My project classifies the images in the single-etiquette multi-class classification problem from here: https://github.com/ardamavi/Sign-Language-Digits-Dataset
That code classifies the images using the neural networks from Keras. I also add here requirements.txt with librariers to install, as well as best model. Deep Learning Computer Vision Image Classification Keras Neural network Supervised Learning
I add here three models - main one is the best one with RMSprop optimizer. I also tested Adam and SGD. You can also see plots of the accuracy of these three models.
Before running my code, install the libraries with:
python -m pip install --upgrade pip
pip install -r requirements.txt
and adjust the paths to the training and test images.