What is TensorFlow?

Small overview of open source software library for numerical computation using data flow graphs
24 August 2017   1039

TensorFlow is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API. TensorFlow was originally developed by researchers and engineers working on the Google Brain Team within Google's Machine Intelligence research organization for the purposes of conducting machine learning and deep neural networks research, but the system is general enough to be applicable in a wide variety of other domains as well.

Main features:

  • The main library is suitable for a wide range of machine learning techniques, and not just for in-depth training.
  • Linear algebra and other insides are clearly visible from the outside.
  • In addition to the basic functionality of machine learning, TensorFlow also includes its own logging system, its own interactive log visualizer and even a powerful data delivery architecture.
  • The TensorFlow performance model differs from the scicit-learn of the Python language and from most tools in R.
     

Check official website for more info.

Students to Beat Google’s Machine-Learning Code

Student programmers' image classification algorithm successfully identifies the object in 93% of cases
13 August 2018   394

Developers-students from Fast.ai which organize free online computer training courses have created an image classification algorithm that successfully identifies the object in 93% of cases and copes with it faster than a similar Google algorithm with a similar configuration. The authors argue that "the creation of breakthrough technologies is not just for big companies". This is reported by MIT Technology Review.

When evaluating performance, the DAWNBench test was used, which calculates the speed and cost of teaching the neural network. During the Fast.ai experiment, the neural network was launched on 16 virtual AWS nodes, each contained 8 NVIDIA V100 graphics cards. This configuration achieved accuracy of 93% in 18 minutes, and the cost of machine time was estimated at $ 40. The result of Fast.ai is faster than the development of Google engineers by 40%, but the corporation uses its own clusters TPU Pod, so the comparison is not entirely objective.

The developers used the PyTorch Python library, as well as their own development - fastai. They were able to achieve this learning speed with the new method of cropping images from the ImageNet dataset: instead of square pictures, they began to use rectangular:

Fast AI
Fast AI

State-of-the-art results are not the exclusive domain of big companies. These are the obvious, dumb things that many researchers wouldn’t even think to do.
 

Jeremy Howard

Founder, Fast.AI

The authors tried to make the project accessible to everyone, so they simplified its infrastructure, refusing to use distributed computing systems and containers. To implement it, developers teamed up with engineers from the innovative division of the Pentagon (DIU) to release software to quickly create and support distributed models on AWS.