Lam1360/YOLOv3-model-pruning

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1676 stars · 429 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch implementation of YOLOv3 channel pruning (network slimming) applied to hand detection on the Oxford Hand dataset. It provides sparse training, pruning, and fine-tuning scripts that shrink the model to about one-sixth the parameters and one-third the FLOPs while keeping mAP essentially unchanged.

Use cases

• prune yolov3 to reduce model size and inference latency
• apply network slimming channel pruning to an object detector
• train a hand detector on the oxford hand dataset
• speed up yolov3 inference on gpu
• compress a detection model without losing accuracy
• learn how bn gamma based pruning works

When to choose

• you need a smaller, faster YOLOv3 detector and can retrain or fine-tune on your own dataset
• you want a working reference implementation of network slimming for detection models
• your target is hand detection specifically and you want pretrained pruned weights

When to avoid

• you need a maintained production-ready detection framework
• you want pruning for classification models as in the original paper
• you cannot run PyTorch 1.x training pipelines or lack GPU resources
• you expect the same compression ratios on datasets other than Oxford Hand

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning image-processing python yolov3 model-pruning network-slimming channel-pruning object-detection hand-detection pytorch model-compression sparse-training oxford-hand-dataset gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Lam1360/YOLOv3-model-pruning")