https://github.com/thangbuiq/garbage-classification-web

Garbage classification website on AWS with Tensorflow ResNet50 as deeplearning model, FastAPI as backend and ReactJs as frontend. DEPRECATED: No resource for API hosting
https://github.com/thangbuiq/garbage-classification-web

ec2 fastapi reactjs resnet-50

Last synced: 7 months ago
JSON representation

Garbage classification website on AWS with Tensorflow ResNet50 as deeplearning model, FastAPI as backend and ReactJs as frontend. DEPRECATED: No resource for API hosting

• Host: GitHub
• URL: https://github.com/thangbuiq/garbage-classification-web
• Owner: thangbuiq
• License: apache-2.0
• Created: 2023-10-14T11:59:56.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-05-04T07:58:40.000Z (over 1 year ago)
• Last Synced: 2025-01-25T04:48:14.732Z (9 months ago)
• Topics: ec2, fastapi, reactjs, resnet-50
• Language: JavaScript
• Homepage: https://garbage-classification-web.vercel.app
• Size: 170 MB
• Stars: 2
• Watchers: 1
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Machine Learning To Production

> [!IMPORTANT]

> Our project during the university course, we have deployed a webapp to classify garbage images. We have used **ResNet50** model to classify the images. The model has been trained on the dataset of 6 classes: **cardboard, glass, metal, paper, plastic, trash**. The model has achieved **90%** accuracy on the test set.

> You can see the proof at [our report](https://thangbuiq.github.io/garbage-classification-web).

> But because of the cost, we have to stop the service. So, we choose **Render** to deploy our webapp and change the model to **Zero-shot learning** instead of **ResNet50**.

> [!NOTE]

> View our webapp at => [garbage-classification-web.vercel.app](https://garbage-classification-web.vercel.app/)

- Architect Design:

  ![Architecture Diagram](architecture.gif)

# Thank you for visiting