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 31, 2023 | 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.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
import torchvision.transforms as transforms

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


transform = transforms.Compose(
    [transforms.ToTensor(),
    transforms.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('Training set has {} instances'.format(len(training_set)))
print('Validation set has {} instances'.format(len(validation_set)))

  0%|          | 0.00/26.4M [00:00<?, ?B/s]
  0%|          | 65.5k/26.4M [00:00<01:12, 362kB/s]
  1%|          | 229k/26.4M [00:00<00:38, 681kB/s]
  3%|▎         | 852k/26.4M [00:00<00:13, 1.94MB/s]
 13%|█▎        | 3.44M/26.4M [00:00<00:03, 6.79MB/s]
 36%|███▌      | 9.50M/26.4M [00:00<00:01, 16.4MB/s]
 59%|█████▊    | 15.5M/26.4M [00:01<00:00, 22.0MB/s]
 82%|████████▏ | 21.7M/26.4M [00:01<00:00, 26.0MB/s]
100%|██████████| 26.4M/26.4M [00:01<00:00, 19.3MB/s]

  0%|          | 0.00/29.5k [00:00<?, ?B/s]
100%|██████████| 29.5k/29.5k [00:00<00:00, 328kB/s]

  0%|          | 0.00/4.42M [00:00<?, ?B/s]
  1%|▏         | 65.5k/4.42M [00:00<00:12, 362kB/s]
  5%|▌         | 229k/4.42M [00:00<00:06, 682kB/s]
 21%|██        | 918k/4.42M [00:00<00:01, 2.10MB/s]
 83%|████████▎ | 3.67M/4.42M [00:00<00:00, 7.27MB/s]
100%|██████████| 4.42M/4.42M [00:00<00:00, 6.09MB/s]

  0%|          | 0.00/5.15k [00:00<?, ?B/s]
100%|██████████| 5.15k/5.15k [00:00<00:00, 52.7MB/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)))

Pullover  Sneaker  Sandal  Trouser

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(GarmentClassifier, self).__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('Total loss for this batch: {}'.format(loss.item()))

tensor([[0.1738, 0.1524, 0.0309, 0.4891, 0.7602, 0.1513, 0.5012, 0.5772, 0.4416,
         0.5611],
        [0.5069, 0.9598, 0.5699, 0.2628, 0.8927, 0.3696, 0.0405, 0.7505, 0.7107,
         0.2398],
        [0.4360, 0.3193, 0.2203, 0.6215, 0.4130, 0.6750, 0.4002, 0.4607, 0.1738,
         0.2239],
        [0.5604, 0.7513, 0.4779, 0.3549, 0.4414, 0.2100, 0.8822, 0.5509, 0.3112,
         0.8924]])
tensor([1, 5, 3, 7])
Total loss for this batch: 2.3678841590881348

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('  batch {} loss: {}'.format(i + 1, 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('runs/fashion_trainer_{}'.format(timestamp))
epoch_number = 0

EPOCHS = 5

best_vloss = 1_000_000.

for epoch in range(EPOCHS):
    print('EPOCH {}:'.format(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('LOSS train {} valid {}'.format(avg_loss, 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 = 'model_{}_{}'.format(timestamp, epoch_number)
        torch.save(model.state_dict(), model_path)

    epoch_number += 1

EPOCH 1:
  batch 1000 loss: 1.8858949508666991
  batch 2000 loss: 0.8253540680715814
  batch 3000 loss: 0.7029954082183539
  batch 4000 loss: 0.6235998484961456
  batch 5000 loss: 0.6021948530338704
  batch 6000 loss: 0.5721047330989968
  batch 7000 loss: 0.5107071617020993
  batch 8000 loss: 0.49358848758332896
  batch 9000 loss: 0.472066092497902
  batch 10000 loss: 0.4754930540170753
  batch 11000 loss: 0.45402154320210686
  batch 12000 loss: 0.476449992939597
  batch 13000 loss: 0.42854416111379395
  batch 14000 loss: 0.4234786861875327
  batch 15000 loss: 0.40942823638697157
LOSS train 0.40942823638697157 valid 0.43071553111076355
EPOCH 2:
  batch 1000 loss: 0.42588597617764024
  batch 2000 loss: 0.4014824729000684
  batch 3000 loss: 0.38625473850197156
  batch 4000 loss: 0.3829549978270661
  batch 5000 loss: 0.3847250122866826
  batch 6000 loss: 0.36429688713364883
  batch 7000 loss: 0.387048584116681
  batch 8000 loss: 0.37762961884832474
  batch 9000 loss: 0.38527828438940925
  batch 10000 loss: 0.3575005230311799
  batch 11000 loss: 0.3470037491089315
  batch 12000 loss: 0.3586366216586321
  batch 13000 loss: 0.3542666059020994
  batch 14000 loss: 0.34874988160590875
  batch 15000 loss: 0.35706947678347933
LOSS train 0.35706947678347933 valid 0.3465743660926819
EPOCH 3:
  batch 1000 loss: 0.33074528904895123
  batch 2000 loss: 0.3366497194762342
  batch 3000 loss: 0.3321119079241762
  batch 4000 loss: 0.3267548837979848
  batch 5000 loss: 0.31407298621948576
  batch 6000 loss: 0.3163806858165772
  batch 7000 loss: 0.33558194709911915
  batch 8000 loss: 0.32354416232123184
  batch 9000 loss: 0.32098647650849305
  batch 10000 loss: 0.2995396272375037
  batch 11000 loss: 0.33434525950111127
  batch 12000 loss: 0.3118759000442674
  batch 13000 loss: 0.32606208193562636
  batch 14000 loss: 0.32317182823370966
  batch 15000 loss: 0.3153763594997399
LOSS train 0.3153763594997399 valid 0.3625868558883667
EPOCH 4:
  batch 1000 loss: 0.311724279472699
  batch 2000 loss: 0.30374270691718264
  batch 3000 loss: 0.29485863707353926
  batch 4000 loss: 0.2958039883861584
  batch 5000 loss: 0.2929758029977966
  batch 6000 loss: 0.314122219143821
  batch 7000 loss: 0.3195479475443135
  batch 8000 loss: 0.2810526036817464
  batch 9000 loss: 0.2893854405378661
  batch 10000 loss: 0.2838528581634164
  batch 11000 loss: 0.29831466531276235
  batch 12000 loss: 0.2869449937127356
  batch 13000 loss: 0.3012405734501517
  batch 14000 loss: 0.291908602690557
  batch 15000 loss: 0.2953515689158003
LOSS train 0.2953515689158003 valid 0.31732383370399475
EPOCH 5:
  batch 1000 loss: 0.27049518805105616
  batch 2000 loss: 0.2768019415046583
  batch 3000 loss: 0.2607175925662887
  batch 4000 loss: 0.28726730807768763
  batch 5000 loss: 0.2853227079210992
  batch 6000 loss: 0.2892833945671855
  batch 7000 loss: 0.2774344372921187
  batch 8000 loss: 0.27457155733661787
  batch 9000 loss: 0.28711449797423483
  batch 10000 loss: 0.278477436379304
  batch 11000 loss: 0.28131438646370455
  batch 12000 loss: 0.28872690925986355
  batch 13000 loss: 0.27541564789701806
  batch 14000 loss: 0.26372287162054997
  batch 15000 loss: 0.2538918277323028
LOSS train 0.2538918277323028 valid 0.3073248565196991

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