Dataset of Devnagari (Nepali) handwritten characters.
-
Updated
Jul 3, 2020 - Jupyter Notebook
Dataset of Devnagari (Nepali) handwritten characters.
License Plate Recognition (LPR) dataset for Nepali motorbike license plate.
A 3-block CNN built from scratch in PyTorch that recognises all 46 handwritten Devanagari characters, 36 consonants and 10 digits, at 96.8% test accuracy from only 100 training images per class. Photograph or draw a character in the Gradio app for a top-5 prediction. PyTorch, torchvision, scikit-learn, NumPy, Matplotlib, Seaborn, Pillow, Gradio.
🌟 Access a vast collection of Nepali datasets for NLP, speech, geospatial, and more, streamlining your machine learning projects in the Nepali language.
Add a description, image, and links to the dhcd topic page so that developers can more easily learn about it.
To associate your repository with the dhcd topic, visit your repo's landing page and select "manage topics."