TensorFlow™
Price of TensorFlow™: free
Version: 1.3.1
TensorFlow™ is a popular library for deep learning and training of neural networks. A flexible system, which can be easily scalable, is used on both smartphones and desktops. TensorFlow™ is used in a variety of popular applications, such as Google Translate, Airbnb, Dropbox, Uber, Snapchat, etc.
The foundation of TensorFlow™ is data flow graphs. To get started with TensorFlow™, just specify the parameters of the neural network and its architecture. All calculations are performed on graphs. Data moves along the edges of the graph in the form of tensors - multidimensional arrays, which have a variable size. The transfer of the tensors occurs from one node of the graph to the other along its edges.
The TensorFlow™ library allows you to simplify the addition of self-learning components to various applications. With its help, you can implement the functions of artificial intelligence, which are used in the fields of robotics, speech recognition and image processing.
Instructions for launching Tensorflow™
To find out which versions of Python and pip are installed, run the following commands:
$ python -V && python3.5 -V
Python 2.7.5
Python 3.5.3
$ pip -V && pip3.5 -V
pip 9.0.1 from /usr/lib/python2.7/site-packages (python 2.7)
pip 9.0.1 from /usr/lib/python3.5/site-packages (python 3.5)
To find out which version is installed, run the following command:
$ python -c 'import tensorflow as tf; print(tf.__version__)' # for Python 2.7
1.1.0
$ python3.5 -c 'import tensorflow as tf; print(tf.__version__)' # for Python 3.n
1.2.1
Category
Machine learning
Industry
Automotive, Aerospace, Electronic, Biotechnology, Finance
License
Opensource/Free