Sequential model shortcut in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a simple sequential model with one linear layer.

PyTorch

import torch.nn as nn
model = nn.Sequential(nn.Linear(10, [1]))

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

A5

B10

C15

D20

Attempts:

3 left

💡 Hint

Common Mistakes

Using the input size instead of output size for the second argument.

Confusing input and output dimensions.

The linear layer output size is set to 5, which matches the intended model design.

2fill in blank

medium

Complete the code to add a ReLU activation after the linear layer in the sequential model.

PyTorch

import torch.nn as nn
model = nn.Sequential(
    nn.Linear(10, 5),
    [1]()
)

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

ASigmoid

BTanh

CSoftmax

DReLU

Attempts:

3 left

💡 Hint

Common Mistakes

Using Sigmoid or Softmax which are less common for hidden layers.

Forgetting to add parentheses after the activation class.

ReLU is a common activation function used after linear layers to add non-linearity.

3fill in blank

hard

Fix the error in the code to correctly create a sequential model with two layers.

PyTorch

import torch.nn as nn
model = nn.Sequential(
    nn.Linear(10, 5),
    nn.ReLU(),
    [1](5, 2)
)

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

AConv2d

BDropout

CLinear

DBatchNorm1d

Attempts:

3 left

💡 Hint

Common Mistakes

Using Conv2d which expects image data.

Using BatchNorm1d or Dropout incorrectly as a layer with input/output sizes.

The second linear layer should be nn.Linear to connect 5 inputs to 2 outputs.

4fill in blank

hard

Fill both blanks to create a sequential model with two linear layers and a ReLU activation in between.

PyTorch

import torch.nn as nn
model = nn.Sequential(
    nn.[1](10, 8),
    nn.[2](),
    nn.Linear(8, 3)
)

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

ALinear

BReLU

CSigmoid

DDropout

Attempts:

3 left

💡 Hint

Common Mistakes

Using Sigmoid instead of ReLU for activation.

Using Dropout instead of activation.

The first blank is 'Linear' to create the first layer, the second blank is 'ReLU' for activation.

5fill in blank

hard

Fill all three blanks to build a sequential model with two linear layers, a ReLU activation, and a dropout layer.

PyTorch

import torch.nn as nn
model = nn.Sequential(
    nn.[1](12, 10),
    nn.[2](),
    nn.[3](p=0.3),
    nn.Linear(10, 4)
)

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

ALinear

BReLU

CDropout

DBatchNorm1d

Attempts:

3 left

💡 Hint

Common Mistakes

Using BatchNorm1d instead of Dropout for regularization.

Forgetting to add parentheses after the class names.

The model has a Linear layer, followed by ReLU activation, then Dropout with 0.3 probability.