Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Waste Management :india:

The world generates at least 3.5 million tons of waste per day and this number is still increasing day by day that's why we need to aware about waste.

This web application can classify waste with 9 different waste materials and it will show you the details of that particular waste materials. This will help to raise awareness for people to reduce and recycle waste.

Overview

  • There are LIGHT BLUBS, PAPER, PLASTIC, ORGANIC, GLASS, BATTERIES, CLOTHES, METAL, E-WASTE total 9 different types of waste materials which are use for recycling.
  • In this project i have collected and filtered data by my self from google images and dreamstime.com
  • Here i have 8369 images belonging 9 classes.
  • Here i have trained dataset using VGG16 Transfer Learning technique of CNN for classification.
  • Here i have trained this model till 28 epochs and i got 69.77% accuracy.
  • Initially i had trained my model with Inceptionv3 and it's gave me 90.34% accuracy. But it was not accurate when i tested it on some images. But when i tested VGG16 with 69.77% accuracy it gives me accurate result.

Data Source

  • In this project i have collected and filtered data by my self from google images and dreamstime.com
  • I have uploaded my dataset on google drive.
  • click here to get dataset

Here's simple steps to create an application on Elastic Bean Stalk

  1. Open the Elastic Beanstalk console using this link: https://console.aws.amazon.com/elasticbeanstalk/home#/gettingStarted?applicationName=getting-started-app
  2. Enter your application name.
  3. Application tags are optional so just ignore it.
  4. For Platform, choose a python platform.
  5. For Application code choose Upload your code.
  6. Upload a zip file of your project.
  7. Click on create application button.
  • rest of the things will take care by aws elastic bean stalk and you will get deployed link.

Technologies Used

Motivation

  • My motivation watch is here

Team

  • If you like my work and it helped you in anyway then please do ⭐ the repository it will motivate me to make more amazing projects
Downloads last month

-

Downloads are not tracked for this model. How to track
Unable to determine this model's library. Check the docs .