Handwritten Letters Classifier

Model (PyTorch) + Web App (Streamlit) for the EMNIST letters dataset containing 145,600 images across 26 classes.

How To Run The Web App

1. Clone the repository with https://github.com/gitHasty-0321/canvasClassifier.git
2. To install - pip install -r requirements.txt
3. To install all deps separately - pip install streamlit streamlit-drawable-canvas torch torchvision
4. To run the app on http://localhost:8501 run streamlit run app/app.py

Handwritten.Letters.Classifier.-.Google.Chrome.2022-07-01.15-59-44_Trim.mp4