train_image_rnn.py

for epoch in range(N_EPHOCS):  # loop over the dataset multiple times
    train_running_loss = 0.0
    train_acc = 0.0
    model.train()
    
    # TRAINING ROUND
    for i, data in enumerate(trainloader):
         # zero the parameter gradients
        optimizer.zero_grad()
        
        # reset hidden states
        model.hidden = model.init_hidden() 
        
        # get the inputs
        inputs, labels = data
        inputs = inputs.view(-1, 28,28) 

        # forward + backward + optimize
        outputs = model(inputs)

        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        train_running_loss += loss.detach().item()
        train_acc += get_accuracy(outputs, labels, BATCH_SIZE)
         
    model.eval()
    print('Epoch:  %d | Loss: %.4f | Train Accuracy: %.2f' 
          %(epoch, train_running_loss / i, train_acc/i))
### output
'''
Epoch:  0 | Loss: 0.7149 | Train Accuracy: 75.81
Epoch:  1 | Loss: 0.2770 | Train Accuracy: 91.46
Epoch:  2 | Loss: 0.2099 | Train Accuracy: 93.58
Epoch:  3 | Loss: 0.1766 | Train Accuracy: 94.50
Epoch:  4 | Loss: 0.1638 | Train Accuracy: 94.94
Epoch:  5 | Loss: 0.1457 | Train Accuracy: 95.44
Epoch:  6 | Loss: 0.1347 | Train Accuracy: 95.81
Epoch:  7 | Loss: 0.1299 | Train Accuracy: 95.87
Epoch:  8 | Loss: 0.1228 | Train Accuracy: 96.06
Epoch:  9 | Loss: 0.1140 | Train Accuracy: 96.45
'''