Web UI with Jupyter Notebooks and GPU support
# Setup platform directory and architecture
export DD_PLATFORM=$HOME/deepdetect
export ARCH=cpu # gpu also available
# Install platform repository
git clone https://github.com/jolibrain/dd_platform_docker.git \
${DD_PLATFORM}
# Go to directory
cd ${DD_PLATFORM}/code/${ARCH}/
# Start platform docker containers
CURRENT_UID=$(id -u):$(id -g) MUID=$(id -u) \
docker-compose up -d
# Go to http://localhost:1912
Portable Deep Learning REST API
# Setup server architecture
export ARCH=cpu # gpu also available
# Pull the docker image
docker pull jolibrain/deepdetect_${ARCH}
# Start the AI server
docker run -d -u $(id -u ${USER}):$(id -g ${USER}) \
-p 8080:8080 jolibrain/deepdetect_${ARCH}
Focus on applications, AI is not a problem.
The core idea is to remove the error sources and difficulties of Deep Learning applications by providing a safe haven of commoditized practices, all available as a single core.
While the Open Source Deep Learning Server is the core element, with REST API, multi-platform support that allows training & inference everywhere, the Deep Learning Platform allows higher level management for training neural network models and using them as if they were simple code snippets.