Introduction to TensorFlow and Keras

Duration: 5 min

This module provides an introduction to TensorFlow and Keras, two powerful libraries for building and deploying machine learning models. You will learn the basics of setting up a TensorFlow environment, creating simple neural networks using Keras, and understanding the fundamental concepts that underpin these technologies. This knowledge is crucial for anyone looking to delve into deep learning and apply it to real-world problems.

Understanding TensorFlow

TensorFlow is an open-source machine learning framework developed by Google. It allows developers to build and train machine learning models, particularly deep learning models, with high-level APIs. TensorFlow provides a flexible ecosystem of tools, libraries, and community resources that lets researchers push the state-of-the-art in machine learning and developers easily build and deploy machine learning-powered applications.

import tensorflow as tf

# Create a simple constant tensor
hello = tf.constant('Hello, TensorFlow!')

# Start a TensorFlow session
sess = tf.Session()

# Run the operation and print the result
print(sess.run(hello))

Try it in Google Colab:

b'Hello, TensorFlow!'

Introduction to Keras

Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research. Keras allows you to quickly build and evaluate neural network architectures.

from keras.models import Sequential
from keras.layers import Dense

# Create a simple Keras Sequential model
model = Sequential()

# Add an input layer 
model.add(Dense(10, activation='relu', input_shape=(4,)))

# Add one hidden layer
model.add(Dense(8, activation='relu'))

# Add an output layer 
model.add(Dense(1))

# Compile the model
model.compile(optimizer='adam', loss='mean_squared_error')

💡 Tip: When defining your model in Keras, always ensure that the input_shape parameter in the first layer matches the shape of your input data to avoid dimension mismatch errors.