GOATmessi8/ASFF

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1085 stars · 214 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 with the Adaptively Spatial Feature Fusion (ASFF) module and optional MobileNetV2 backbone for single-shot object detection. It reproduces the paper 'Learning Spatial Fusion for Single-Shot Object Detection' with training, evaluation, and demo scripts on COCO.

Use cases

• train a YOLOv3 object detector with ASFF feature fusion
• run object detection with a lightweight MobileNetV2 backbone
• reproduce ASFF paper results on COCO
• benchmark single-shot object detection models
• run object detection inference on images with a demo script

When to choose

• you need a research-grade YOLOv3+ASFF implementation in PyTorch
• you want a lightweight MobileNetV2-based detector for edge or mobile use
• you want to reproduce or extend the ASFF paper

When to avoid

• you need a modern, actively maintained detector like YOLOX or YOLOv5+
• you need FP16 training with MobileNetV2, which is unsupported
• you need production support, broad documentation, or recent PyTorch compatibility

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning image-processing python object-detection yolov3 asff mobilenetv2 pytorch single-shot-detector feature-fusion research-code linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="GOATmessi8/ASFF")