Keras vs PyTorch

Overview

Keras

Stacks1.1K

Followers1.1K

Votes22

PyTorch

Stacks1.6K

Followers1.5K

Votes43

GitHub Stars94.7K

Forks25.8K

Keras vs PyTorch: What are the differences?

Ease of Use: Keras is known for its simplicity and ease of use, as it provides a high-level API that allows for quick prototyping and experimentation. On the other hand, PyTorch offers more flexibility and control to the users, making it suitable for researchers and practitioners who require fine-grained control over their models.
Computational Graph Definition: In Keras, the computational graph is defined statically before the model is run, which can limit flexibility in certain scenarios. PyTorch, on the other hand, utilizes dynamic computation graphs, allowing for more flexibility as the graph is built on-the-fly during execution.
Deployment and Production: Keras models can be more easily deployed in production environments due to its simplified API and integration with tools like TensorFlow Serving. PyTorch, while providing flexibility, may require more effort for deployment in production systems.
Community Support and Documentation: Keras has a larger community and more comprehensive documentation compared to PyTorch, making it easier for beginners to find help and resources. PyTorch, on the other hand, is favored by many researchers and academic institutions, leading to a more research-heavy community.
Graphical User Interface: Keras provides tools like TensorBoard for visualization and monitoring of models, whereas PyTorch lacks a built-in graphical interface, although third-party tools can be integrated for similar functionality.
Integration with Other Frameworks: Keras has seamless integration with TensorFlow, allowing users to leverage the capabilities of both frameworks. PyTorch, while compatible with other libraries, may require more manual intervention for integrating with different frameworks like TensorFlow.

In Summary, the key differences between Keras and PyTorch lie in ease of use, computational graph definition, deployment, community support, graphical user interface, and integration with other frameworks.

Share your Stack

Help developers discover the tools you use. Get visibility for your team's tech choices and contribute to the community's knowledge.

View Docs

CLI (Node.js)

Manual

Advice on Keras, PyTorch

Developer at DCSIL

Oct 11, 2020

Decided

For data analysis, we choose a Python-based framework because of Python's simplicity as well as its large community and available supporting tools. We choose PyTorch over TensorFlow for our machine learning library because it has a flatter learning curve and it is easy to debug, in addition to the fact that our team has some existing experience with PyTorch. Numpy is used for data processing because of its user-friendliness, efficiency, and integration with other tools we have chosen. Finally, we decide to include Anaconda in our dev process because of its simple setup process to provide sufficient data science environment for our purposes. The trained model then gets deployed to the back end as a pickle.

99.3k views99.3k

Comments

Adithya

Student at PES UNIVERSITY

May 11, 2020

Needs advice

I have just started learning some basic machine learning concepts. So which of the following frameworks is better to use: Keras / TensorFlow/PyTorch. I have prior knowledge in python(and even pandas), java, js and C. It would be nice if something could point out the advantages of one over the other especially in terms of resources, documentation and flexibility. Also, could someone tell me where to find the right resources or tutorials for the above frameworks? Thanks in advance, hope you are doing well!!

107k views107k

Comments

philippe

Research & Technology & Innovation | Software & Data & Cloud | Professor in Computer Science

Sep 13, 2020

Review

Hello Amina, You need first to clearly identify the input data type (e.g. temporal data or not? seasonality or not?) and the analysis type (e.g., time series?, categories?, etc.). If you can answer these questions, that would be easier to help you identify the right tools (or Python libraries). If time series and Python, you have choice between Pendas/Statsmodels/Serima(x) (if seasonality) or deep learning techniques with Keras.

Good work, Philippe

4.64k views4.64k

Comments

Detailed Comparison

Keras	PyTorch
Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on TensorFlow or Theano. https://keras.io/	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.
neural networks API;Allows for easy and fast prototyping;Convolutional networks support;Recurent networks support;Runs on GPU	Tensor computation (like numpy) with strong GPU acceleration;Deep Neural Networks built on a tape-based autograd system
Statistics
GitHub Stars -	GitHub Stars 94.7K
GitHub Forks -	GitHub Forks 25.8K
Stacks 1.1K	Stacks 1.6K
Followers 1.1K	Followers 1.5K
Votes 22	Votes 43
Pros & Cons
Pros 8 Quality Documentation 7 Supports Tensorflow and Theano backends 7 Easy and fast NN prototyping Cons 4 Hard to debug	Pros 15 Easy to use 11 Developer Friendly 10 Easy to debug 7 Sometimes faster than TensorFlow Cons 3 Lots of code 1 It eats poop
Integrations
TensorFlow scikit-learn Python	Python

What are some alternatives to Keras, PyTorch?

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.

scikit-learn

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

Kubeflow

The Kubeflow project is dedicated to making Machine Learning on Kubernetes easy, portable and scalable by providing a straightforward way for spinning up best of breed OSS solutions.

TensorFlow.js

Use flexible and intuitive APIs to build and train models from scratch using the low-level JavaScript linear algebra library or the high-level layers API

Polyaxon

An enterprise-grade open source platform for building, training, and monitoring large scale deep learning applications.

Streamlit

It is the app framework specifically for Machine Learning and Data Science teams. You can rapidly build the tools you need. Build apps in a dozen lines of Python with a simple API.

MLflow

MLflow is an open source platform for managing the end-to-end machine learning lifecycle.

H2O

H2O.ai is the maker behind H2O, the leading open source machine learning platform for smarter applications and data products. H2O operationalizes data science by developing and deploying algorithms and models for R, Python and the Sparkling Water API for Spark.

PredictionIO

PredictionIO is an open source machine learning server for software developers to create predictive features, such as personalization, recommendation and content discovery.

Gluon

A new open source deep learning interface which allows developers to more easily and quickly build machine learning models, without compromising performance. Gluon provides a clear, concise API for defining machine learning models using a collection of pre-built, optimized neural network components.

Related Comparisons

Keras vs PyTorch: What are the differences?

Ease of Use: Keras is known for its simplicity and ease of use, as it provides a high-level API that allows for quick prototyping and experimentation. On the other hand, PyTorch offers more flexibility and control to the users, making it suitable for researchers and practitioners who require fine-grained control over their models.
Computational Graph Definition: In Keras, the computational graph is defined statically before the model is run, which can limit flexibility in certain scenarios. PyTorch, on the other hand, utilizes dynamic computation graphs, allowing for more flexibility as the graph is built on-the-fly during execution.
Deployment and Production: Keras models can be more easily deployed in production environments due to its simplified API and integration with tools like TensorFlow Serving. PyTorch, while providing flexibility, may require more effort for deployment in production systems.
Community Support and Documentation: Keras has a larger community and more comprehensive documentation compared to PyTorch, making it easier for beginners to find help and resources. PyTorch, on the other hand, is favored by many researchers and academic institutions, leading to a more research-heavy community.
Graphical User Interface: Keras provides tools like TensorBoard for visualization and monitoring of models, whereas PyTorch lacks a built-in graphical interface, although third-party tools can be integrated for similar functionality.
Integration with Other Frameworks: Keras has seamless integration with TensorFlow, allowing users to leverage the capabilities of both frameworks. PyTorch, while compatible with other libraries, may require more manual intervention for integrating with different frameworks like TensorFlow.

Keras vs PyTorch

Overview