yolov3 and tensorflow-yolov3
These two tools are competitors, as both are implementations of YOLOv3, with the first being the original Ultralytics implementation and the second an alternative TensorFlow implementation by YunYang1994.
About yolov3
ultralytics/yolov3
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
Implements multi-scale feature pyramids and anchor-based detection with spatial attention mechanisms for improved accuracy on small objects. Provides built-in training pipelines with data augmentation, mixed-precision support, and batch normalization optimization across PyTorch, ONNX, CoreML, and TFLite export targets for seamless deployment across cloud and edge devices.
About tensorflow-yolov3
YunYang1994/tensorflow-yolov3
🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"
Implements YOLOv3 object detection with TensorFlow 1.x, featuring pre-trained COCO weights convertible to frozen graph format for inference on images and video streams. Supports transfer learning from COCO checkpoints and training on custom datasets (VOC, PASCAL) with configurable anchor boxes and class definitions. Includes evaluation utilities for mAP calculation and TensorBoard integration for monitoring training metrics.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work