gjy3035/C-3-Framework

An open-source PyTorch code for crowd counting

51
/ 100
Established

Provides standardized benchmarking across six mainstream crowd-counting datasets (GCC, UCF-QNRF, ShanghaiTech, WorldExpo'10, UCF_CC_50, UCSD) with solid baseline implementations of classic architectures (VGG, ResNet, CSRNet, SANet). Features automatic experiment reproducibility through code snapshots saved with each run and TensorBoard integration for loss visualization. Built on PyTorch with support for both ImageNet pretrained models and end-to-end density map regression training.

729 stars. No commits in the last 6 months.

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

How are scores calculated?

Stars

729

Forks

199

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gjy3035/C-3-Framework"

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