A large-image collection explorer and fast classification tool

Related tags

Deep Learningimax
Overview

IMAX: Interactive Multi-image Analysis eXplorer

This is an interactive tool for visualize and classify multiple images at a time. It written in Python and Javascript. It is based on Leaflet and it reads the images from a single directory and there is no need for multiple resolutions folders as images are scaled dynamically when zooming in/out. It runs an asyncio server in the back end and supports up 10,000 images reasonable well. It can load more images but it will slower. It runs using multiple cores and has been tested with over 50K images.

You can move and label images all from the keyboard.

You can see a (not very good) gif demo ot the tool in action, a live demo or a better video is here

Demo

Deployment

Simple deployment

Clone this repository:

	git clone https://github.com/mgckind/imax.git
	cd imax/python_server

Create a config file template:

	cp config_template.yaml config.yaml

Edit the config.yaml file to have the correct parameters, see Configuration for more info.

Start the server:

   python3 server.py

Start the client and visit the url printed python_server:

   python3 client.py

If you are running locally you can go to http://localhost:8000/

Docker

  1. Create image from Dockerfile

     cd imax
     docker build -t imax .
    
  2. Create an internal network so server/client can talk through the internal network (is not need for now as we are exposing both services at the localhost)

     docker network create --driver bridge imaxnet
    
  3. Create local config file to be mounted inside the containers. Create config.yaml based on the template, and replace the image location.

  4. Start the server container and attach the volume with images, connect to network and expose port 8888 to localhost

        docker run -d --name server -p 8888:8888 -v {PATH TO CONFIG FILE}:/home/explorer/server/config.yaml -v {PATH TO LOCAL IMAGES}:{PATH TO CONTAINER IMAGES} --network imaxnet imax python server.py
    
  5. Start the client container, connect to network and expose the port 8000 to local host

        docker run -d --name client -p 8000:8000 -v {PATH TO CONFIG FILE}:/home/explorer/server/config.yaml  --network imaxnet imax python client.py
    

Now the containers can talk at the localhost. If you are running locally you can go to http://localhost:8000/

Usage

This is the Help window displayed


Help


-> Fullscreen
-> Invert colors
/ -> Toggle On/Off classified tiles.
First time it reads from DB.

-> Random. Show a new random subsample (if available data is larger)
-> Apply filter to the displayed data.
Use the checkboxes on the left bottom side. -1 means no classified.
-> Reset filters and view. Do not display deleted images.

Move around with mouse and keyboard , use the mouse wheel to zoom in/out and double click to focus on one image.

Keyboard

Use "w","a","s","d" to move the selected tile and the keyboard numbers to apply a class as defined in the configuration file
Use "+", "-" to zoom in/out
Use "c" to clear any class selection
Use "t" to toggle on/off the classes
Use "h" to toggle on/off the Help
Use "f" to toggle on/off Full screen
Defined classes will appear at the bottom right side of the map

Configuration

This is the template config file to use:

#### DISPLAY
display:
  dataname: '{FILL ME}' #Name for the sqlite DB and config file
  path: '{FILL ME}'
  nimages: 1200 #Number of objects to be displayed even if there are more in the folder
  xdim: 40 #X dimension for the display
  ydim: 30 #Y dimension for the display
  tileSize: 256 #Size of the tile for which images are resized at max zoom level
  minXrange: 0
  minYrange: 0
  deltaZoom: 3 #default == 3
#### SERVER
server:
  ssl: false #use ssl, need to have certificates
  sslName: test #prefix of .crt and .key files inside ssl/ folder e.g., ssl/{sslName.key}
  host: 'http://localhost' #if using ssl, change to https
  port: 8888
  rootUrl: '/cexp' #root url for server, e.g. request are made to /cexp/, if None use "/"
  #workers: None # None will default to the workers in the machine
#### CLIENT
client:
  host: 'http://localhost'
  port: 8000
#### OPERATIONS options
operation:
  updates: true #allows to update and/or remove classes to images, false and classes are fixed.
#### CLASSES
#### classes, use any classes from 0 to 9, class 0 is for hidden! class -1 is no class
classes:
    - Delete: 0
    - Spiral: 8
    - Elliptical: 9
    - Other: 7
Owner
Matias Carrasco Kind
Data Science Research Services @giesdsrs director at UIUC. Astrophysicist and former Senior Research Scientist at @ncsa
Matias Carrasco Kind
Use AI to generate a optimized stock portfolio

Use AI, Modern Portfolio Theory, and Monte Carlo simulation's to generate a optimized stock portfolio that minimizes risk while maximizing returns. Ho

Greg James 30 Dec 22, 2022
Code for the Image similarity challenge.

ISC 2021 This repository contains code for the Image Similarity Challenge 2021. Getting started The docs subdirectory has step-by-step instructions on

Facebook Research 173 Dec 12, 2022
Kaggle Lyft Motion Prediction for Autonomous Vehicles 4th place solution

Lyft Motion Prediction for Autonomous Vehicles Code for the 4th place solution of Lyft Motion Prediction for Autonomous Vehicles on Kaggle. Discussion

44 Jun 27, 2022
Metadata-Extractor - Metadata Extractor Script can be used to read in exif metadata

Metadata Extractor The exifextract script can be used to read in exif metadata f

1 Feb 16, 2022
Using machine learning to predict undergrad college admissions.

College-Prediction Project- Overview: Many have tried, many have failed. Few trailblazers are ambitious enought to chase acceptance into the top 15 un

John H Klinges 1 Jan 05, 2022
render sprites into your desktop environment as shaped windows using GTK

spritegtk render static or animated sprites into your desktop environment as dynamic shaped windows using GTK requires pycairo and PYGobject: pip inst

hermit 20 Oct 27, 2022
Image Captioning on google cloud platform based on iot

Image-Captioning-on-google-cloud-platform-based-on-iot - Image Captioning on google cloud platform based on iot

Shweta_kumawat 1 Jan 20, 2022
Continuous Conditional Random Field Convolution for Point Cloud Segmentation

CRFConv This repository is the implementation of "Continuous Conditional Random Field Convolution for Point Cloud Segmentation" 1. Setup 1) Building c

Fei Yang 8 Dec 08, 2022
The fastai deep learning library

Welcome to fastai fastai simplifies training fast and accurate neural nets using modern best practices Important: This documentation covers fastai v2,

fast.ai 23.2k Jan 07, 2023
PoolFormer: MetaFormer is Actually What You Need for Vision

PoolFormer: MetaFormer is Actually What You Need for Vision (arXiv) This is a PyTorch implementation of PoolFormer proposed by our paper "MetaFormer i

Sea AI Lab 1k Dec 30, 2022
Official pytorch implementation of "DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion"

DSPoint Official pytorch implementation of "DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion" Coming soon, as soon as I finish a

Ziyao Zeng 14 Feb 26, 2022
EXplainable Artificial Intelligence (XAI)

EXplainable Artificial Intelligence (XAI) This repository includes the codes for different projects on eXplainable Artificial Intelligence (XAI) by th

4 Nov 28, 2022
Implementation of the method proposed in the paper "Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation"

Neural Descriptor Fields (NDF) PyTorch implementation for training continuous 3D neural fields to represent dense correspondence across objects, and u

167 Jan 06, 2023
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

English | 简体中文 Documentation: https://mmtracking.readthedocs.io/ Introduction MMTracking is an open source video perception toolbox based on PyTorch.

OpenMMLab 2.7k Jan 08, 2023
Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving

SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving Abstract In this paper, we introduce SalsaNext f

308 Jan 04, 2023
RaceBERT -- A transformer based model to predict race and ethnicty from names

RaceBERT -- A transformer based model to predict race and ethnicty from names Installation pip install racebert Using a virtual environment is highly

Prasanna Parasurama 3 Nov 02, 2022
PyTorch Live is an easy to use library of tools for creating on-device ML demos on Android and iOS.

PyTorch Live is an easy to use library of tools for creating on-device ML demos on Android and iOS. With Live, you can build a working mobile app ML demo in minutes.

559 Jan 01, 2023
Adjust Decision Boundary for Class Imbalanced Learning

Adjusting Decision Boundary for Class Imbalanced Learning This repository is the official PyTorch implementation of WVN-RS, introduced in Adjusting De

Peyton Byungju Kim 16 Jan 04, 2023
SAS output to EXCEL converter for Cornell/MIT Language and acquisition lab

CORNELLSASLAB SAS output to EXCEL converter for Cornell/MIT Language and acquisition lab Instructions: This python code can be used to convert SAS out

2 Jan 26, 2022
A PyTorch implementation of "Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning", IJCAI-21

MERIT A PyTorch implementation of our IJCAI-21 paper Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning. Depen

Graph Analysis & Deep Learning Laboratory, GRAND 32 Jan 02, 2023