Sign Language Image Classification.

I entered a simple Vision classification competition. This competition will be split into 3 parts. This is because we will keep improving on our model, but initially we start with a basic model.

Introduction: Business Problem

Description: The sign language database of hand gestures represents a multi-class problem with 20 classes of letters and numbers (excluding some classes which require motion).

Evaluation: The evaluation metric for this competition is accuracy.

Methodology

The project will be executed by completing the following tasks:

1. Notebook setup
2. Create data block
3. Create dataloaders
4. Create model
5. Test dataloaders
6. Model submission file creation
7. Submit to kaggle
8. Add .ipynb notebook to kaggle

Link to Github Repository

Link to Blog post