Why developers like TensorFlow

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 150.8K GitHub stars and 83.3K GitHub forks. Here’s a link to TensorFlow's open source repository on GitHub

Who uses TensorFlow?

Companies

370 companies reportedly use TensorFlow in their tech stacks, including Uber, Delivery Hero, and Ruangguru.

Uber

Delivery Hero

Ruangguru

Hepsiburada

9GAG

WISESIGHT

Channel.io

Postmates

UpstageAI

Developers

1741 developers on StackShare have stated that they use TensorFlow.

General

Thrive Ministry

steakknife

My Stack

RunnerTag

My Stack

TensorFlow Integrations

JavaScript, Jupyter, Keras, Databricks, and Kubeflow are some of the popular tools that integrate with TensorFlow. Here's a list of all 43 tools that integrate with TensorFlow.

JavaScript

Jupyter

Keras

Databricks

Kubeflow

TensorFlow.js

Amazon SageMaker

Streamlit

Amazon Elastic Inference

Pros of TensorFlow

High Performance

Connect Research and Production

High level abstraction

Powerful

Public Decisions about TensorFlow

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

adarsh pandey

Apr 26, 2020 | 4 upvotes · 46.4K views

Shared insights

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.

Ayah Sa'fin

Mar 18, 2020 | 4 upvotes · 18.8K views

Shared insights

Falcon

Phalcon

TensorFlow

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 all decisions

Blog Posts

Empowering Pinterest Data Scientists and Machine Learning Engi...

Jul 9, 2020 at 2:41PM

+11

1655

AI/ML Pipelines Using Open Data Hub and Kubeflow on Red Hat Op...

Jan 29, 2020 at 2:08PM

Red Hat, Inc.

+14

1813

Building a Kubernetes Platform at Pinterest

Dec 4, 2019 at 8:01PM

2684

TensorFlow Alternatives & Comparisons

What are some alternatives to TensorFlow?

Theano

Theano is a Python library that lets you to define, optimize, and evaluate mathematical expressions, especially ones with multi-dimensional arrays (numpy.ndarray).

PyTorch

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

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.

Keras

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

Related Comparisons