jrzech/reproduce-chexnet
Reproduce CheXNet
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.
Stars
199
Forks
110
Language
Jupyter Notebook
License
BSD-3-Clause
Category
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.
Related frameworks
brucechou1983/CheXNet-Keras
This project is a tool to build CheXNet-like models, written in Keras.
gregwchase/nih-chest-xray
Identifying diseases in chest X-rays using convolutional neural networks
arnoweng/CheXNet
A pytorch reimplementation of CheXNet
dstrick17/DacNet
Reproducing and Improving CheXNet: Deep Learning for Chest X-ray Disease Classification
rmcnew/Pneumonia_Classifier
Machine Learning Image Classification of Pediatric Chest X-Rays to Detect Pneumonia