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)
This project helps quickly and accurately identify multi-digit numbers found in street-level images, like house numbers or speed limits. You provide an image containing one or more digits, and it outputs the sequence of digits it detects. This is useful for anyone working with automated data collection from street imagery, such as city planners, mapping services, or urban data analysts.
201 stars. No commits in the last 6 months.
Use this if you need to automatically extract sequences of numbers from photographs of street scenes, especially for tasks like cataloging addresses or road signs.
Not ideal if you need to recognize text in general, or digits from different contexts like scanned documents or handwriting.
Stars
201
Forks
44
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
greydanus/mnist1d
A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep...
potterhsu/SVHNClassifier
A TensorFlow implementation of Multi-digit Number Recognition from Street View Imagery using...
kensanata/numbers
Handwritten digits, a bit like the MNIST dataset.
kdexd/digit-classifier
A single handwritten digit classifier, using the MNIST dataset. Pure Numpy.
billy-enrizky/Pytorch-Handwritten-Digit-Recognition
🚀 PyTorch Handwritten Digit Recognition 🤖 Discover the world of machine learning with our...