Alternatives to TensorFlow logo

Alternatives to TensorFlow

Theano, PyTorch, OpenCV, Keras, and Apache Spark are the most popular alternatives and competitors to TensorFlow.
3.1K
3.2K
+ 1
93

What is TensorFlow and what are its top alternatives?

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 168K GitHub stars and 87.2K GitHub forks. Here’s a link to TensorFlow's open source repository on GitHub

Top Alternatives to TensorFlow

  • Theano
    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

    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

    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
    Keras

    Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on TensorFlow or Theano. https://keras.io/ ...

  • Apache Spark
    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. ...

  • MXNet
    MXNet

    A deep learning framework designed for both efficiency and flexibility. It allows you to mix symbolic and imperative programming to maximize efficiency and productivity. At its core, it contains a dynamic dependency scheduler that automatically parallelizes both symbolic and imperative operations on the fly. ...

  • Caffe2
    Caffe2

    Caffe2 is deployed at Facebook to help developers and researchers train large machine learning models and deliver AI-powered experiences in our mobile apps. Now, developers will have access to many of the same tools, allowing them to run large-scale distributed training scenarios and build machine learning applications for mobile. ...

  • scikit-learn
    scikit-learn

    scikit-learn is a Python module for machine learning built on top of SciPy and distributed under the 3-Clause BSD license. ...

TensorFlow alternatives & related posts

Theano logo

Theano

28
62
0
Define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently
28
62
+ 1
0
PROS OF THEANO
    Be the first to leave a pro
    CONS OF THEANO
      Be the first to leave a con

      related Theano posts

      PyTorch logo

      PyTorch

      1.2K
      1.3K
      42
      A deep learning framework that puts Python first
      1.2K
      1.3K
      + 1
      42
      PROS OF PYTORCH
      • 14
        Easy to use
      • 11
        Developer Friendly
      • 10
        Easy to debug
      • 7
        Sometimes faster than TensorFlow
      CONS OF PYTORCH
      • 3
        Lots of code
      • 1
        It eats poop

      related PyTorch posts

      Server side

      We decided to use Python for our backend because it is one of the industry standard languages for data analysis and machine learning. It also has a lot of support due to its large user base.

      • Web Server: We chose Flask because we want to keep our machine learning / data analysis and the web server in the same language. Flask is easy to use and we all have experience with it. Postman will be used for creating and testing APIs due to its convenience.

      • Machine Learning: We decided to go with PyTorch for machine learning since it is one of the most popular libraries. It is also known to have an easier learning curve than other popular libraries such as Tensorflow. This is important because our team lacks ML experience and learning the tool as fast as possible would increase productivity.

      • Data Analysis: Some common Python libraries will be used to analyze our data. These include NumPy, Pandas , and matplotlib. These tools combined will help us learn the properties and characteristics of our data. Jupyter notebook will be used to help organize the data analysis process, and improve the code readability.

      Client side

      • UI: We decided to use React for the UI because it helps organize the data and variables of the application into components, making it very convenient to maintain our dashboard. Since React is one of the most popular front end frameworks right now, there will be a lot of support for it as well as a lot of potential new hires that are familiar with the framework. CSS 3 and HTML5 will be used for the basic styling and structure of the web app, as they are the most widely used front end languages.

      • State Management: We decided to use Redux to manage the state of the application since it works naturally to React. Our team also already has experience working with Redux which gave it a slight edge over the other state management libraries.

      • Data Visualization: We decided to use the React-based library Victory to visualize the data. They have very user friendly documentation on their official website which we find easy to learn from.

      Cache

      • Caching: We decided between Redis and memcached because they are two of the most popular open-source cache engines. We ultimately decided to use Redis to improve our web app performance mainly due to the extra functionalities it provides such as fine-tuning cache contents and durability.

      Database

      • Database: We decided to use a NoSQL database over a relational database because of its flexibility from not having a predefined schema. The user behavior analytics has to be flexible since the data we plan to store may change frequently. We decided on MongoDB because it is lightweight and we can easily host the database with MongoDB Atlas . Everyone on our team also has experience working with MongoDB.

      Infrastructure

      • Deployment: We decided to use Heroku over AWS, Azure, Google Cloud because it is free. Although there are advantages to the other cloud services, Heroku makes the most sense to our team because our primary goal is to build an MVP.

      Other Tools

      • Communication Slack will be used as the primary source of communication. It provides all the features needed for basic discussions. In terms of more interactive meetings, Zoom will be used for its video calls and screen sharing capabilities.

      • Source Control The project will be stored on GitHub and all code changes will be done though pull requests. This will help us keep the codebase clean and make it easy to revert changes when we need to.

      See more
      Conor Myhrvold
      Tech Brand Mgr, Office of CTO at Uber · | 8 upvotes · 1.5M views

      Why we built an open source, distributed training framework for TensorFlow , Keras , and PyTorch:

      At Uber, we apply deep learning across our business; from self-driving research to trip forecasting and fraud prevention, deep learning enables our engineers and data scientists to create better experiences for our users.

      TensorFlow has become a preferred deep learning library at Uber for a variety of reasons. To start, the framework is one of the most widely used open source frameworks for deep learning, which makes it easy to onboard new users. It also combines high performance with an ability to tinker with low-level model details—for instance, we can use both high-level APIs, such as Keras, and implement our own custom operators using NVIDIA’s CUDA toolkit.

      Uber has introduced Michelangelo (https://eng.uber.com/michelangelo/), an internal ML-as-a-service platform that democratizes machine learning and makes it easy to build and deploy these systems at scale. In this article, we pull back the curtain on Horovod, an open source component of Michelangelo’s deep learning toolkit which makes it easier to start—and speed up—distributed deep learning projects with TensorFlow:

      https://eng.uber.com/horovod/

      (Direct GitHub repo: https://github.com/uber/horovod)

      See more
      OpenCV logo

      OpenCV

      947
      963
      96
      Open Source Computer Vision Library
      947
      963
      + 1
      96
      PROS OF OPENCV
      • 36
        Computer Vision
      • 17
        Open Source
      • 11
        Imaging
      • 9
        Machine Learning
      • 9
        Face Detection
      • 6
        Great community
      • 4
        Realtime Image Processing
      • 2
        Helping almost CV problem
      • 2
        Image Augmentation
      CONS OF OPENCV
        Be the first to leave a con

        related OpenCV posts

        Shared insights
        on
        FFMPEGFFMPEGOpenCVOpenCV

        Hi Team,

        Could you please suggest which one need to be used in between OpenCV and FFMPEG.

        Thank you in Advance.

        See more
        Keras logo

        Keras

        1K
        1K
        20
        Deep Learning library for Theano and TensorFlow
        1K
        1K
        + 1
        20
        PROS OF KERAS
        • 7
          Easy and fast NN prototyping
        • 7
          Quality Documentation
        • 6
          Supports Tensorflow and Theano backends
        CONS OF KERAS
        • 4
          Hard to debug

        related Keras posts

        Conor Myhrvold
        Tech Brand Mgr, Office of CTO at Uber · | 8 upvotes · 1.5M views

        Why we built an open source, distributed training framework for TensorFlow , Keras , and PyTorch:

        At Uber, we apply deep learning across our business; from self-driving research to trip forecasting and fraud prevention, deep learning enables our engineers and data scientists to create better experiences for our users.

        TensorFlow has become a preferred deep learning library at Uber for a variety of reasons. To start, the framework is one of the most widely used open source frameworks for deep learning, which makes it easy to onboard new users. It also combines high performance with an ability to tinker with low-level model details—for instance, we can use both high-level APIs, such as Keras, and implement our own custom operators using NVIDIA’s CUDA toolkit.

        Uber has introduced Michelangelo (https://eng.uber.com/michelangelo/), an internal ML-as-a-service platform that democratizes machine learning and makes it easy to build and deploy these systems at scale. In this article, we pull back the curtain on Horovod, an open source component of Michelangelo’s deep learning toolkit which makes it easier to start—and speed up—distributed deep learning projects with TensorFlow:

        https://eng.uber.com/horovod/

        (Direct GitHub repo: https://github.com/uber/horovod)

        See more

        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
        Apache Spark logo

        Apache Spark

        2.7K
        3.2K
        137
        Fast and general engine for large-scale data processing
        2.7K
        3.2K
        + 1
        137
        PROS OF APACHE SPARK
        • 59
          Open-source
        • 48
          Fast and Flexible
        • 8
          One platform for every big data problem
        • 7
          Great for distributed SQL like applications
        • 6
          Easy to install and to use
        • 3
          Works well for most Datascience usecases
        • 2
          Interactive Query
        • 2
          In memory Computation
        • 2
          Machine learning libratimery, Streaming in real
        CONS OF APACHE SPARK
        • 3
          Speed

        related Apache Spark posts

        Eric Colson
        Chief Algorithms Officer at Stitch Fix · | 21 upvotes · 2.5M views

        The algorithms and data infrastructure at Stitch Fix is housed in #AWS. Data acquisition is split between events flowing through Kafka, and periodic snapshots of PostgreSQL DBs. We store data in an Amazon S3 based data warehouse. Apache Spark on Yarn is our tool of choice for data movement and #ETL. Because our storage layer (s3) is decoupled from our processing layer, we are able to scale our compute environment very elastically. We have several semi-permanent, autoscaling Yarn clusters running to serve our data processing needs. While the bulk of our compute infrastructure is dedicated to algorithmic processing, we also implemented Presto for adhoc queries and dashboards.

        Beyond data movement and ETL, most #ML centric jobs (e.g. model training and execution) run in a similarly elastic environment as containers running Python and R code on Amazon EC2 Container Service clusters. The execution of batch jobs on top of ECS is managed by Flotilla, a service we built in house and open sourced (see https://github.com/stitchfix/flotilla-os).

        At Stitch Fix, algorithmic integrations are pervasive across the business. We have dozens of data products actively integrated systems. That requires serving layer that is robust, agile, flexible, and allows for self-service. Models produced on Flotilla are packaged for deployment in production using Khan, another framework we've developed internally. Khan provides our data scientists the ability to quickly productionize those models they've developed with open source frameworks in Python 3 (e.g. PyTorch, sklearn), by automatically packaging them as Docker containers and deploying to Amazon ECS. This provides our data scientist a one-click method of getting from their algorithms to production. We then integrate those deployments into a service mesh, which allows us to A/B test various implementations in our product.

        For more info:

        #DataScience #DataStack #Data

        See more
        Conor Myhrvold
        Tech Brand Mgr, Office of CTO at Uber · | 7 upvotes · 1.2M views

        Why we built Marmaray, an open source generic data ingestion and dispersal framework and library for Apache Hadoop :

        Built and designed by our Hadoop Platform team, Marmaray is a plug-in-based framework built on top of the Hadoop ecosystem. Users can add support to ingest data from any source and disperse to any sink leveraging the use of Apache Spark . The name, Marmaray, comes from a tunnel in Turkey connecting Europe and Asia. Similarly, we envisioned Marmaray within Uber as a pipeline connecting data from any source to any sink depending on customer preference:

        https://eng.uber.com/marmaray-hadoop-ingestion-open-source/

        (Direct GitHub repo: https://github.com/uber/marmaray Kafka Kafka Manager )

        See more
        MXNet logo

        MXNet

        44
        76
        2
        A flexible and efficient library for deep learning
        44
        76
        + 1
        2
        PROS OF MXNET
        • 2
          User friendly
        CONS OF MXNET
          Be the first to leave a con

          related MXNet posts

          Caffe2 logo

          Caffe2

          48
          81
          2
          Open Source Cross-Platform Machine Learning Tools (by Facebook)
          48
          81
          + 1
          2
          PROS OF CAFFE2
          • 1
            Mobile deployment
          • 1
            Open Source
          CONS OF CAFFE2
            Be the first to leave a con

            related Caffe2 posts

            scikit-learn logo

            scikit-learn

            1.1K
            1K
            41
            Easy-to-use and general-purpose machine learning in Python
            1.1K
            1K
            + 1
            41
            PROS OF SCIKIT-LEARN
            • 23
              Scientific computing
            • 18
              Easy
            CONS OF SCIKIT-LEARN
            • 2
              Limited

            related scikit-learn posts

            Should I continue learning Django or take this Spring opportunity? I have been coding in python for about 2 years. I am currently learning Django and I am enjoying it. I also have some knowledge of data science libraries (Pandas, NumPy, scikit-learn, PyTorch). I am currently enhancing my web development and software engineering skills and may shift later into data science since I came from a medical background. The issue is that I am offered now a very trustworthy 9 months program teaching Java/Spring. The graduates of this program work directly in well know tech companies. Although I have been planning to continue with my Python, the other opportunity makes me hesitant since it will put me to work in a specific roadmap with deadlines and mentors. I also found on glassdoor that Spring jobs are way more than Django. Should I apply for this program or continue my journey?

            See more