https://github.com/mgitrov/coce
A deep learning-based project aiming to classify images out of 10 classes.
https://github.com/mgitrov/coce
computer-vision convolutional-neural-networks deep-learning docker fastapi keras matplotlib numpy pillow regularization
Last synced: about 1 month ago
JSON representation
A deep learning-based project aiming to classify images out of 10 classes.
- Host: GitHub
- URL: https://github.com/mgitrov/coce
- Owner: MGitrov
- License: mit
- Created: 2022-11-29T15:18:47.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2023-02-09T08:40:33.000Z (almost 3 years ago)
- Last Synced: 2025-02-02T06:41:25.554Z (about 1 year ago)
- Topics: computer-vision, convolutional-neural-networks, deep-learning, docker, fastapi, keras, matplotlib, numpy, pillow, regularization
- Language: Jupyter Notebook
- Homepage:
- Size: 14.1 MB
- Stars: 0
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Introduction
CoCe :robot: is a deep learning-based project aiming to classify images out of the following 10 classes:
* Airplane
* Automobile
* Bird
* Cat
* Deer
* Dog
* Frog
* Horse
* Ship
* Truck
CoCe was built as part of the EASS course in order to get an understanding of how to deploy an end-to-end application using various tools commonly used in the tech industry.
# Demonstration
https://user-images.githubusercontent.com/68182283/215993391-bb095f79-2d3a-4f56-bc0d-aeb70c3acfaa.mp4
# Architecture
# Performance
Due to computational restrictions, the neural network was not able to go through many epochs. Nevertheless, the neural network gain pretty good accuracy score and the loss was minimized as much as possible so the neural network did not went to overfit.
* Accuracy: 43.25% -> 76.15%
* Loss: 1.5687 -> 0.6955
# Deployment
First of all you will need Git and Docker installed on your machine.
1. Open the Terminal, go inside your desired folder and run the following command:
``` bash
git clone https://github.com/EASS-HIT-PART-A-2022-CLASS-II/CoCe.git
```
2. Then you will have to go inside the "CoCe" folder using the following command:
```bash
cd CoCe
```
3. To run CoCe, you will have to enter the following command:
```bash
docker-compose up
```
4. Congratulations! You may access CoCe via your browser by typing the following address:
```bash
http://localhost:8501/
```