Keras and TensorFlow

In the past, we’ve worked with datasets that have been pre-compiled and labeled for us — but what if we wanted to go about creating our own custom dataset and then training a CNN on it? In this tutorial, I’ll…

In this tutorial, we will be building a complete end-to-end application that can detect smiles in a video stream in real-time using deep learning along with traditional computer vision techniques. To accomplish this task, we’ll be training the LetNet architecture…

In this tutorial, you will learn two methods to incorporate data augmentation into your tf.data pipeline using Keras and TensorFlow. This tutorial is part in our three part series on the tf.data module: A gentle introduction to tf.data Data pipelines…

In this tutorial, you will learn how to implement fast, efficient data pipelines for training neural networks using tf.data and TensorFlow. This tutorial is part two in our three part series on the tf.data module: A gentle introduction to tf.data…

In this tutorial, you will learn the basics of TensorFlow’s tf.data module used to build faster, more efficient deep learning data pipelines. This blog post is part one in our three part series on tf.data: A gentle introduction to tf.data…

In this tutorial, you will learn how to use the Keras Tuner package for easy hyperparameter tuning with Keras and TensorFlow. This tutorial is part four in our four-part series on hyperparameter tuning: Introduction to hyperparameter tuning with scikit-learn and…

In this tutorial, you will learn how to tune the hyperparameters of a deep neural network using scikit-learn, Keras, and TensorFlow. This tutorial is part three in our four-part series on hyperparameter tuning: Introduction to hyperparameter tuning with scikit-learn and…

Now that we’ve trained our model and serialized it, we need to load it from disk. As a practical application of model serialization, I’ll be demonstrating how to classify individual images from the Animals dataset and then display the classified…

The LeNet architecture is a seminal work in the deep learning community, first introduced by LeCun et al. in their 1998 paper, Gradient-Based Learning Applied to Document Recognition. As the name of the paper suggests, the authors’ motivation behind implementing…