TensorFlow | Overview

TensorFlow is an end-to-end open source platform for machine learning. TensorFlow makes it easy for beginners and experts to create machine learning models. It supports the following:

• Multidimensional-array based numeric computation
• GPU and distributed processing
• Automatic differentiation
• Model construction, training, and export Tensor

TensorFlow Libraries and extensions

Let's have a look to some of the TensorFlow libraries and extensions to build advanced models or methods using TensorFlow.

TensorBoard: TensorBoard is TensorFlow's visualization toolkit. It provides the visualization and tooling needed for machine learning experimentation. Some of the features offered by TensorBoard are listed below.

• Visualizing the model graph
• Tracking and visualizing metrics such as loss and accuracy
• Projecting embeddings to a lower dimensional space
• Displaying images, text, and audio data

TensorFlow Hub: TensorFlow Hub is a repository of trained machine learning models. The tensorflow_hub library lets you download and reuse them in your TensorFlow program with a minimum amount of code.

TensorFlow Datasets: TensorFlow Datasets is a collection of datasets ready to use, with TensorFlow or other Python ML frameworks. All datasets are exposed as tf.data.Datasets , enabling easy-to-use and high-performance input pipeline.

TensorFlow Serving: TensorFlow Serving is a flexible, high-performance serving system for machine learning models, designed for production environments.

TensorFlow Model Optimization: TensorFlow Model Optimization Toolkit is a suite of tools for optimizing ML models for deployment and execution.

TensorFlow Federated: TensorFlow Federated (TFF) is an open-source framework for machine learning and other computations on decentralized data.

TensorFlow Probability: TensorFlow Probability is a Python library built on TensorFlow that makes it easy to combine probabilistic models and deep learning on modern hardware. It's for data scientists, statisticians, ML researchers, and practitioners who want to encode domain knowledge to understand data and make predictions.