PyTorch vs TensorFlow comparison - Interactive Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import PyTorch library.

PyTorch

import [1]

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

Atorch

Btensorflow

Ckeras

Dsklearn

Attempts:

3 left

💡 Hint

Common Mistakes

Importing tensorflow instead of torch

Using keras or sklearn which are different libraries

PyTorch is imported using the name torch.

2fill in blank

medium

Complete the code to create a tensor with PyTorch.

PyTorch

x = torch.[1]([1, 2, 3])

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

Atensor

Barray

Cmatrix

Dvariable

Attempts:

3 left

💡 Hint

Common Mistakes

Using torch.array which does not exist

Using torch.variable which is deprecated

PyTorch creates tensors using torch.tensor().

3fill in blank

hard

Fix the error in the TensorFlow code to create a constant tensor.

PyTorch

import tensorflow as tf
x = tf.[1]([1, 2, 3])

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

Aarray

Btensor

Cvariable

Dconstant

Attempts:

3 left

💡 Hint

Common Mistakes

Using tf.variable instead of tf.constant

Using tf.tensor which does not exist

TensorFlow creates constant tensors using tf.constant().

4fill in blank

hard

Fill both blanks to create a simple neural network layer in PyTorch.

PyTorch

layer = torch.nn.[1](in_features=10, [2]=5)

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

ALinear

Bout_features

CConv2d

Din_channels

Attempts:

3 left

💡 Hint

Common Mistakes

Using Conv2d which is for convolutional layers

Using in_channels which is not a parameter for Linear

PyTorch's fully connected layer is Linear with in_features and out_features.

5fill in blank

hard

Fill all three blanks to define a TensorFlow model with one dense layer.

PyTorch

import tensorflow as tf
model = tf.keras.Sequential([
    tf.keras.layers.[1](units=[2], activation=[3])
])

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

ADense

B10

C'relu'

DConv2D

Attempts:

3 left

💡 Hint

Common Mistakes

Using Conv2D which is for convolutional layers

Passing activation without quotes

TensorFlow's dense layer is Dense with units and activation parameters.