PyTorch and object-oriented programming

Intermediate Deep Learning with PyTorch

Michal Oleszak

Machine Learning Engineer

What we will learn

How to train robust deep learning models:

Improving training with optimizers
Mitigating vanishing and exploding gradients
Convolutional Neural Networks (CNNs)
Recurrent Neural Networks (RNNs)
Multi-input and multi-output models

PyTorch logo

Prerequisites

The course assumes you are comfortable with the following topics:

Neural networks training:
- Forward pass
- Loss calculation
- Backward pass (backpropagation)
Training models with PyTorch:
- Datasets and DataLoaders
- Model training loop
- Model evaluation
Prerequisite course: Introduction to Deep Learning with PyTorch

Object-Oriented Programming (OOP)

We will use OOP to define:
- PyTorch Datasets
- PyTorch Models
In OOP, we create objects with:
- Abilities (methods)
- Data (attributes)

Object-Oriented Programming (OOP)

class BankAccount:
    def __init__(self, balance):
        self.balance = balance

__init__ is called when BankAccount object is created
balance is the attribute of the BankAccount object

account = BankAccount(100)
print(account.balance)

Object-Oriented Programming (OOP)

Methods: Python functions to perform tasks
deposit method increases balance

class BankAccount:
    def __init__(self, balance):
        self.balance = balance


    def deposit(self, amount):
        self.balance += amount

account = BankAccount(100)
account.deposit(50)
print(account.balance)

Water potability dataset

Pandas DataFrame showing a couple of first and last rows of the water potability data.

PyTorch Dataset

from torch.utils.data import Dataset

class WaterDataset(Dataset):

    def __init__(self, csv_path):
        super().__init__()
        df = pd.read_csv(csv_path)
        self.data = df.to_numpy()


    def __len__(self):
        return self.data.shape[0]


    def __getitem__(self, idx):
        features = self.data[idx, :-1]
        label = self.data[idx, -1]
        return features, label

init: load data, store as numpy array
- super().__init__() ensures WaterDataset behaves like torch Dataset
len: return the size of the dataset
getitem:
- take one argument called idx
- return features and label for a single sample at index idx

PyTorch DataLoader

dataset_train = WaterDataset(
    "water_train.csv"
)

from torch.utils.data import DataLoader

dataloader_train = DataLoader(
    dataset_train,
    batch_size=2,
    shuffle=True,
)

features, labels = next(iter(dataloader_train))
print(f"Features: {features},\nLabels: {labels}")

Features: tensor([
  [0.4899, 0.4180, 0.6299, 0.3496, 0.4575,
   0.3615, 0.3259, 0.5011, 0.7545],
  [0.7953, 0.6305, 0.4480, 0.6549, 0.7813,
   0.6566, 0.6340, 0.5493, 0.5789]
]),
Labels: tensor([1., 0.])

PyTorch Model

Sequential model definition:

net = nn.Sequential(
  nn.Linear(9, 16),
  nn.ReLU(),
  nn.Linear(16, 8),
  nn.ReLU(),
  nn.Linear(8, 1),
  nn.Sigmoid(),
)

Class-based model definition:

class Net(nn.Module):

    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(9, 16)
        self.fc2 = nn.Linear(16, 8)
        self.fc3 = nn.Linear(8, 1)


    def forward(self, x):
        x = nn.functional.relu(self.fc1(x))
        x = nn.functional.relu(self.fc2(x))
        x = nn.functional.sigmoid(self.fc3(x))
        return x

net = Net()

Let's practice!

Intermediate Deep Learning with PyTorch