potterhsu/SVHNClassifier-PyTorch

A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks (http://arxiv.org/pdf/1312.6082.pdf)

47
/ 100
Emerging

Implements multi-task learning with separate digit length and individual digit classifiers (10 output classes per position, with class 10 representing "no digit"), achieving 95.65% accuracy on SVHN. The architecture uses convolutional feature extraction with multi-head classification branches trained jointly on the Street View House Numbers dataset. Includes LMDB data pipeline for efficient preprocessing and Visdom integration for training visualization, plus optional C++ inference backend.

201 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

201

Forks

44

Language

Jupyter Notebook

License

MIT

Last pushed

Apr 26, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/potterhsu/SVHNClassifier-PyTorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.