Skip to content

lumialfe/CarSpottr

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

68 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CarSpottr

Project Description

CarSpottr is a web application that allows users to upload images of vehicles and get 3 segmentations of the images, corresponding to three different trained models.

This app is part of my final degree project, which aims to answer of whether it is possible to train a model to segment images of vehicles by using images generated from 3D renders as a form of data augmentation.

I used DeepLabV3+ as the model for the segmentation, and trained it using the a combination of datastes: one soruced online, and one generated from 3D renders.

Preview

image

Project Setup

  1. Get Docker Images
docker pull lumialfe/carspottr-webapp
docker pull lumialfe/carspottr-restapi
  1. Start the project
docker compose up --build
  1. Shut down the project
docker compose down

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published