beginner/introyt/trainingyt

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

Introduction || Tensors || Autograd || Building Models || TensorBoard Support || Training Models || Model Understanding

Training with PyTorch

Created On: Nov 30, 2021 | Last Updated: May 06, 2026 | Last Verified: Nov 05, 2024

Follow along with the video below or on youtube.

Introduction

In past videos, we’ve discussed and demonstrated:

• Building models with the neural network layers and functions of the torch.nn module

• The mechanics of automated gradient computation, which is central to gradient-based model training

• Using TensorBoard to visualize training progress and other activities

In this video, we’ll be adding some new tools to your inventory:

• We’ll get familiar with the dataset and dataloader abstractions, and how they ease the process of feeding data to your model during a training loop

• We’ll discuss specific loss functions and when to use them

• We’ll look at PyTorch optimizers, which implement algorithms to adjust model weights based on the outcome of a loss function

Finally, we’ll pull all of these together and see a full PyTorch training loop in action.

Dataset and DataLoader

The Dataset and DataLoader classes encapsulate the process of pulling your data from storage and exposing it to your training loop in batches.

The Dataset is responsible for accessing and processing single instances of data.

The DataLoader pulls instances of data from the Dataset (either automatically or with a sampler that you define), collects them in batches, and returns them for consumption by your training loop. The DataLoader works with all kinds of datasets, regardless of the type of data they contain.

For this tutorial, we’ll be using the Fashion-MNIST dataset provided by TorchVision. We use torchvision.transforms.v2.Normalize() to zero-center and normalize the distribution of the image tile content, and download both training and validation data splits.

import torch
import torchvision
from torchvision.transforms import v2

# PyTorch TensorBoard support
from torch.utils.tensorboard import SummaryWriter
from datetime import datetime


transform = v2.Compose([
    v2.ToImage(),
    v2.ToDtype(torch.float32, scale=True),
    v2.Normalize((0.5,), (0.5,))
])

# Create datasets for training & validation, download if necessary
training_set = torchvision.datasets.FashionMNIST('./data', train=True, transform=transform, download=True)
validation_set = torchvision.datasets.FashionMNIST('./data', train=False, transform=transform, download=True)

# Create data loaders for our datasets; shuffle for training, not for validation
training_loader = torch.utils.data.DataLoader(training_set, batch_size=4, shuffle=True)
validation_loader = torch.utils.data.DataLoader(validation_set, batch_size=4, shuffle=False)

# Class labels
classes = ('T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
        'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle Boot')

# Report split sizes
print(f'Training set has {len(training_set)} instances')
print(f'Validation set has {len(validation_set)} instances')

  0%|          | 0.00/26.4M [00:00<?, ?B/s]
  0%|          | 65.5k/26.4M [00:00<01:11, 366kB/s]
  1%|          | 229k/26.4M [00:00<00:38, 688kB/s]
  3%|▎         | 918k/26.4M [00:00<00:12, 2.12MB/s]
 14%|█▍        | 3.67M/26.4M [00:00<00:03, 7.32MB/s]
 35%|███▍      | 9.14M/26.4M [00:00<00:01, 15.7MB/s]
 57%|█████▋    | 15.0M/26.4M [00:01<00:00, 21.4MB/s]
 79%|███████▉  | 20.9M/26.4M [00:01<00:00, 25.1MB/s]
100%|██████████| 26.4M/26.4M [00:01<00:00, 19.5MB/s]

  0%|          | 0.00/29.5k [00:00<?, ?B/s]
100%|██████████| 29.5k/29.5k [00:00<00:00, 337kB/s]

  0%|          | 0.00/4.42M [00:00<?, ?B/s]
  1%|▏         | 65.5k/4.42M [00:00<00:11, 375kB/s]
  5%|▌         | 229k/4.42M [00:00<00:05, 705kB/s]
 21%|██        | 918k/4.42M [00:00<00:01, 2.18MB/s]
 83%|████████▎ | 3.67M/4.42M [00:00<00:00, 7.51MB/s]
100%|██████████| 4.42M/4.42M [00:00<00:00, 6.28MB/s]

  0%|          | 0.00/5.15k [00:00<?, ?B/s]
100%|██████████| 5.15k/5.15k [00:00<00:00, 57.3MB/s]
Training set has 60000 instances
Validation set has 10000 instances

As always, let’s visualize the data as a sanity check:

import matplotlib.pyplot as plt
import numpy as np

# Helper function for inline image display
def matplotlib_imshow(img, one_channel=False):
    if one_channel:
        img = img.mean(dim=0)
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    if one_channel:
        plt.imshow(npimg, cmap="Greys")
    else:
        plt.imshow(np.transpose(npimg, (1, 2, 0)))

dataiter = iter(training_loader)
images, labels = next(dataiter)

# Create a grid from the images and show them
img_grid = torchvision.utils.make_grid(images)
matplotlib_imshow(img_grid, one_channel=True)
print('  '.join(classes[labels[j]] for j in range(4)))

Sandal  Sandal  Bag  T-shirt/top

The Model

The model we’ll use in this example is a variant of LeNet-5 - it should be familiar if you’ve watched the previous videos in this series.

import torch.nn as nn
import torch.nn.functional as F

# PyTorch models inherit from torch.nn.Module
class GarmentClassifier(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 4 * 4, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 4 * 4)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


model = GarmentClassifier()

Loss Function

For this example, we’ll be using a cross-entropy loss. For demonstration purposes, we’ll create batches of dummy output and label values, run them through the loss function, and examine the result.

loss_fn = torch.nn.CrossEntropyLoss()

# NB: Loss functions expect data in batches, so we're creating batches of 4
# Represents the model's confidence in each of the 10 classes for a given input
dummy_outputs = torch.rand(4, 10)
# Represents the correct class among the 10 being tested
dummy_labels = torch.tensor([1, 5, 3, 7])

print(dummy_outputs)
print(dummy_labels)

loss = loss_fn(dummy_outputs, dummy_labels)
print(f'Total loss for this batch: {loss.item()}')

tensor([[0.1063, 0.4805, 0.3113, 0.2341, 0.6327, 0.0655, 0.8668, 0.2094, 0.1315,
         0.0075],
        [0.2904, 0.0943, 0.8309, 0.4719, 0.4114, 0.0227, 0.4410, 0.1284, 0.3970,
         0.0783],
        [0.0920, 0.9528, 0.3411, 0.1153, 0.3330, 0.0112, 0.1891, 0.7977, 0.9695,
         0.7480],
        [0.5943, 0.2169, 0.1453, 0.4899, 0.0082, 0.8484, 0.0590, 0.2488, 0.4550,
         0.8911]])
tensor([1, 5, 3, 7])
Total loss for this batch: 2.497455596923828

Optimizer

For this example, we’ll be using simple stochastic gradient descent with momentum.

It can be instructive to try some variations on this optimization scheme:

• Learning rate determines the size of the steps the optimizer takes. What does a different learning rate do to the your training results, in terms of accuracy and convergence time?

• Momentum nudges the optimizer in the direction of strongest gradient over multiple steps. What does changing this value do to your results?

• Try some different optimization algorithms, such as averaged SGD, Adagrad, or Adam. How do your results differ?

# Optimizers specified in the torch.optim package
optimizer = torch.optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

The Training Loop

Below, we have a function that performs one training epoch. It enumerates data from the DataLoader, and on each pass of the loop does the following:

• Gets a batch of training data from the DataLoader

• Zeros the optimizer’s gradients

• Performs an inference - that is, gets predictions from the model for an input batch

• Calculates the loss for that set of predictions vs. the labels on the dataset

• Calculates the backward gradients over the learning weights

• Tells the optimizer to perform one learning step - that is, adjust the model’s learning weights based on the observed gradients for this batch, according to the optimization algorithm we chose

• It reports on the loss for every 1000 batches.

• Finally, it reports the average per-batch loss for the last 1000 batches, for comparison with a validation run

def train_one_epoch(epoch_index, tb_writer):
    running_loss = 0.
    last_loss = 0.

    # Here, we use enumerate(training_loader) instead of
    # iter(training_loader) so that we can track the batch
    # index and do some intra-epoch reporting
    for i, data in enumerate(training_loader):
        # Every data instance is an input + label pair
        inputs, labels = data

        # Zero your gradients for every batch!
        optimizer.zero_grad()

        # Make predictions for this batch
        outputs = model(inputs)

        # Compute the loss and its gradients
        loss = loss_fn(outputs, labels)
        loss.backward()

        # Adjust learning weights
        optimizer.step()

        # Gather data and report
        running_loss += loss.item()
        if i % 1000 == 999:
            last_loss = running_loss / 1000 # loss per batch
            print(f'  batch {i + 1} loss: {last_loss}')
            tb_x = epoch_index * len(training_loader) + i + 1
            tb_writer.add_scalar('Loss/train', last_loss, tb_x)
            running_loss = 0.

    return last_loss

Per-Epoch Activity

There are a couple of things we’ll want to do once per epoch:

• Perform validation by checking our relative loss on a set of data that was not used for training, and report this

• Save a copy of the model

Here, we’ll do our reporting in TensorBoard. This will require going to the command line to start TensorBoard, and opening it in another browser tab.

# Initializing in a separate cell so we can easily add more epochs to the same run
timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
writer = SummaryWriter(f'runs/fashion_trainer_{timestamp}')
epoch_number = 0

EPOCHS = 5

best_vloss = 1_000_000.

for epoch in range(EPOCHS):
    print(f'EPOCH {epoch_number + 1}:')

    # Make sure gradient tracking is on, and do a pass over the data
    model.train(True)
    avg_loss = train_one_epoch(epoch_number, writer)


    running_vloss = 0.0
    # Set the model to evaluation mode, disabling dropout and using population
    # statistics for batch normalization.
    model.eval()

    # Disable gradient computation and reduce memory consumption.
    with torch.no_grad():
        for i, vdata in enumerate(validation_loader):
            vinputs, vlabels = vdata
            voutputs = model(vinputs)
            vloss = loss_fn(voutputs, vlabels)
            running_vloss += vloss

    avg_vloss = running_vloss / (i + 1)
    print(f'LOSS train {avg_loss} valid {avg_vloss}')

    # Log the running loss averaged per batch
    # for both training and validation
    writer.add_scalars('Training vs. Validation Loss',
                    { 'Training' : avg_loss, 'Validation' : avg_vloss },
                    epoch_number + 1)
    writer.flush()

    # Track best performance, and save the model's state
    if avg_vloss < best_vloss:
        best_vloss = avg_vloss
        model_path = f'model_{timestamp}_{epoch_number}'
        torch.save(model.state_dict(), model_path)

    epoch_number += 1

EPOCH 1:
  batch 1000 loss: 1.654247484177351
  batch 2000 loss: 0.7726962686181068
  batch 3000 loss: 0.6987732860718389
  batch 4000 loss: 0.6221569780111312
  batch 5000 loss: 0.5804557499862276
  batch 6000 loss: 0.5524890179708017
  batch 7000 loss: 0.5295137383388355
  batch 8000 loss: 0.5009265253145714
  batch 9000 loss: 0.5058054737325292
  batch 10000 loss: 0.49260745361773295
  batch 11000 loss: 0.468585665261955
  batch 12000 loss: 0.45380957032914737
  batch 13000 loss: 0.44796896913426465
  batch 14000 loss: 0.41935056390626413
  batch 15000 loss: 0.4201206929102191
LOSS train 0.4201206929102191 valid 0.40279826521873474
EPOCH 2:
  batch 1000 loss: 0.41227510012625135
  batch 2000 loss: 0.39864704573201015
  batch 3000 loss: 0.4001820913331467
  batch 4000 loss: 0.39508082253983595
  batch 5000 loss: 0.36207930756598944
  batch 6000 loss: 0.35573555010774727
  batch 7000 loss: 0.3830765788261197
  batch 8000 loss: 0.3624298877255933
  batch 9000 loss: 0.3632407153651584
  batch 10000 loss: 0.3778950179115636
  batch 11000 loss: 0.3576152681231906
  batch 12000 loss: 0.36515091116545956
  batch 13000 loss: 0.3611713805411709
  batch 14000 loss: 0.33597958153762736
  batch 15000 loss: 0.343264871072548
LOSS train 0.343264871072548 valid 0.40966489911079407
EPOCH 3:
  batch 1000 loss: 0.32743183934202535
  batch 2000 loss: 0.3444891562992852
  batch 3000 loss: 0.3291725230075281
  batch 4000 loss: 0.3187070913249045
  batch 5000 loss: 0.32714095296346934
  batch 6000 loss: 0.30739905216288754
  batch 7000 loss: 0.32212489395512967
  batch 8000 loss: 0.29795379653651616
  batch 9000 loss: 0.3247700735194667
  batch 10000 loss: 0.315623918322759
  batch 11000 loss: 0.33626489514997226
  batch 12000 loss: 0.32514980087045114
  batch 13000 loss: 0.338065604444957
  batch 14000 loss: 0.3192359950903192
  batch 15000 loss: 0.3433123947502827
LOSS train 0.3433123947502827 valid 0.3421742916107178
EPOCH 4:
  batch 1000 loss: 0.30375947376329715
  batch 2000 loss: 0.29673802652818265
  batch 3000 loss: 0.3037119593455718
  batch 4000 loss: 0.30708115856312906
  batch 5000 loss: 0.3028442856037436
  batch 6000 loss: 0.27089441766872185
  batch 7000 loss: 0.3011226830706473
  batch 8000 loss: 0.2984363955456356
  batch 9000 loss: 0.3007340987546827
  batch 10000 loss: 0.29771704207872973
  batch 11000 loss: 0.31568263667479185
  batch 12000 loss: 0.25841389897736733
  batch 13000 loss: 0.30573024399650606
  batch 14000 loss: 0.31712972641549275
  batch 15000 loss: 0.2965977080956945
LOSS train 0.2965977080956945 valid 0.3430803716182709
EPOCH 5:
  batch 1000 loss: 0.2697474466083549
  batch 2000 loss: 0.2738529558030714
  batch 3000 loss: 0.28960374634153413
  batch 4000 loss: 0.268796529449495
  batch 5000 loss: 0.3020780498078084
  batch 6000 loss: 0.2722164069009668
  batch 7000 loss: 0.2717584210411369
  batch 8000 loss: 0.2732993564447643
  batch 9000 loss: 0.2600738099713435
  batch 10000 loss: 0.2821929820111945
  batch 11000 loss: 0.29318459536922775
  batch 12000 loss: 0.26708484860020687
  batch 13000 loss: 0.2733659076172953
  batch 14000 loss: 0.2895496564986479
  batch 15000 loss: 0.3003611703527422
LOSS train 0.3003611703527422 valid 0.3127398192882538

To load a saved version of the model:

saved_model = GarmentClassifier()
saved_model.load_state_dict(torch.load(PATH))

Once you’ve loaded the model, it’s ready for whatever you need it for - more training, inference, or analysis.

Note that if your model has constructor parameters that affect model structure, you’ll need to provide them and configure the model identically to the state in which it was saved.

Other Resources

• Docs on the data utilities, including Dataset and DataLoader, at pytorch.org

• A note on the use of pinned memory for GPU training

• Documentation on the datasets available in TorchVision, TorchText, and TorchAudio

• Documentation on the loss functions available in PyTorch

• Documentation on the torch.optim package, which includes optimizers and related tools, such as learning rate scheduling

• A detailed tutorial on saving and loading models

• The Tutorials section of pytorch.org contains tutorials on a broad variety of training tasks, including classification in different domains, generative adversarial networks, reinforcement learning, and more