https://github.com/jamormoussa/sign-language-translation-using-deep-learning

Sign Language Translator using MLP, CNN and GCN.
https://github.com/jamormoussa/sign-language-translation-using-deep-learning

Last synced: 5 days ago
JSON representation

Sign Language Translator using MLP, CNN and GCN.

• Host: GitHub
• URL: https://github.com/jamormoussa/sign-language-translation-using-deep-learning
• Owner: JamorMoussa
• Created: 2024-05-28T19:33:16.000Z (7 months ago)
• Default Branch: main
• Last Pushed: 2024-06-02T22:10:46.000Z (7 months ago)
• Last Synced: 2024-12-16T04:17:07.923Z (9 days ago)
• Language: Python
• Homepage:
• Size: 32.8 MB
• Stars: 1
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Sign-Language-Translation-using-Deep-Learning

**Motivation:** How Can we use AI technologie to help Deaf People?

This project aims to build a Sign Language Translator system, which able to map each sign into english lettre. So, we're going to test vaious Deep Learning architectures including **Multi-layer Perceptron (MLP)**, **Convolution Neural Networks (CNN)** and **Graph Convolution Networks (GCN)**. 

## Project setup

Let's first create a virtual enviroment for this project

```bash

python3 -m venv --system-site-packages env

```

Next, install the `asl` library, which contains datasets for various architectures mentionned previously.

```bash

pip install -e .

```

**Note:** before install the `asl` lib, make sure that the `env` has been activated.

## Data Processing

For data processing you need to run the `process_data.py` script, with different arguments.

```bash

python3 process_data.py --which=gcn --max_sample=100 --replace=true

```