Please :star: this repo if you find it useful

DeepStack Trainer

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.

DeepStack’s source code is available on GitHub via https://github.com/johnolafenwa/DeepStack

DeepStack Trainer is a FastAPI powerd web application that helps us train and test Deepstack AI easelly as possible.

Features

Face Registring.
Test face recognition.
Test scene recognition.
Test object detection.
Gallery page, display all uploaded images (For traning only).

Components used in Deepstack Trainer

FastAPI - For running web server
materializecss - For web forms
sweetalert2 - For alerts and messages

Installation

Deepstack Installation

In order to use Deepstack Trainer we need to install Deepstack. We can do that by running the following command:

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

Basic Parameters:

-e VISION-FACE=True This enables the face recognition APIs.
-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.

We can also install Deepstack using docker-compose:

version: "3.7"
services:
  deepstack:
    image: deepquestai/deepstack:latest
    restart: unless-stopped
    container_name: deepstack
    ports:
      - "80:5000"
    environment:
      - TZ=Asia/Jerusalem
      - VISION-FACE=True
      - VISION-DETECTION=True
      - VISION-SCENE=True
    volumes:
      - ./deepstack:/datastore

Deepstack Trainer Installation

Deepstack Trainer installation is very easy using docker-compose:

version: "3.7"
services:
  deepstack_trainer:
    image: techblog/deepstack-trainer
    container_name: deepstack_trainer
    privileged: true
    restart: always
    environment:
      - DEEPSTACK_HOST_ADDRESS=
      - DEEPSTACK_API_KEY=
      - MIN_CONFIDANCE=
    ports:
      - "8080:8080" 
    volumes:
      - ./deepstack-trainer/db:/opt/trainer/db #Database storing the uploaded photos data (Filename, Person name, Date).
      - ./deepstack-trainer/uploads:/opt/trainer/photos/uploads #Phisical path for storing the images

Basic Parameters:

DEEPSTACK_HOST_ADDRESS - Deepstack API Url (http://localhost:5000)
DEEPSTACK_API_KEY - If your Deepstack API is token protected enter your token here or alse leave blank
MIN_CONFIDANCE - Minimum Confidence level to identify object or face (Default is 0.70)

Working with Deepstack Trainer

After the docker is up and running, open your browser and navigate to your Deepstack Trainer url. you will be able to see four tabs:

Face Learning (Registring).
Face Recognition
Object Detection
Scene Detection
Photo Gallery

Integrations and Community

The DeepStack ecosystem includes a number of popular integrations and libraries built to expand the functionalities of the AI engine to serve IoT, industrial, monitoring and research applications. A number of them are listed below

t0mer / deepstack-trainer

readme