Model parameters inspection in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of model parameter count code

What is the output of the following PyTorch code that counts the total number of parameters in a simple linear model?

PyTorch

import torch
import torch.nn as nn

model = nn.Linear(3, 2)

param_count = sum(p.numel() for p in model.parameters())
print(param_count)

A 9

B 6

C 5

D 8

💡 Hint

Remember that nn.Linear has weights and biases. Weights shape is (out_features, in_features).

The linear layer has weights of shape (2,3) = 6 parameters and biases of shape (2,) = 2 parameters, total 8.

🧠 Conceptual

intermediate

Understanding requires_grad attribute

Which statement correctly describes the effect of setting requires_grad=False on a model parameter in PyTorch?

A The parameter will not be updated during training because gradients are not computed for it.

B The parameter will be updated normally but gradients will be zero.

C The parameter will cause an error during backpropagation.

D The parameter will be frozen but still receive gradient updates.

💡 Hint

Think about what happens when gradients are not computed for a parameter.

If requires_grad=False, PyTorch does not compute gradients for that parameter, so optimizer does not update it.

❓ Metrics

advanced

Inspecting model parameter shapes

Given the following PyTorch model, what is the shape of the parameter named 'fc2.weight'?

PyTorch

import torch.nn as nn

class SimpleNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(10, 5)
        self.fc2 = nn.Linear(5, 2)

model = SimpleNN()
print(model.fc2.weight.shape)

A torch.Size([5, 2])

B torch.Size([2, 5])

C torch.Size([10, 5])

D torch.Size([5, 10])

💡 Hint

Recall that nn.Linear weight shape is (out_features, in_features).

fc2 is Linear(5, 2), so weight shape is (2, 5).

🔧 Debug

advanced

Identifying error when accessing model parameters

What error will the following code raise when trying to access a non-existent parameter 'fc3.weight' in a PyTorch model?

PyTorch

import torch.nn as nn

model = nn.Sequential(
    nn.Linear(4, 3),
    nn.ReLU(),
    nn.Linear(3, 2)
)

param = dict(model.named_parameters())['fc3.weight']

A KeyError

B AttributeError

C TypeError

D IndexError

💡 Hint

Check what keys are in the named_parameters dictionary.

The model has no parameter named 'fc3.weight', so accessing it raises KeyError.

❓ Model Choice

expert

Choosing model to inspect parameters for convolutional layers

You want to inspect the parameters of a convolutional neural network with two Conv2d layers. Which model definition will allow you to correctly access the weight tensor of the second convolutional layer as 'conv2.weight'?

A

class CNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = nn.Conv2d(1, 16, 3)
        self.layer2 = nn.Conv2d(16, 32, 3)

model = CNN()

B

model = nn.Sequential(
    nn.Conv2d(1, 16, 3),
    nn.Conv2d(16, 32, 3)
)

# Access conv2.weight

C

class CNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 16, 3)
        self.conv2 = nn.Conv2d(16, 32, 3)

model = CNN()

D

model = nn.ModuleList([
    nn.Conv2d(1, 16, 3),
    nn.Conv2d(16, 32, 3)
])

# Access conv2.weight

💡 Hint

Only named attributes can be accessed by their names directly.

Only in option C the second conv layer is named 'conv2', so model.conv2.weight works.