PyTorch ecosystem overview - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding PyTorch's Core Components

Which of the following is NOT a core component of the PyTorch ecosystem?

A NumPy for tensor operations within PyTorch

B TensorBoard for visualization and debugging

C TorchScript for model serialization and optimization

D TorchVision for computer vision datasets and models

💡 Hint

Think about which library is external and not part of PyTorch itself.

NumPy is a separate library for numerical computing in Python. While PyTorch tensors can interoperate with NumPy arrays, NumPy is not a core component of the PyTorch ecosystem.

❓ Predict Output

intermediate

Output of PyTorch Model Training Loop

What will be the printed output after running this PyTorch training loop snippet?

PyTorch

import torch
import torch.nn as nn

model = nn.Linear(2, 1)
criterion = nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

inputs = torch.tensor([[1.0, 2.0]])
targets = torch.tensor([[1.0]])

optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, targets)
loss.backward()
optimizer.step()

print(round(loss.item(), 4))

A 0.75

B 0.5

C 0.25

D 0.0

💡 Hint

The loss is the mean squared error between model output and target before the optimizer step.

The initial weights are random, so the output will not match the target exactly. The MSE loss will be a positive value around 0.5 for this simple input and target.

❓ Model Choice

advanced

Choosing the Right PyTorch Ecosystem Library

You want to train a natural language processing model using pre-built datasets and tokenizers. Which PyTorch ecosystem library should you use?

A TorchServe

B TorchAudio

C TorchText

D TorchVision

💡 Hint

Think about which library focuses on text data.

TorchText provides tools for text processing, datasets, and tokenization for NLP tasks within the PyTorch ecosystem.

❓ Hyperparameter

advanced

Effect of Learning Rate in PyTorch Optimizer

If you increase the learning rate in a PyTorch optimizer too much, what is the most likely effect on training?

A Training will always reach a better minimum

B Training will ignore the learning rate and behave the same

C Training will converge faster and more smoothly

D Training may become unstable and loss may oscillate or diverge

💡 Hint

Think about what happens if steps are too large when trying to find a minimum.

A very high learning rate can cause the model to overshoot minima, causing unstable training and possibly divergence.

❓ Metrics

expert

Calculating Accuracy from PyTorch Model Outputs

Given a batch of model outputs as logits and true labels, which code snippet correctly computes the classification accuracy in PyTorch?

PyTorch

outputs = torch.tensor([[2.0, 1.0, 0.1], [0.5, 2.5, 0.3], [1.2, 0.7, 2.1]])
labels = torch.tensor([0, 1, 2])

A

preds = outputs.argmax(dim=1)
accuracy = (preds == labels).float().mean().item()

B

preds = outputs.max(dim=0)[1]
accuracy = (preds == labels).float().mean().item()

C

preds = outputs.argmax(dim=1)
accuracy = (preds == labels).sum().item()

D

preds = outputs.max(dim=1)[0]
accuracy = (preds == labels).float().mean().item()

💡 Hint

Check how to get predicted class indices and how to compute mean accuracy.

Using argmax over dimension 1 gives predicted class indices per sample. Comparing with labels and taking the mean of correct predictions gives accuracy.

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