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, 363kB/s]
  1%|          | 229k/26.4M [00:00<00:38, 681kB/s]
  3%|▎         | 885k/26.4M [00:00<00:12, 2.02MB/s]
 14%|█▎        | 3.57M/26.4M [00:00<00:03, 7.08MB/s]
 36%|███▋      | 9.63M/26.4M [00:00<00:01, 16.6MB/s]
 60%|█████▉    | 15.7M/26.4M [00:01<00:00, 22.4MB/s]
 78%|███████▊  | 20.5M/26.4M [00:01<00:00, 27.8MB/s]
 93%|█████████▎| 24.5M/26.4M [00:01<00:00, 26.2MB/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, 327kB/s]

  0%|          | 0.00/4.42M [00:00<?, ?B/s]
  1%|▏         | 65.5k/4.42M [00:00<00:12, 359kB/s]
  4%|▍         | 197k/4.42M [00:00<00:07, 570kB/s]
 19%|█▉        | 852k/4.42M [00:00<00:01, 1.95MB/s]
 76%|███████▋  | 3.38M/4.42M [00:00<00:00, 6.63MB/s]
100%|██████████| 4.42M/4.42M [00:00<00:00, 6.03MB/s]

  0%|          | 0.00/5.15k [00:00<?, ?B/s]
100%|██████████| 5.15k/5.15k [00:00<00:00, 30.8MB/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)))

Sneaker  Sandal  T-shirt/top  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([[0.6335, 0.8404, 0.7911, 0.0527, 0.9522, 0.6044, 0.6361, 0.5268, 0.6741,
         0.0745],
        [0.0858, 0.7118, 0.1284, 0.7213, 0.8344, 0.4634, 0.2952, 0.4063, 0.3951,
         0.7342],
        [0.4290, 0.9676, 0.1062, 0.0758, 0.2829, 0.3220, 0.6016, 0.7543, 0.9236,
         0.4663],
        [0.0707, 0.6166, 0.7924, 0.4642, 0.5513, 0.0921, 0.2721, 0.0640, 0.7682,
         0.5982]])
tensor([1, 5, 3, 7])
Total loss for this batch: 2.473301410675049

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: 1.7145920102149248
  batch 2000 loss: 0.8235682709794492
  batch 3000 loss: 0.7207916981494055
  batch 4000 loss: 0.6275576916576828
  batch 5000 loss: 0.6042224839720876
  batch 6000 loss: 0.5623287307145074
  batch 7000 loss: 0.5364523524737451
  batch 8000 loss: 0.5037632062113844
  batch 9000 loss: 0.4933920327766391
  batch 10000 loss: 0.49161900748318293
  batch 11000 loss: 0.4789795746002346
  batch 12000 loss: 0.44408697785879486
  batch 13000 loss: 0.41461889480426906
  batch 14000 loss: 0.4216751749664545
  batch 15000 loss: 0.42592228615214117
LOSS train 0.42592228615214117 valid 0.42898499965667725
EPOCH 2:
  batch 1000 loss: 0.40419557761889885
  batch 2000 loss: 0.40585206551736336
  batch 3000 loss: 0.3693359024801175
  batch 4000 loss: 0.4005058672881569
  batch 5000 loss: 0.35799718544336795
  batch 6000 loss: 0.37616050212885604
  batch 7000 loss: 0.362023459906457
  batch 8000 loss: 0.3696461351417529
  batch 9000 loss: 0.3613383244249562
  batch 10000 loss: 0.3588132489417039
  batch 11000 loss: 0.3686094664734992
  batch 12000 loss: 0.37369391124557294
  batch 13000 loss: 0.35058256195962895
  batch 14000 loss: 0.34978781719107066
  batch 15000 loss: 0.3428797536211787
LOSS train 0.3428797536211787 valid 0.36259883642196655
EPOCH 3:
  batch 1000 loss: 0.34094711185975757
  batch 2000 loss: 0.32355542407097526
  batch 3000 loss: 0.33627194206009153
  batch 4000 loss: 0.3225269444920705
  batch 5000 loss: 0.33323195794012284
  batch 6000 loss: 0.3036006186067243
  batch 7000 loss: 0.3310658884346776
  batch 8000 loss: 0.32868925408500943
  batch 9000 loss: 0.3085202551511175
  batch 10000 loss: 0.3115400400201033
  batch 11000 loss: 0.30975718266579133
  batch 12000 loss: 0.3028712621678387
  batch 13000 loss: 0.31091342667635036
  batch 14000 loss: 0.33600624543541924
  batch 15000 loss: 0.30540612479025003
LOSS train 0.30540612479025003 valid 0.3292856812477112
EPOCH 4:
  batch 1000 loss: 0.2928314355900511
  batch 2000 loss: 0.2787869850393181
  batch 3000 loss: 0.28585888121119934
  batch 4000 loss: 0.3000644226927943
  batch 5000 loss: 0.30355137911041674
  batch 6000 loss: 0.2814378829449997
  batch 7000 loss: 0.288217053858345
  batch 8000 loss: 0.28591725382947336
  batch 9000 loss: 0.30822685341428585
  batch 10000 loss: 0.2997927851047243
  batch 11000 loss: 0.2995932452319248
  batch 12000 loss: 0.274024466788469
  batch 13000 loss: 0.3123988458639651
  batch 14000 loss: 0.3086550104165217
  batch 15000 loss: 0.28720580484875247
LOSS train 0.28720580484875247 valid 0.3164930045604706
EPOCH 5:
  batch 1000 loss: 0.2530782210218349
  batch 2000 loss: 0.28425286195498484
  batch 3000 loss: 0.2794657775498126
  batch 4000 loss: 0.2643006381587911
  batch 5000 loss: 0.2763024186127186
  batch 6000 loss: 0.2886416846691336
  batch 7000 loss: 0.28484058134279255
  batch 8000 loss: 0.2711345990908121
  batch 9000 loss: 0.26837128878933797
  batch 10000 loss: 0.27452892530261486
  batch 11000 loss: 0.2744442263479905
  batch 12000 loss: 0.2715800129591371
  batch 13000 loss: 0.273013107275292
  batch 14000 loss: 0.29252272258620177
  batch 15000 loss: 0.271147990041005
LOSS train 0.271147990041005 valid 0.30869561433792114

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