jrzech/reproduce-chexnet

Reproduce CheXNet

50
/ 100
Established

Implements multi-label CNN classification on 100,000+ NIH chest X-rays to detect 14 pathologies, using DenseNet-121 backbone with PyTorch and SGD+momentum optimization. Includes Jupyter notebooks for interactive prediction exploration, heatmap visualization, and model retraining on GPU. Provides pretrained checkpoints, performance metrics (AUC scores), and batch download utilities for the full NIH dataset, with 2022 updates ensuring compatibility with modern PyTorch/CUDA versions.

199 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

199

Forks

110

Language

Jupyter Notebook

License

BSD-3-Clause

Last pushed

Oct 18, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jrzech/reproduce-chexnet"

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