Error in losstrain

1 
def train(epoch):
  
    model.train()
    tr_loss = 0
    # getting the training set
    x_train, y_train = Variable(train_x), Variable(train_y)
    # getting the validation set
    x_val, y_val = Variable(val_x), Variable(val_y)
    # converting the data into GPU format
    if torch.cuda.is_available():
        #model.cuda()
        x_train = x_train.cuda()
        y_train = y_train.cuda()
        x_val = x_val.cuda()
        y_val = y_val.cuda()

    # clearing the Gradients of the model parameters
    optimizer.zero_grad()

    # prediction for training and validation set
    output_train = model(x_train.float())
    output_val = model(x_val.float())

    # computing the training and validation loss
    loss_train = criterion(output_train, y_train.long())
    loss_val = criterion(output_val, y_val.long())
    train_losses.append(loss_train)
    val_losses.append(loss_val)
    
    # computing the updated weights of all the model parameters
    ###loss_train.backward()
    optimizer.step()
    tr_loss = loss_train.item()
    
    if epoch % 2 == 0:
        # printing the validation loss
        print('Epoch : ', epoch + 1, '\t', 'loss :', loss_train, loss_val)

   train_losses = []
    # empty list to store validation losses
    val_losses = []
    correct = 0
    total = 0
    predictions =[]
    actuals=[]
    predictiontest=[]
    # training the model
    m1=0
    m2=0
    for epoch in range(n_epochs):
        
      train(epoch)
     
    # plotting the training and validation loss
    plt.plot(train_losses, label='Training loss')
    plt.plot(val_losses, label='Validation loss')

RuntimeError: Can’t call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead.

help me plzz

2

Did you try to use the suggested approach from the error message?

It seems you are trying to call numpy() on a tensor which is attached to the computation graph so would need to detach it first.

3

@ptrblck I did not understand how I solve

4

Try to call tensor.detach().cpu().numpy() instead of tensor.numpy().

5

@ptrblck in my coded

with torch.no_grad():
        output1 = model((train_x.float()))     

        softmax1 = torch.exp(output1).cpu()    
        prob1 = list(softmax1.numpy())

I replace this numpy() by tensor.detach().cpu().numpy() ??