Sign in to see all reviews and comparisons. It's Free!
By clicking Sign In with Social Media, you agree to let PAT RESEARCH store, use and/or disclose your Social Media profile and email address in accordance with the PAT RESEARCH Privacy Policy and agree to the Terms of Use.
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.
Category
AI Platforms
Features
•Deep flexibility •True portability •Connect research and production •Auto-differentiation •Language options •Maximize performance
License
Proprietary Software
Price
Contact for Pricing
Pricing
Subscription
Free Trial
Available
Users Size
Small (<50 employees), Medium (50 to 1000 Enterprise (>1001 employees)
Company
TensorFlow
What is best?
•Deep flexibility •True portability •Connect research and production •Auto-differentiation •Language options
What are the benefits?
• You are able to share the benefits of machine learning • It's fast • Cloud TPUs are built to train and run ML models • Assists you in numerical computation • Flexible architecture
PAT Rating™
Editor Rating
Aggregated User Rating
Rate Here
Ease of use
9.3
5.9
Features & Functionality
9.3
6.0
Advanced Features
9.5
7.2
Integration
9.5
8.5
Performance
9.4
7.5
Customer Support
8.1
7.4
Implementation
9.2
Renew & Recommend
7.6
Bottom Line
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.
9.4
Editor Rating
7.5
Aggregated User Rating
41 ratings
You have rated this
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 users 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.Users construct the graph, and write the inner loop that drives computation.
TensorFlow will then provide helpful tools to assemble subgraphs common in neural networks, but users can write their own higher-level libraries on top of TensorFlow. Defining handy new compositions of operators is as easy as writing a Python function and costs the company nothing in performance.
TensorFlow runs on CPUs or GPUs, and on desktop, server, or mobile computing platforms. Using TensorFlow allows industrial researchers to push ideas to products faster, and allows academic researchers to share code more directly and with greater scientific reproducibility.TensorFlow users define the computational architecture of their predictive model, combine with the objective function, and just add data — TensorFlow handles computing the derivatives for the company.
TensorFlow comes with an easy to use Python interface and a no-nonsense C++ interface to build and execute computational graphs. Write stand-alone TensorFlow Python or C++ programs, or try things out in an interactive TensorFlow iPython notebook where users can keep notes, code, and visualizations logically grouped.
By clicking Sign In with Social Media, you agree to let PAT RESEARCH store, use and/or disclose your Social Media profile and email address in accordance with the PAT RESEARCH Privacy Policy and agree to the Terms of Use.