Keras Tutorial For Beginners | Creating Deep Learning Models Using Keras In Python | Edureka
10 likes1,169 views
The document provides an overview of Keras, a high-level API for building neural networks that operates on top of TensorFlow, Theano, or CNTK. It outlines Keras's features, including its modularity, multi-backend compatibility, and focus on user experience, making it accessible for both beginners and advanced users. Additionally, it describes various model types, implementation steps for neural networks, and presents a practical use case involving predicting wine prices based on descriptions.
Keras Tutorial For Beginners | Creating Deep Learning Models Using Keras In Python | Edureka
- 1. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
- 2. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Agenda What is Keras? Contributors for Keras Keras Models Implementing a Neural Network Use-Case Summary
- 3. Copyright © 2017, edureka and/or its affiliates. All rights reserved. What Is Keras? Official high-level API of TensorFlow! Copyright © 2018, edureka and/or its affiliates. All rights reserved.
- 4. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow What Is Keras? Keras - Modular âą Building models is as simple as stacking layers and connecting graphs. Open Source âą Actively developed by contributors across the world! âą Good amount of documentation Deep Learning Library âą High-level Neural Network API âą Runs on top of TensorFlow, Theano or CNTK. High Performance âą High performing API used to specify and train differentiable programs.
- 5. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Who Makes Keras? Who are the contributors and backers? Copyright © 2018, edureka and/or its affiliates. All rights reserved.
- 6. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Who Makes Keras? 4800+ Contributors 250,000 Keras developers > 2x Year-on-year growth Start-ups Good amount of traction
- 7. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Who Uses Keras? Letâs check out the industry traction! Copyright © 2018, edureka and/or its affiliates. All rights reserved.
- 8. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Industry Traction And more..!
- 9. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow What Makes Keras Special? Highlights from one of the top Deep Learning libraries! Copyright © 2018, edureka and/or its affiliates. All rights reserved.
- 10. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow What Makes Keras Special? Large adoption in the industry Multi-backend, multi-platform Focus on user experience Research community4 Easy to grasp all concepts5 Fast prototyping6 Runs seamlessly on CPU and GPU7 Freedom to design any architecture8 Simple to get started9 Easy production of models10
- 11. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Keras User Experience API Designed for Humans âą Keras follows best practices for reducing cognitive load âą Offers consistent and simple APIs Not Designed for Machines âą Minimizes number of user actions required for common use cases âą Provides clear feedback upon user error Easy to Learn & Easy to Use âą More productive âą Try more ideas than your competition âą Helps you win competitions High Flexibility âą Keras integrates with lower-level Deep Learning languages like TensorFlow âą Implement anything which was built in base language. 1 3 2 4
- 12. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Multi-Backend & Multi-Platform 01 02 03 Development Develop in Python, R Run the code with: âą TensorFlow âą CNTK âą Theano âą MXNet âą CPU âą NVIDIA GPU âą AMD GPU âą TPU âą Etc.. Producing Models âą TF-Serving âą GPU acceleration (WebKeras, Keras.js) âą Android (TF, TF Lite) âą iOS (Native CoreML) âą Raspberry Pi {code} Run The Code
- 13. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Working Principle Of Keras Letâs take a quick look at the basics of Kerasâ backend Copyright © 2018, edureka and/or its affiliates. All rights reserved.
- 14. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Working Principle â Backend âą e = c*d where, âc = a+bâ and âd = b+1â âą So, e = (a+b)*(b+1) âą Here âaâ ,âbâ are inputs 01 02 03 04 Expressing complex expressions as a combination of simple operations Useful for calculating derivatives during backpropagation Easier to implement distributed computation Just specify the inputs, outputs and make sure the graph is connected Computational Graphs As easy as that!
- 15. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Keras Models There are 2 major models that Keras offers! Copyright © 2018, edureka and/or its affiliates. All rights reserved.
- 16. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Keras Models Sequential Model âą Linear stack of layers âą Useful for building simple models âą Simple classification network âą Encoder â Decoder models âą The model we all know and love! âą Treat each layer as object that feeds into the next.
- 17. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Keras Models Functional Model âą Like playing with Lego bricks âą Good for 95% of use cases Multi-input, multi-output and arbitrary static graph topologies Multi â input and Multi â output models Complex models which forks into 2 or more branches Models with shared (Weights) layers 01 02 03 04
- 18. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Keras Models Functional Model (Domain Adaption) âą Train on Domain A and Test on Domain B âą Results in poor performance on test set âą The data are from different domains We will be looking at a very interesting use case using the functional model in the upcoming slides Solution: Adapt the model to both the domains
- 19. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Understanding Execution There are 2 types of execution! Copyright © 2018, edureka and/or its affiliates. All rights reserved.
- 20. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Execution â Two Types Deferred (symbolic) âą We use Python to build a computation graph first âą The compiled graph then gets executed later Eager ( imperative) âą Here, the Python runtime is the execution runtime âą It is similar to execution with Numpy âą Symbolic tensors donât have a value in the Python code (yet) âą Eager tensors have a value in the Python code âą With eager execution, value-dependent dynamic topologies (tree-RNNs) can be used. On the whole
- 21. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Implementing a Neural Network There are 5 major steps to implement our own Neural Network with Keras! Copyright © 2018, edureka and/or its affiliates. All rights reserved.
- 22. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Implementing A Neural Network 1. Prepare Input âą Preparing the input and specify the input dimension (size) âą Images, videos, text and audio 2. Define the ANN Model âą Define the model architecture and build the computational graph âą Sequential or Functional Style âą MLP, CNN, RNN 3. Optimizers âą Specify the optimizer and configure the learning process âą SGD, RMSprop, Adam 5. Train and Evaluate Model âą Train the model based on the training data âą Test the model on the dataset with the testing data 4. Loss Function âą Specify the Inputs, Outputs of the computational graph (model) and the Loss function âą MSE, Cross Entropy, Hinge
- 23. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Use-Case With Keras Letâs check out an interesting Wine Classifier use-case! Copyright © 2018, edureka and/or its affiliates. All rights reserved.
- 24. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Use Case â Problem Statement âPredicting the price of wine with the Keras Functional API and TensorFlowâ Building a wide and deep network using Keras (tf.Keras) to predict the price of wine from its description Predict the price of a bottle of wine just from its description and variety? âą This problem is well suited for wide & deep learning âą It involves text input and there isnât any correlation between a wineâs description and its price
- 25. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Use Case â Model A good use-case for the Functional API is implementing a wide and deep network in Keras! A lot of Keras models are built using the Sequential model API BUT Letâs try to solve our use-case with the Functional API The Sequential API is the best way to get started with Keras Because it lets you easily define models as a stack of layers The Functional API allows for more flexibility and is best suited for models with multiple inputs or combined models Wide models are models with sparse feature vectors or vectors with mostly zero values Multi-layer deep networks do well on tasks like image or speech recognition
- 26. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Use Case â Dataset DATASET Country1 2 Description 3 Designation 4 Points 5 Price 6 Region_1 Region_27 8 Taster Name 9 Taster Twitter Handle 10 Title Variety11 Winery12 The overall goal is to create a model that can identify the variety, winery and location of a wine based on a description This dataset offers some great opportunities for sentiment analysis and other text related predictive models
- 27. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Use Case â Sample Description: âą Powerful vanilla scents rise from the glass, but the fruit, even in this difficult vintage, comes out immediately. âą Itâs tart and sharp, with a strong herbal component, and the wine snaps into focus quickly with fruit, acid, tannin, herb and vanilla in equal proportion. âą Firm and tight, still quite young, this wine needs decanting and/or further bottle age to show its best. Variety: Pinot Noir Prediction: Priceâââ$45
- 28. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Use Case â Prerequisites
- 29. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Use Case â Prerequisites Here are all the imports weâll need to build this model! Test presence of TensorFlow by printing the version Download the data and convert it to a Pandas Data Frame
- 30. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Use Case â Letâs See Code! Google Colaboratory
- 31. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Session In A Minute What is Keras? Contributors Specialty of Keras Implementing a Neural Network Use-Case ImplementationKeras Models
- 32. Copyright © 2018, edureka and/or its affiliates. All rights reserved.