Keras is a high-level neural networks APIs that provide easy and efficient design and training of deep learning models. It is built on top of TensorFlow, making it both highly flexible and accessible. Keras has a simple and user-friendly interface, making it ideal for both beginners and experts in deep learning.
Installing
This section will guide you through installation steps on various operating systems.
Basics
Keras is a high-level neural networks API designed to simplify the process of building and training deep learning models.
- Introduction
- Keras vs Tensorflow vs Pytorch
- Keras with Scikit-Learn
- Datasets
- How to create Models
- Sequential and Functional API
- Keras Layers
- Input Layer
- Convolution Layer
Training the Model
Training a model in Keras involves preparing your data, defining a model and specifying the number of epochs.
- Epochs to Train a Neural Network
- Create a Custom Loss Function
- Log Keras Loss Output
- Saving a Deep Learning model
Neural Network
Building a neural network in Keras involves selecting appropriate layers, defining activation functions and tuning the model’s hyperparameters.
- Neural Style Transfer
- Neural Network
- Auto-Encoder
- Deep Convolutional GAN
- Colorization Autoencoders
- Swish Function
- Generative Adversarial Network
- Auxiliary GAN
- Time Series Forecasting with LSTMs
- Image Processing
Evaluating the Model
Evaluating a model in Keras involves testing its performance using unseen data.
- Model evaluate and Predict
- Loss Function and Metric
- Hyperparameter tuning
- Transfer learning and fine-tuning
- Dropout
R Language
Keras can be used with R to build deep learning models using keras package.
- Install Package Keras
- Introduction
- Convert TensorFlow Tensor to R Array
- Neural Network Classifier
- Train and Test Neural Networks
- Image Classification
- Class weight in Keras Package
- Custom Loss Function
- Early stopping
- Optimizing for Accuracy
Projects
Explore hands-on Keras projects like:
