Data augmentation in PyTorch

Let's include data augmentation in your Dataset and inspect some images visually to make sure the desired transformations are applied.

First, you'll add the augmenting transformations to train_transforms. Let's use a random horizontal flip and a rotation by a random angle between 0 and 45 degrees. The code that follows to create the Dataset and the DataLoader is exactly the same as before. Finally, you'll reshape the image and display it to see if the new augmenting transformations are visible.

All the imports you need have been called for you:

from torchvision.datasets import ImageFolder
from torch.utils.data import DataLoader
from torchvision import transforms
import matplotlib.pyplot as plt

Time to augment some cloud photos!

This exercise is part of the course

Intermediate Deep Learning with PyTorch

Exercise instructions

Add two more transformations to train_transforms to perform a random horizontal flip and then a rotation by a random angle between 0 and 45 degrees.
Reshape the image tensor from the DataLoader to make it suitable for display.
Display the image.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

train_transforms = transforms.Compose([
    # Add horizontal flip and rotation
    ____,
    ____,
    transforms.ToTensor(),
    transforms.Resize((128, 128)),
])

dataset_train = ImageFolder(
  "clouds_train",
  transform=train_transforms,
)

dataloader_train = DataLoader(
  dataset_train, shuffle=True, batch_size=1
)

image, label = next(iter(dataloader_train))
# Reshape the image tensor
image = image.____.____(____, ____, ____) 
# Display the image
____
plt.show()

Edit and Run Code

This exercise is part of the course

Intermediate Deep Learning with PyTorch

IntermediateSkill Level

4.8+

Start Course for Free

Learn how to train neural networks in a robust way. In this chapter, you will use object-oriented programming to define PyTorch datasets and models and refresh your knowledge of training and evaluating neural networks. You will also get familiar with different optimizers and, finally, get to grips with various techniques that help mitigate the problems of unstable gradients so ubiquitous in neural nets training.

Exercise 1: PyTorch and object-oriented programming Exercise 2: PyTorch Dataset Exercise 3: PyTorch DataLoader Exercise 4: PyTorch Model Exercise 5: Optimizers, training, and evaluation Exercise 6: Training loop Exercise 7: Optimizers Exercise 8: Model evaluation Exercise 9: Vanishing and exploding gradients Exercise 10: Initialization and activation Exercise 11: Activations: ReLU vs. ELU Exercise 12: Batch Normalization

Train neural networks to solve image classification tasks. In this chapter, you will learn how to handle image data in PyTorch and get to grips with convolutional neural networks (CNNs). You will practice training and evaluating an image classifier while learning about how to improve the model performance with data augmentation.

Exercise 1: Handling images with PyTorch Exercise 2: Image dataset Exercise 3: Data augmentation Exercise 4: Data augmentation in PyTorch

Current Exercise

Exercise 5: Convolutional Neural Networks Exercise 6: The convolutional layer Exercise 7: Building convolutional networks Exercise 8: Training image classifiers Exercise 9: Choosing augmentations Exercise 10: Dataset with augmentations Exercise 11: Image classifier training loop Exercise 12: Evaluating image classifiers Exercise 13: Multi-class model evaluation Exercise 14: Analyzing metrics per class

Build and train recurrent neural networks (RNNs) for processing sequential data such as time series, text, or audio. You will learn about the two most popular recurrent architectures, Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, as well as how to prepare sequential data for model training. You will practice your skills by training and evaluating a recurrent model for predicting electricity consumption.

Exercise 1: Handling sequences with PyTorch Exercise 2: Generating sequences Exercise 3: Sequential Dataset Exercise 4: Recurrent Neural Networks Exercise 5: Sequential architectures Exercise 6: Building a forecasting RNN Exercise 7: LSTM and GRU cells Exercise 8: RNN vs. LSTM vs. GRU Exercise 9: LSTM network Exercise 10: GRU network Exercise 11: Training and evaluating RNNs Exercise 12: RNN training loop Exercise 13: Evaluating forecasting models

Build multi-input and multi-output models, demonstrating how they can handle tasks requiring more than one input or generating multiple outputs. You will explore how to design and train these models using PyTorch and delve into the crucial topic of loss weighting in multi-output models. This involves understanding how to balance the importance of different tasks when training a model to perform multiple tasks simultaneously.

Exercise 1: Multi-input models Exercise 2: Two-input dataset Exercise 3: Two-input model Exercise 4: Training two-input model Exercise 5: Multi-output models Exercise 6: Two-output Dataset and DataLoader Exercise 7: Two-output model architecture Exercise 8: Training multi-output models Exercise 9: Evaluation of multi-output models and loss weighting Exercise 10: Multi-output model evaluation Exercise 11: Loss weighting Exercise 12: Wrap-up