count.append(epoch)
      train_loss_values.append(loss.detach().numpy())
      test_loss_values.append(test_loss.detach().numpy())
      print(f"Epoch: {epoch} | MAE Train Loss: {loss} | MAE Test Loss: {test_loss} ")


    y_pred = y_pred.detach().numpy()
    plot_prediction(predictions=y_pred)`

there may be mistake in post but indentation is true. I am new at github.

[miladnorouziii]

try using this code. plt.plot(epochArray, torch.Tensor(training_losses).numpy(), label = "Train Loss")
plt.plot(epochArray, torch.Tensor(validation_losses).numpy(), label = "Validation Loss")
plt.title("Loss plots")
plt.xlabel("Epochs")
plt.ylabel("Loss")
plt.legend()
plt.show()