I made this project when I participated in Task Mate Kenyan Sign Language Classification Challenge.
A common misconception of sign language is that it is the same everywhere; in reality there are as many as 300 different languages (approximately 50 of these from Africa) with new signs evolving each day as a need appears. Kenyan Sign Language (KSL) is used in Kenya and Somalia, and there are different dialects depending on what region you are in. It is used by over half of Kenya's estimated 600 000-strong deaf population.
The objective of this competition is to build a model to recognise ten different everyday KSL signs present in the images, using machine learning or deep learning algorithms.
Streamlit is a free and open-source framework to rapidly build and share beautiful machine learning and data science web apps. It is a Python-based library specifically designed for machine learning engineers. Data scientists or machine learning engineers are not web developers and they're not interested in spending weeks learning to use these frameworks to build web apps. Instead, they want a tool that is easier to learn and to use, as long as it can display data and collect needed parameters for modeling. Streamlit allows you to create a stunning-looking application with only a few lines of code.
Streamlit is the easiest way especially for people with no front-end knowledge to put their code into a web application:
- No front-end (html, js, css) experience or knowledge is required.
- You don't need to spend days or months to create a web app, you can create a really beautiful machine learning or data science app in only a few hours or even minutes.
- It is compatible with the majority of Python libraries (e.g. pandas, matplotlib, seaborn, plotly, Keras, PyTorch, SymPy(latex)).
- Less code is needed to create amazing web apps.
- Data caching simplifies and speeds up computation pipelines.
src/SignDetection/StratifiedKFold.py- This file contains the code for the StratifiedKFold class which is used to split the data into train and validation sets.src/SignDetection/augmentations.py- Contains the image augmentation functions.src/SignDetection/datloader.py- Contains the code for the dataloader class.src/SignDetection/engine.py- Contains the code for the training and validation functions.src/SignDetection/model.py- Contains the code for the model.src/SignDetection/train.py- Contains the code for the training loop.src/SignDetection/train_config.py- Contains the code for the training configuration.
src/utils/get_dataset.py- contains the code for encoding the dataset classes.
Dataset can be founded on the Zindi Competitions page. Dataset