Dropout (nn.Dropout) in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a dropout layer with 30% dropout rate.

PyTorch

dropout = nn.Dropout(p=[1])

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

A0.3

B3

C30

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using an integer like 30 instead of 0.3.

Setting dropout to 0 which means no dropout.

The dropout probability p is a float between 0 and 1 representing the fraction of neurons to drop. Here, 0.3 means 30% dropout.

2fill in blank

medium

Complete the code to apply dropout to the input tensor during training.

PyTorch

output = dropout([1])

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

Aoutput_tensor

Bmodel

Cinput_tensor

Dnn.Dropout

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the model or dropout class instead of the input tensor.

Passing the output tensor before dropout.

The dropout layer is applied to the input tensor to randomly zero some elements during training.

3fill in blank

hard

Fix the error in the code to ensure dropout is only applied during training mode.

PyTorch

dropout = nn.Dropout(p=0.5)
model.train()
if model.training:
    output = dropout([1])
else:
    output = [1]

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

Amodel

Binput_tensor

Cdropout

Doutput_tensor

Attempts:

3 left

💡 Hint

Common Mistakes

Using the model or dropout layer as input to dropout.

Using output tensor before dropout in the else branch.

Dropout should be applied to the input tensor only when the model is in training mode. Otherwise, the input tensor is passed unchanged.

4fill in blank

hard

Fill both blanks to create a dropout layer and apply it to the input tensor.

PyTorch

dropout = nn.Dropout(p=[1])
output = dropout([2])

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

A0.4

Binput_tensor

C0.1

Doutput_tensor

Attempts:

3 left

💡 Hint

Common Mistakes

Using output tensor instead of input tensor.

Using incorrect dropout probability values.

The dropout layer is created with 40% dropout rate and applied to the input tensor.

5fill in blank

hard

Fill all three blanks to define a dropout layer, apply it to input, and check training mode.

PyTorch

dropout = nn.Dropout(p=[1])
model.eval()
output = dropout([2]) if model.[3] else [2]

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

A0.2

Binput_tensor

Ctraining

Ddropout

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'dropout' instead of 'training' for model mode check.

Applying dropout when model is in eval mode.

The dropout layer is created with 20% dropout. The output applies dropout only if the model is in training mode, otherwise returns input unchanged.