Shortcuts

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)))
trainingyt
Sandal  Sneaker  Ankle Boot  Coat

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([[0.3557, 0.8645, 0.5204, 0.7741, 0.1139, 0.4145, 0.7348, 0.6162, 0.7117,
         0.4355],
        [0.1968, 0.2940, 0.9526, 0.3006, 0.2524, 0.0563, 0.8280, 0.6981, 0.1534,
         0.7943],
        [0.8296, 0.4251, 0.3695, 0.4926, 0.9087, 0.2559, 0.7270, 0.5436, 0.4969,
         0.0528],
        [0.2731, 0.1459, 0.0121, 0.0764, 0.9622, 0.0705, 0.4019, 0.9218, 0.3255,
         0.4819]])
tensor([1, 5, 3, 7])
Total loss for this batch: 2.2294564247131348

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)

    # We don't need gradients on to do reporting
    model.train(False)

    running_vloss = 0.0
    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: 1.7202785748690366
  batch 2000 loss: 0.845874194022268
  batch 3000 loss: 0.732324289727956
  batch 4000 loss: 0.6354306528866291
  batch 5000 loss: 0.6131504484317265
  batch 6000 loss: 0.567986206448637
  batch 7000 loss: 0.5372601917202119
  batch 8000 loss: 0.5053758663563058
  batch 9000 loss: 0.49465197931975124
  batch 10000 loss: 0.5076907618881669
  batch 11000 loss: 0.46406069002777806
  batch 12000 loss: 0.4415618053285871
  batch 13000 loss: 0.44091974885249513
  batch 14000 loss: 0.4528954788306728
  batch 15000 loss: 0.4185415775780857
LOSS train 0.4185415775780857 valid 0.46565160155296326
EPOCH 2:
  batch 1000 loss: 0.40298158676864115
  batch 2000 loss: 0.40473773716104916
  batch 3000 loss: 0.38914263153739737
  batch 4000 loss: 0.3757844932905864
  batch 5000 loss: 0.3827904837153619
  batch 6000 loss: 0.3848549308850488
  batch 7000 loss: 0.3905026990728802
  batch 8000 loss: 0.38856515373918227
  batch 9000 loss: 0.3564304211178387
  batch 10000 loss: 0.36028160640364515
  batch 11000 loss: 0.3723825469583971
  batch 12000 loss: 0.36065482496072215
  batch 13000 loss: 0.33004516918264565
  batch 14000 loss: 0.33926659194543024
  batch 15000 loss: 0.36926333564339436
LOSS train 0.36926333564339436 valid 0.3682301342487335
EPOCH 3:
  batch 1000 loss: 0.33908599126932676
  batch 2000 loss: 0.33328665195067153
  batch 3000 loss: 0.34383849349398227
  batch 4000 loss: 0.3386286224864598
  batch 5000 loss: 0.30894843620294704
  batch 6000 loss: 0.31473890036073865
  batch 7000 loss: 0.35206592389044816
  batch 8000 loss: 0.34070784154451755
  batch 9000 loss: 0.32317093205050335
  batch 10000 loss: 0.31863069278492184
  batch 11000 loss: 0.3223233843835915
  batch 12000 loss: 0.3212246052912378
  batch 13000 loss: 0.313270448437077
  batch 14000 loss: 0.3107176462450734
  batch 15000 loss: 0.3348360576608102
LOSS train 0.3348360576608102 valid 0.3295780420303345
EPOCH 4:
  batch 1000 loss: 0.30621629190409294
  batch 2000 loss: 0.30041255712847487
  batch 3000 loss: 0.3135477342647937
  batch 4000 loss: 0.3057122708450479
  batch 5000 loss: 0.29008026074404913
  batch 6000 loss: 0.2992399424277246
  batch 7000 loss: 0.31303461115027315
  batch 8000 loss: 0.3122637828371662
  batch 9000 loss: 0.29342313165057565
  batch 10000 loss: 0.3023379071165909
  batch 11000 loss: 0.29337365927846987
  batch 12000 loss: 0.301957116057888
  batch 13000 loss: 0.29463459993346985
  batch 14000 loss: 0.2867325887364932
  batch 15000 loss: 0.2853214175022965
LOSS train 0.2853214175022965 valid 0.3170975148677826
EPOCH 5:
  batch 1000 loss: 0.28858077543755645
  batch 2000 loss: 0.2810371044729436
  batch 3000 loss: 0.2812339045305016
  batch 4000 loss: 0.2746079366629047
  batch 5000 loss: 0.2683956420585473
  batch 6000 loss: 0.2631060717847674
  batch 7000 loss: 0.2790748407724029
  batch 8000 loss: 0.27848986026216155
  batch 9000 loss: 0.27318187057405885
  batch 10000 loss: 0.2862526961476833
  batch 11000 loss: 0.2881018204827342
  batch 12000 loss: 0.27561038138403454
  batch 13000 loss: 0.27629870265011414
  batch 14000 loss: 0.297017796376982
  batch 15000 loss: 0.284842627136979
LOSS train 0.284842627136979 valid 0.30397823452949524

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

Total running time of the script: ( 2 minutes 8.094 seconds)

Gallery generated by Sphinx-Gallery


더 궁금하시거나 개선할 내용이 있으신가요? 커뮤니티에 참여해보세요!


이 튜토리얼이 어떠셨나요? 평가해주시면 이후 개선에 참고하겠습니다! :)

© Copyright 2018-2023, PyTorch & 파이토치 한국 사용자 모임(PyTorch Korea User Group).

Built with Sphinx using a theme provided by Read the Docs.

PyTorchKorea @ GitHub

파이토치 한국 사용자 모임을 GitHub에서 만나보세요.

GitHub로 이동

한국어 튜토리얼

한국어로 번역 중인 PyTorch 튜토리얼입니다.

튜토리얼로 이동

커뮤니티

다른 사용자들과 의견을 나누고, 도와주세요!

커뮤니티로 이동