We do offer an on premises solution that we provide using Docker.
How does this on premises solution work?
Our customers can run our Deep Learning model on their own premises using our docker images. This creates a version of our api that is hosted on our customers own servers.
What is Docker
Docker is a set of platform as a service products that use OS-level virtualization to deliver software in packages called containers. Containers are isolated from one another and bundle their own software, libraries and configuration files; they can communicate with each other through well-defined channels.
You can read more about it here: docker.com
According to Docker, over 3.5 million applications have been placed in containers using Docker technology and over 37 billion containerized applications have been downloaded. It's not just Docker who thinks they're on to something big.
What is the pricing for Docker
You can see the details of the pricing at nanonets.com/pricing
What are the hardware requirements
c4.2xlarge (8 core 15GB memory)
D4 v3. (4 core 16GB memory)
Minimum requirement of 4 cores and 8 GB ram. You can run it on a machine with similar specifications.
What is the architecture diagram
The Standard NanoNets docker architecture diagram looks like the one below. It makes network requests for 2 purposes -
1. To fetch the docker image
2. To perform license checks
Architecture diagrams for specific use-cases may vary slightly.
What are the instructions to run the Docker Image
Once you upgrade to the Pro plan, under the Integrate tab you'll see "DOCKER INTEGRATION" After you click on it, you'll see the following instructions:
Here is the URL for Nvidia docker installation instructions: https://github.