QData/C-Tran

General Multi-label Image Classification with Transformers

38
/ 100
Emerging

Implements a transformer-based architecture with label-specific attention mechanisms and multi-head label attention (LMT) to model inter-label dependencies for multi-label classification tasks. Built on PyTorch with support for standard benchmarks (COCO, VOC2007), featuring configurable transformer layers and gradient accumulation for efficient training on large-scale datasets.

280 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 19 / 25

How are scores calculated?

Stars

280

Forks

44

Language

Python

License

MIT

Last pushed

Nov 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/QData/C-Tran"

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