`Keras | Deep Learning with Tensorflow | Sicara

OPEN SOURCE CONTRIBUTION

Sicara in the Keras Ecosystem

Sicara is involved in the Keras Ecosystem.

All of our Deep Learning and Image Recognition projects use Keras. Leveraging the use of this powerful library, Sicara is involved in the Open-Source communities of Keras and Keras-RL, as both contributors and proofreaders.

Keras Deep Learning

Keras is the 2nd most-used Python tool in the world for Deep Learning. This open source library, created by François Chollet in 2015 (Software Engineer @Google), makes it easy and quick to create neural networks based on the main frameworks (Tensorflow, Pytorch, MXNET).

40K

Stars on Github

2nd

on Python

2015

Launch

Results

+30%
Speed of development
+800
Contributors
Background
Background
Quotes

Keras is a model-level library, providing high-level building blocks for developing deep-learning models. It doesn’t handle low-level operations such as tensor manipulation and differentiation. Instead, it relies on a specialized, well-optimized tensor library to do so, serving as the backend engine of Keras.

Creator of Keras

François Chollet, Deep Learning with Python

Why choose Keras?

Keras permet de diminuer de 30% le temps de développement d’un prototype de réseaux de neurones

How to do segmentation with Keras in Python

Why choose Keras?

Keras permet de diminuer de 30% le temps de développement d’un prototype de réseaux de neurones

En proposant une interface haut-niveau, Keras permet de diminuer de 30% le temps de développement d’un prototype de réseaux de neurones. Les temps d’entraînement restent semblables à ceux rencontrés en utilisant Tensorflow. Keras est également soutenue par une large communauté (26K stars, 630 contributeurs sur Github) dont des membres de Google, Microsoft, Nvidia et AWS. Sa pérennité en est assurée, la preuve: Netflix, Uber, Google ou encore la NASA l’utilisent.

Sicara in the Keras community

We maintain the KERAS-RL project

Breakout game with reinforcement learning

Sicara in the Keras community

We maintain the KERAS-RL project

Sicara participates in the efforts of the open-source deep learning community by maintaining the KERAS-RL project on Github. The KERAS-RL repertory offers algorithmic implementation of Reinforcement Learning using the Keras library.

Our Keras Experts

We have a Team of Experienced Keras users

startup, sicara, team, teamwork

Our Keras Experts

We have a Team of Experienced Keras users

As Keras is used on most our projects, we developed an expertise.

Adil

Centrale Paris

Clément

Mines Paris, PhD

Alexandre

Centrale Paris

Félix

Polytechnique

Raphaël

ENSTA, Polytechnique


Associated articles written by Sicara's Data Scientists

blurry street

GAN with Keras: Application to Image Deblurring

A Generative Adversarial Networks tutorial applied to Image Deblurring with the Keras library.

graph

Keras Tutorial: Content Based Image Retrieval Using a Denoising Autoencoder

How to find similar images thanks to Convolutional Denoising Autoencoder.

TensorFlow, AI, Docker, GPU

Set up TensorFlow with Docker + GPU in Minutes

Why Docker is the best platform to use Tensorflow with a GPU.