Linear (fully connected) layers in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a linear layer with 10 inputs and 5 outputs.

PyTorch

import torch.nn as nn

layer = nn.Linear([1], 5)

Drag options to blanks, or click blank then click option'

A10

B15

C5

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using the output size as the input size.

Confusing input and output sizes.

The first argument to nn.Linear is the number of input features. Here, it should be 10.

2fill in blank

medium

Complete the code to pass input data through the linear layer.

PyTorch

import torch
import torch.nn as nn

layer = nn.Linear(4, 2)
input_data = torch.randn(1, 4)
output = layer([1])

Drag options to blanks, or click blank then click option'

Atorch.tensor([1, 2, 3, 4])

Blayer

Ctorch.randn(1, 2)

Dinput_data

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the layer itself instead of the input data.

Passing a tensor with wrong shape.

To get the output, we pass the input data to the layer as a function call.

3fill in blank

hard

Fix the error in the code to correctly create a linear layer with 3 inputs and 1 output.

PyTorch

import torch.nn as nn

layer = nn.Linear([1], 1)

Drag options to blanks, or click blank then click option'

A1

B3

C4

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using output size as input size.

Using zero or invalid sizes.

The input size must match the number of input features, which is 3 here.

4fill in blank

hard

Fill both blanks to create a linear layer and pass a tensor through it.

PyTorch

import torch
import torch.nn as nn

layer = nn.Linear([1], [2])
input_tensor = torch.randn(2, 3)
output = layer(input_tensor)

Drag options to blanks, or click blank then click option'

A3

B2

C1

D4

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping input and output sizes.

Confusing batch size with input features.

The input tensor has shape (2, 3), so input features = 3 and batch size = 2. The layer output size is 2.

5fill in blank

hard

Fill all three blanks to create a linear layer, pass input, and get output shape.

PyTorch

import torch
import torch.nn as nn

layer = nn.Linear([1], [2])
input_tensor = torch.randn(4, [3])
output = layer(input_tensor)
output_shape = output.shape

Drag options to blanks, or click blank then click option'

A5

B3

C7

D4

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up input and output sizes.

Using wrong tensor shapes.

The input tensor has shape (4, 3), so input features = 3. The layer outputs 7 features. The input tensor's last dimension is 3.