> For the complete documentation index, see [llms.txt](https://machine-learning.paperspace.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://machine-learning.paperspace.com/wiki/comparison-of-ai-frameworks.md).

# Comparison of ML Frameworks

There are several popular frameworks for DNNs and classical ML.  All widely used frameworks are open source. Most but not all support GPU acceleration.

## Deep Learning frameworks

<div align="left"><img src="/files/-LwEmD_aNkyWXiVQpETt" alt=""></div>

**TensorFlow** (by Google): Offers training, distributed training, and inference (TensorFlow Serving) as well as other capabilities such as TFLite (mobile, embedded), Federated Learning (compute on end-user device, share learnings centrally), TensorFlow\.js, (web-native ML), TFX for platform etc.  TensorFlow is widely adopted, especially in enterprise/production-grade ML.  <br>

<div align="left"><img src="/files/-LwEly1m45zmV1d031Y4" alt=""></div>

**Keras** (also by Google): A higher-level wrapper around TensorFlow and other frameworks such as R and CNTK, which form the “backend” to Keras in this context.<br>

<div align="left"><img src="/files/-LwEmWqI7I47OMlGZkFE" alt=""></div>

**PyTorch** (by Facebook): An easy-to-use framework known for rapid prototyping. Facebook recently merged Caffe2 into the PyTorch project to support productionalizing and serving PyTorch-based models. PyTorch is especially popular in the research community.<br>

<div align="left"><img src="/files/-LwEmujRrD-Vz1qdZAT0" alt=""></div>

**Fast.ai** (by Fast.ai team): A library that sits on top of PyTorch to simplify and accelerate deep learning training.  Fast.ai is very new and its full reach is not yet known.<br>

<div align="left"><img src="/files/-LwEnY1FCCyLJfI8MEF2" alt=""></div>

**Microsoft Cognitive Toolkit\*** (by Microsoft): A framework focused on large-scale production deployments.  The community is small relative to other frameworks.\
\* Formerly **CNTK**<br>

<div align="left"><img src="/files/-LwEns_zopfPOTbBo-Pz" alt=""></div>

**MXNet** (by Apache but associated with Amazon): An open source deep learning framework focused on large-scale production deployments.  MXNet is popular at Microsoft, Intel, and Amazon but not in the research community.<br>

<div align="left"><img src="/files/-LwEoAL68gMOyAWyA1QJ" alt=""></div>

**Gluon** (by Amazon and Microsoft): An attempt to create a Keras-like API layer for MXNet and CNTK.  Gluon is not very popular.  <br>

<div align="left"><img src="/files/-LwEoTBvKk2XYgD5061x" alt=""></div>

**Chainer** (by a Japanese company called Preferred Networks):  A deep learning framework that is popular in Japan and supported by tech giants such as IBM, NVIDIA, AWS, and Intel. That said, the Chainer community is relatively small.<br>

<div align="left"><img src="/files/-LwEokOc4jGcUZ6RBU3e" alt=""></div>

**PaddlePaddle** (by Baidu): A scalable deep learning platform originally developed for use on Baidu products that is focused on large-scale production deployments.  The PaddlePaddle community is relatively small.<br>

<div align="left"><img src="/files/-LwEp01Oku5oreNKuUz0" alt=""></div>

**Deeplearning4j** (by Konduit, related to Eclipse): A deep learning programming library built for companies that need support for Java and Scala.  The community is relatively small.<br>

<div align="left"><img src="/files/-LwEpa3U9HKE0EedkEWZ" alt=""></div>

**Caffe** & **Caffe2** (by UC Berkeley): A deep learning framework that is especially suited to image classification and image segmentation. Caffe is not popular anymore but Facebook created a successor called Caffe2 which was recently merged into PyTorch.

## ML frameworks&#x20;

These frameworks are mostly used for “Classical ML” rather than Deep Learning:&#x20;

<div align="left"><img src="/files/-LwEpu9rwWgVsSseffNt" alt=""></div>

**XGBoost**: An open-source library built for one of the most common machine learning algorithms, [gradient boosting](/wiki/gradient-boosting.md). The community is very large.<br>

<div align="left"><img src="/files/-LwEq8nntcxnljDRUZuO" alt=""></div>

**Scikit-learn**: A machine learning library that provides algorithms for many standard machine learning tasks such as clustering, regression, classification, dimensionality reduction, and more. The community is very large.

## Libraries

Other popular machine learning libraries are typically used when preparing data for later use in ML frameworks. These include:&#x20;

* NumPy (arrays & linear algebra library)
* SciPy (scientific computing library)
* Pandas (data extraction & preparation)
* Matplotlib (plotting & data visualization)