zylo117/Yet-Another-EfficientDet-Pytorch

Health v2 · maintenance only

Adoption not part of the score

5238 stars · 1245 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A PyTorch re-implementation of Google's EfficientDet object detection model with pretrained weights matching near-SOTA accuracy at real-time speeds. It includes training scripts, evaluation benchmarks, and model scales D0-D7.

Use cases

• train a custom object detection model in pytorch
• run real-time object detection with pretrained efficientdet weights
• benchmark efficientdet mAP and FPS on my GPU
• detect objects in images using efficientdet D0-D7
• fine-tune efficientdet on my own dataset
• convert efficientdet from tensorflow to pytorch

When to choose

• you want EfficientDet in PyTorch with pretrained weights close to official accuracy
• you need real-time object detection with a range of model sizes
• you want to fine-tune a detector on a custom dataset with provided tutorials

When to avoid

• you need the latest maintained implementation or newest model architectures
• you require TensorFlow or the official Google automl toolchain
• you need production support or frequent updates - the repo has not seen releases since 2021

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning image-processing python cross-platform object-detection efficientdet efficientnet bifpn pytorch pretrained-weights real-time-inference gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zylo117/Yet-Another-EfficientDet-Pytorch")