General Overview of TensorFlow

TensorFlow is an open source framework from Google for scientific and numerical computation based on dataflow graphs that stand for the TensorFlow's execution model. The dataflow graphs used in TensorFlow help the machine learning experts to perform more advanced and intensive training on the data for developing deep learning and predictive analytics models. In 2015, Google open sourced the TensorFlow and all of its reference implementation and made all the source code available on GitHub under the Apache 2.0 license. Since then, TensorFlow has achieved wide adoption from academia and research to the industry, and following that recently the most stable version 1.x has been released with a unified API.

As the name TensorFlow implies, operations are performed by neural networks on multidimensional data arrays (aka flow of tensors). This way, TensorFlow provides some widely used and robust implementation linear models and deep learning algorithms.

Deploying a predictive or general purpose model using TensorFlow is pretty straightforward. The thing is that once you have constructed your neural networks model after necessary feature engineering, you can simply perform the training interactively using plotting or TensorBoard (we will see more on it in upcoming sections). Finally, you deploy it eventually after evaluating it by feeding it some test data.

Since we are talking about the dataflow graphs, nodes in a flow graph correspond to the mathematical operations, such as addition, multiplication, matrix factorization, and so on, whereas, edges correspond to tensors that ensure communication between edges and nodes, that is dataflow and controlflow.

You can perform the numerical computation on a CPU. Nevertheless, using TensorFlow, it is also possible to distribute the training across multiple devices on the same system and train on them, especially if you have more than one GPU on your system so that these can share the computational load. But the precondition is if TensorFlow can access these devices, it will automatically distribute the computations to the multiple devices via a greedy process. But TensorFlow also allows the program, to specify which operations will be on which devices via name scope placement.

The APIs in TensorFlow 1.x have changed in ways that are not all backward compatible. That is, TensorFlow programs that worked on TensorFlow 0.x won't necessarily work on TensorFlow 1.x.

The main features offered by the latest release of TensorFlow are:

• Faster computing: The latest release of TensorFlow is incredibly faster. For example, it is 7.3 times faster on 8 GPUs for Inception v3 and 58 times speedup for distributed inception (v3 training on 64 GPUs).
• Flexibility: TensorFlow is not just a deep learning library, but it comes with almost everything you need for powerful mathematical operations through functions for solving the most difficult problems. TensorFlow 1.x introduces some high-level APIs for high-dimensional arrays or tensors, with tf.layers, tf.metrics, tf.losses, and tf.keras modules. These have made TensorFlow very suitable for high-level neural networks computing.
• Portability: TensorFlow runs on Windows, Linux, and Mac machines and on mobile computing platforms (that is, Android).
• Easy debugging: TensorFlow provides the TensorBoard tool for the analysis of the developed models.
• Unified API: TensorFlow offers you a very flexible architecture that enables you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.
• Transparent use of GPU computing: Automating management and optimization of the same memory and the data used. You can now use your machine for large-scale and data-intensive GPU computing with NVIDIA cuDNN and CUDA toolkits.
• Easy use: TensorFlow is for everyone, it's for students, researchers, deep learning practitioners, and also for readers of this book.
• Production ready at scale: Recently it has evolved as the neural network for machine translation, at production scale. TensorFlow 1.x promises Python API stability, making it easier to choose new features without worrying too much about breaking your existing code.
• Extensibility: TensorFlow is relatively newer technology and it's still under active development. However, it is extensible because it was released with source code available on GitHub (https://github.com/tensorflow/tensorflow).
• Supported: There is a large community of developers and users working together to make TensorFlow a better product, both by providing feedback and by actively contributing to the source code.
• Wide adoption: Numerous tech giants are using TensorFlow for increasing their business intelligence. For example, ARM, Google, Intel, eBay, Qualcomm, SAM, Drobox, DeepMind, Airbnb, Twitter, and so on.

Throughout the next lesson, we will see how to achieve these features for predictive analytics.