Building Deep Learning Applications with Keras 2.0 (2017)
1h 24mIntermediate2017-08-01
Authors
Adam Geitgey
Developer and Machine Learning Consultant
Course details
Keras is a popular programming framework for deep learning that simplifies the process of building deep learning applications. Instead of providing all the functionality itself, it uses either TensorFlow or Theano behind the scenes and adds a standard, simplified programming interface on top. In this course, learn how to install Keras and use it to build a simple deep learning model. Explore the many powerful pre-trained deep learning models included in Keras and how to use them. Discover how to deploy Keras models, and how to transfer data between Keras and TensorFlow so that you can take advantage of all the TensorFlow tools while using Keras. When you wrap up this course, you'll be ready to start building and deploying your own models with Keras.
Topics include:
What's Keras?
Using Keras vs. TensorFlow
Training a deep learning model
Using a pre-trained deep learning model
Monitoring a Keras model with TensorBoard
Using a trained Keras model in Google Cloud
Topics include:
What's Keras?
Using Keras vs. TensorFlow
Training a deep learning model
Using a pre-trained deep learning model
Monitoring a Keras model with TensorBoard
Using a trained Keras model in Google Cloud
Skills covered
KerasTensorFlowNeural Networks and Deep LearningPythonGoogleArtificial Intelligence (AI)Open SourceOne-Off
Concepts
0. Introduction
- 01 - Welcome
- 02 - What you should know
- 03 - Using the exercise files
1. Keras Overview
- 04 - What is Keras
- 05 - TensorFlow and Theano backends
- 06 - Using Keras vs. TensorFlow
2. Setting Up Keras
- 07 - Installing Keras with the TensorFlow backend on macOS
- 08 - Installing Keras with the TensorFlow backend on Windows
3. Creating a Neural Network in Keras
- 09 - The train-test-evaluation flow
- 10 - Keras Sequential API
- 11 - Pre-processing training data
- 12 - Define a Keras model using the Sequential API
4. Training Models
- 13 - Training and evaluating the model
- 14 - Making predictions
- 15 - Saving and loading models
5. Pre-Trained Models in Keras
- 16 - Pre-trained models
- 17 - Recognize images with ResNet50 model
6. Monitoring a Keras model with TensorBoard
- 18 - Export Keras logs in TensorFlow format
- 19 - Visualize the computational graph
- 20 - Visualize training progress
7. Using a Trained Keras Model in Google Cloud
- 21 - Exporting Google Cloud-compatible models
- 22 - Configuring a new Google Cloud account
- 23 - Uploading a Keras model to Google Cloud
- 24 - Using a model in Google Cloud
Conclusion
- 25 - Next steps
Related courses
- Building Deep Learning Applications with Keras
- Recurrent Neural Networks
- Deep Learning and Generative AI: Data Prep, Analysis, and Visualization with Python
- Deep Learning with Python: Hands-On Introduction to Deep Learning Models
- Building and Deploying Deep Learning Applications with TensorFlow
- Building Computer Vision Applications with Python
- Deep Learning Fundamentals for Healthcare
- Deep Learning with Python: Convolutional Neural Networks
Related learn paths
- Advance Your Skills in Deep Learning and Neural Networks
- Fundamentals to Become a Machine Learning Engineer
- Advance Your Skills in Natural Language Processing
- Getting Started with AI and Machine Learning
- Explore AI for Data Engineering
- Moving from Data Scientist to Data Analyst
- Applying AI as a Tech Leader
- Advance Your Skills in AI and Machine Learning