DeepStack is an AI server that empowers every developer in the world to easily build state-of-the-art AI systems both on premise and in the cloud. The promises of Artificial Intelligence are huge but becoming a machine learning engineer is hard. DeepStack is device and language agnostic. You can run it on Windows, Mac OS, Linux, Raspberry PI and use it with any programming language.

Top Features

• ​FACE DETECTION & RECOGNITION​

• ​OBJECT DETECTION​

• ​SCENE RECOGNITION​

• ​SUPPORT FOR CUSTOM ONNX, KERAS AND TENSORFLOW MODELS​

• ​IN-BUILT SECURITY​

• ​SIMPLE REST APIs​

Example Code

Using DeepStack, we can classify the scene of the above image as seen below

import requests
​
image_data = open("image.jpg","rb").read()
​
response = requests.post("http://localhost:80/v1/vision/scene",
files={"image":image_data}).json()
print(response)

Response

{ success: true, label: 'highway', confidence: 0.63377846 }

You simply send in an image by POST and DeepStack returns a JSON response detailing the label of the image as well as the confidence of the prediction on a scale of 0 - 1

DeepStack is developed and maintained by DeepQuest AI​

Installation

DeepStack is available in three variants, CPU Version, GPU Version and Raspberry PI Version (With Support for Intel Neural Compute Stick)

Instructions for installation of the CPU Version is in the next section.

​Installation Guide for GPU Version​

​Installation Guide for Raspberry PI​

Installing DeepStack - CPU Version

Step 1: Install Docker (If not already installed)

sudo apt-get update
sudo apt-get install curl
curl -fsSL get.docker.com -o get-docker.sh && sh get-docker.sh

Mac OS and Windows Users can install docker from Docker's Website​

Step 2: Install DeepStack

sudo docker pull deepquestai/deepstack

Step 3: Run DeepStack

sudo docker run -e VISION-SCENE=True -v localstorage:/datastore -p 80:5000 deepquestai/deepstack

Basic Parameters

-e VISION-SCENE=True This enables the scene recognition API, all apis are disabled by default.

-v localstorage:/datastore This specifies the local volume where DeepStack will store all data.

-p 80:5000 This makes DeepStack accessible via port 80 of the machine.

Run the example scene recognition code to verify your installation is working