TensorFlow logo


Open Source Software Library for Machine Intelligence
+ 1

What is TensorFlow?

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 is a tool in the Machine Learning Tools category of a tech stack.
TensorFlow is an open source tool with 166.8K GitHub stars and 87K GitHub forks. Here’s a link to TensorFlow's open source repository on GitHub

Who uses TensorFlow?

491 companies reportedly use TensorFlow in their tech stacks, including Uber, Delivery Hero, and Hepsiburada.

2368 developers on StackShare have stated that they use TensorFlow.

TensorFlow Integrations

JavaScript, Jupyter, Keras, Databricks, and Kubeflow are some of the popular tools that integrate with TensorFlow. Here's a list of all 51 tools that integrate with TensorFlow.
Pros of TensorFlow
High Performance
Connect Research and Production
Deep Flexibility
True Portability
High level abstraction
Easy to use
Decisions about TensorFlow

Here are some stack decisions, common use cases and reviews by companies and developers who chose TensorFlow in their tech stack.

I am going to send my website to a Venture Capitalist for inspection. If I succeed, I will get funding for my StartUp! This website is based on Django and Uses Keras and TensorFlow model to predict medical imaging. Should I use Heroku or PythonAnywhere to deploy my website ?? Best Regards, Adarsh.

See more
Shared insights

Hello All, I have concerns about which framework to use in my case. I'm working on a project that uses TensorFlow for implementing CNN and image processing, it also deals with a huge dataset. Shall I implement the rest APIs in Phalcon because of its speed and great performance or Falcon since I'm working with TensorFlow and doing image processing steps?

PS: APIs are to receive the image from the user, and call *.py files to execute image processing steps and CNN Thanks In Advance :D

See more
Zack Shainsky
Field Data Scientists at Zepl · | 6 upvotes · 13.9K views
Shared insights

I am working on a data collection project which requires processing images of playing cards for a deck-building game called StarRealms (https://www.starrealms.com/). I need to be able to read in a database of images or videos and recognize each card as a game is played. I believe this would involve some computer vision for image recognition and TensorFlow modeling to ensure an accurate prediction. Which technology stack would be the best for this job? Thank you for the help!

See more
Aicha Mahfoudh
Shared insights
Tesseract OCRTesseract OCRTensorFlowTensorFlow

Can I use both TensorFlow and Tesseract OCR to create a model that detects text out of a document pdf

See more
rashid munir
freelancer at freelancer · | 3 upvotes · 41.4K views

Need your kind suggestion if I should choose TensorFlow.js or TensorFlow with Python for ML models. As I don't want to go and have not gone too deep in JavaScript, I need your suggestion.

See more

I am unhappy. When doing my research, I heard Python is useless. Data science is an unworthy field thanks to TensorFlow, and web scraping has also become pointless since the introduction of the PWA. Since PWAs are only frontend, I feel forced to learn JavaScript, and to ditch Python. I love Python with all my mind, it's simplicity, conciseness, and easiness as a tool. Here are a few questions:

  1. Should I forget Python and move on?
  2. Are there any PWA alternatives to JavaScript/TypeScript. I've been thinking of using Python for WASM and use HTML+CSS for the DOM to create the PWA. Is this possible?
  3. Why is JavaScript such a pain in the butt
  4. What's the point of me learning Python if it's not useful for web development?
See more

Blog Posts

Dec 4 2019 at 8:01PM



TensorFlow Alternatives & Comparisons

What are some alternatives to TensorFlow?
Theano is a Python library that lets you to define, optimize, and evaluate mathematical expressions, especially ones with multi-dimensional arrays (numpy.ndarray).
PyTorch is not a Python binding into a monolothic C++ framework. It is built to be deeply integrated into Python. You can use it naturally like you would use numpy / scipy / scikit-learn etc.
OpenCV was designed for computational efficiency and with a strong focus on real-time applications. Written in optimized C/C++, the library can take advantage of multi-core processing. Enabled with OpenCL, it can take advantage of the hardware acceleration of the underlying heterogeneous compute platform.
Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on TensorFlow or Theano. https://keras.io/
Apache Spark
Spark is a fast and general processing engine compatible with Hadoop data. It can run in Hadoop clusters through YARN or Spark's standalone mode, and it can process data in HDFS, HBase, Cassandra, Hive, and any Hadoop InputFormat. It is designed to perform both batch processing (similar to MapReduce) and new workloads like streaming, interactive queries, and machine learning.
See all alternatives

TensorFlow's Followers
3158 developers follow TensorFlow to keep up with related blogs and decisions.