def train_model()

in sdk/python/jobs/single-step/pytorch/train-hyperparameter-tune-deploy-with-pytorch/src/pytorch_train.py [0:0]

• 47 lines of code
• 12 McCabe index (conditional complexity)

def train_model(model, criterion, optimizer, scheduler, num_epochs, data_dir):
    """Train the model."""

    # load training/validation data
    dataloaders, dataset_sizes, class_names = load_data(data_dir)

    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

    since = time.time()

    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0

    for epoch in range(num_epochs):
        print("Epoch {}/{}".format(epoch, num_epochs - 1))
        print("-" * 10)

        # Each epoch has a training and validation phase
        for phase in ["train", "val"]:
            if phase == "train":
                scheduler.step()
                model.train()  # Set model to training mode
            else:
                model.eval()  # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = labels.to(device)

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward
                # track history if only in train
                with torch.set_grad_enabled(phase == "train"):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)

                    # backward + optimize only if in training phase
                    if phase == "train":
                        loss.backward()
                        optimizer.step()

                # statistics
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects.double() / dataset_sizes[phase]

            print("{} Loss: {:.4f} Acc: {:.4f}".format(phase, epoch_loss, epoch_acc))

            # deep copy the model
            if phase == "val" and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())

            # log the best val accuracy to AML run
            mlflow.log_metric("best_val_acc", np.float(best_acc))

        print()

    time_elapsed = time.time() - since
    print(
        "Training complete in {:.0f}m {:.0f}s".format(
            time_elapsed // 60, time_elapsed % 60
        )
    )
    print("Best val Acc: {:4f}".format(best_acc))

    # load best model weights
    model.load_state_dict(best_model_wts)
    return model