PyTorch ecosystem overview - ML Experiment: Train & Evaluate

Experiment - PyTorch ecosystem overview

Problem:You want to understand the PyTorch ecosystem and how its components work together to build and train machine learning models.

Current Metrics:No model or code yet; just conceptual understanding.

Issue:Lack of practical experience with PyTorch components like tensors, datasets, dataloaders, models, optimizers, and training loops.

Your Task

Build a simple PyTorch model using core ecosystem components and observe training metrics to understand their roles.

Use PyTorch tensors, Dataset, DataLoader, nn.Module, optimizer, and training loop.

Keep the model simple (e.g., linear regression).

Print training loss for each epoch.

Hint 1

Hint 2

Hint 3

Hint 4

Hint 5

Solution

PyTorch

import torch
from torch.utils.data import Dataset, DataLoader
import torch.nn as nn
import torch.optim as optim

# Create a simple dataset
class SimpleDataset(Dataset):
    def __init__(self):
        # Features: x values from 0 to 9
        self.x = torch.arange(10, dtype=torch.float32).unsqueeze(1)
        # Targets: y = 2*x + 1
        self.y = 2 * self.x + 1
    def __len__(self):
        return len(self.x)
    def __getitem__(self, idx):
        return self.x[idx], self.y[idx]

# Define a simple linear model
class LinearModel(nn.Module):
    def __init__(self):
        super(LinearModel, self).__init__()
        self.linear = nn.Linear(1, 1)
    def forward(self, x):
        return self.linear(x)

# Prepare dataset and dataloader
dataset = SimpleDataset()
dataloader = DataLoader(dataset, batch_size=2, shuffle=True)

# Initialize model, loss function, and optimizer
model = LinearModel()
criterion = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)

# Training loop
for epoch in range(10):
    total_loss = 0
    for inputs, targets in dataloader:
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()
        total_loss += loss.item() * inputs.size(0)
    avg_loss = total_loss / len(dataset)
    print(f"Epoch {epoch+1}: Loss = {avg_loss:.4f}")

Created a custom Dataset to hold simple linear data.

Used DataLoader to batch and shuffle data.

Defined a linear model subclassing nn.Module.

Used MSELoss as the loss function.

Used SGD optimizer with learning rate 0.01.

Implemented a training loop printing average loss per epoch.

Fixed super() call in LinearModel to use super(LinearModel, self).__init__() for compatibility.

Results Interpretation

Before: No model or training, no metrics.

After: Model trains successfully with loss decreasing each epoch, showing PyTorch components working together.

This experiment shows how PyTorch ecosystem parts like Dataset, DataLoader, nn.Module, optimizer, and training loop combine to build and train a model.

Bonus Experiment

Try replacing the SGD optimizer with Adam optimizer and observe the training loss changes.

💡 Hint

Use torch.optim.Adam with a learning rate of 0.01 and compare loss decrease speed.

Practice

1. Which of the following is NOT part of the PyTorch ecosystem?

easy

A. torchvision

B. torchaudio

C. torchtext

D. tensorflow

Solution

1. Step 1: Identify PyTorch ecosystem libraries

   PyTorch ecosystem includes torchvision (images), torchtext (text), and torchaudio (audio).

2. Step 2: Recognize the unrelated library

   TensorFlow is a separate deep learning framework, not part of PyTorch ecosystem.

3. Final Answer:

   tensorflow -> Option D

4. Quick Check:

   PyTorch ecosystem excludes tensorflow [OK]

Hint: Remember PyTorch ecosystem libraries start with 'torch' prefix [OK]

Common Mistakes:

• Confusing TensorFlow as part of PyTorch
• Thinking torchvision is unrelated
• Mixing up torchtext with TensorFlow text tools

2. Which code snippet correctly imports the torchvision library in PyTorch?

easy

A. import torchvision

B. from torch import vision

C. import torch.vision

D. from torchvision import torch

Solution

1. Step 1: Recall correct import syntax for torchvision

   The correct way is to import torchvision directly using 'import torchvision'.

2. Step 2: Identify incorrect syntax

   Options A, B, and C use invalid module names or wrong import structure.

3. Final Answer:

   import torchvision -> Option A

4. Quick Check:

   Correct import is 'import torchvision' [OK]

Hint: Use 'import torchvision' to access image tools [OK]

Common Mistakes:

• Using 'from torch import vision' instead of torchvision
• Trying 'import torch.vision' which is invalid
• Confusing import order or names

3. What will the following code print?

import torch
import torchvision.models as models
model = models.resnet18(pretrained=True)
print(type(model))

medium

A. <class 'torchvision.models.resnet.ResNet'>

B. <class 'torch.nn.Module'>

C. <class 'torchvision.models.ResNet18'>

D. Error: pretrained argument not supported

Solution

1. Step 1: Understand model creation with pretrained=True

   models.resnet18(pretrained=True) loads a ResNet18 model with pretrained weights, returning a torch.nn.Module subclass instance.

2. Step 2: Check the type printed

   The type of model is torchvision.models.resnet.ResNet, so printing type(model) shows <class 'torchvision.models.resnet.ResNet'>.

3. Final Answer:

   <class 'torchvision.models.resnet.ResNet'> -> Option A

4. Quick Check:

   Pretrained ResNet models are of type ResNet [OK]

Hint: Pretrained models are always torch.nn.Module objects [OK]

Common Mistakes:

• Expecting base class 'torch.nn.Module' to print
• Thinking pretrained=True causes error
• Confusing model type with string output

4. Identify the error in this PyTorch code snippet:

import torch
from torchvision import datasets
train_data = datasets.MNIST(root='./data', train=True, download=True)
train_loader = torch.utils.data.DataLoader(train_data, batch_size=32, shuffle=True)
for images, labels in train_loader:
    print(images.shape, labels.shape)

medium

A. No error, code runs correctly

B. DataLoader batch_size must be 1

C. Missing transform argument in MNIST dataset

D. shuffle=True is invalid in DataLoader

Solution

1. Step 1: Check MNIST dataset usage

   MNIST without transform returns PIL Images; DataLoader collates them into a list.

2. Step 2: Validate print statement

   print(images.shape) fails because list of PIL Images has no .shape attribute. Need transforms.ToTensor() for tensor images with shape.

3. Final Answer:

   Missing transform argument in MNIST dataset -> Option C

4. Quick Check:

   MNIST needs transform for tensor shapes [OK]

Hint: MNIST dataset needs transform for tensor shapes in batches [OK]

Common Mistakes:

• Assuming transform is optional for shape access
• Thinking batch_size must be 1
• Believing shuffle=True causes error

5. You want to build a speech recognition model using PyTorch. Which ecosystem library should you use to handle audio data and pretrained audio models?

hard

A. torchtext

B. torchaudio

C. torchvision

D. torchvideo

Solution

1. Step 1: Identify the data type for speech recognition

   Speech recognition uses audio data, so the library must support audio processing.

2. Step 2: Match the correct PyTorch ecosystem library

   torchaudio is the PyTorch library designed for audio data and pretrained audio models.

3. Final Answer:

   torchaudio -> Option B

4. Quick Check:

   Audio data uses torchaudio library [OK]

Hint: Audio tasks use torchaudio in PyTorch ecosystem [OK]

Common Mistakes:

• Choosing torchvision for audio data
• Confusing torchtext with audio processing
• Assuming torchvideo exists in PyTorch ecosystem