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

Training with PyTorch

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)))

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  Sneaker  Coat  Sneaker

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([[0.7026, 0.1489, 0.0065, 0.6841, 0.4166, 0.3980, 0.9849, 0.6701, 0.4601,
         0.8599],
        [0.7461, 0.3920, 0.9978, 0.0354, 0.9843, 0.0312, 0.5989, 0.2888, 0.8170,
         0.4150],
        [0.8408, 0.5368, 0.0059, 0.8931, 0.3942, 0.7349, 0.5500, 0.0074, 0.0554,
         0.1537],
        [0.7282, 0.8755, 0.3649, 0.4566, 0.8796, 0.2390, 0.9865, 0.7549, 0.9105,
         0.5427]])
tensor([1, 5, 3, 7])
Total loss for this batch: 2.428950071334839

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: 1.6334228541590274
  batch 2000 loss: 0.8324381597135216
  batch 3000 loss: 0.7350949151031673
  batch 4000 loss: 0.6221513676682953
  batch 5000 loss: 0.6008665340302978
  batch 6000 loss: 0.5533551393696107
  batch 7000 loss: 0.5268192595622968
  batch 8000 loss: 0.4953766325986944
  batch 9000 loss: 0.4763272075761342
  batch 10000 loss: 0.48026260716759134
  batch 11000 loss: 0.4555706014999887
  batch 12000 loss: 0.43150419856602096
  batch 13000 loss: 0.41889463035896185
  batch 14000 loss: 0.4101380754457787
  batch 15000 loss: 0.4188491042831447
LOSS train 0.4188491042831447 valid 0.42083388566970825
EPOCH 2:
  batch 1000 loss: 0.39033183104451746
  batch 2000 loss: 0.35730057470843896
  batch 3000 loss: 0.3797398313785088
  batch 4000 loss: 0.3595128281345387
  batch 5000 loss: 0.3674602470536483
  batch 6000 loss: 0.3695404906652402
  batch 7000 loss: 0.38634192156628705
  batch 8000 loss: 0.37888678515458013
  batch 9000 loss: 0.32936658181797246
  batch 10000 loss: 0.3460305611458316
  batch 11000 loss: 0.355949883276422
  batch 12000 loss: 0.34613123371596155
  batch 13000 loss: 0.3435088261961791
  batch 14000 loss: 0.35190882972519466
  batch 15000 loss: 0.34078337761512373
LOSS train 0.34078337761512373 valid 0.3449384272098541
EPOCH 3:
  batch 1000 loss: 0.3336456001721235
  batch 2000 loss: 0.2948776570415939
  batch 3000 loss: 0.30873254264354183
  batch 4000 loss: 0.3269525112561532
  batch 5000 loss: 0.3081500146031831
  batch 6000 loss: 0.33906219027831686
  batch 7000 loss: 0.3114977335120493
  batch 8000 loss: 0.3028961390093173
  batch 9000 loss: 0.31883212575598735
  batch 10000 loss: 0.3121348040100274
  batch 11000 loss: 0.3204089922408457
  batch 12000 loss: 0.3172754702415841
  batch 13000 loss: 0.3022056705406212
  batch 14000 loss: 0.29925711060611504
  batch 15000 loss: 0.3158802612772852
LOSS train 0.3158802612772852 valid 0.32655972242355347
EPOCH 4:
  batch 1000 loss: 0.2793223039015138
  batch 2000 loss: 0.2759745200898469
  batch 3000 loss: 0.2885438525550344
  batch 4000 loss: 0.29715126178535867
  batch 5000 loss: 0.3092308461628054
  batch 6000 loss: 0.29819886386692085
  batch 7000 loss: 0.28212033420058286
  batch 8000 loss: 0.2652145917697999
  batch 9000 loss: 0.30505836525483027
  batch 10000 loss: 0.28172129570529797
  batch 11000 loss: 0.2760911153540328
  batch 12000 loss: 0.29349113235381813
  batch 13000 loss: 0.28226990548134745
  batch 14000 loss: 0.2974613601177407
  batch 15000 loss: 0.3016561955644138
LOSS train 0.3016561955644138 valid 0.3930961787700653
EPOCH 5:
  batch 1000 loss: 0.2611404411364929
  batch 2000 loss: 0.25894880425418887
  batch 3000 loss: 0.2585991551137176
  batch 4000 loss: 0.2808971864393097
  batch 5000 loss: 0.26857244527151486
  batch 6000 loss: 0.2778763904040534
  batch 7000 loss: 0.2556428771363862
  batch 8000 loss: 0.2892738865161955
  batch 9000 loss: 0.2898595165217885
  batch 10000 loss: 0.24955335284502145
  batch 11000 loss: 0.27326060194405
  batch 12000 loss: 0.2833696024138153
  batch 13000 loss: 0.2705353221144751
  batch 14000 loss: 0.24937306600230658
  batch 15000 loss: 0.27901125454565046
LOSS train 0.27901125454565046 valid 0.3100835084915161

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