Home

Awesome

SAPD (Soft Anchor Point Object Detection)

This is an implementation of SAPD for object detection on Keras and Tensorflow. The project is based on fizyr/keras-retinanet, qubvel/efficientnet, xuannianz/EfficientDet and xuannianz/FSAF. The pretrained EfficientNet weights files are downloaded from Callidior/keras-applications/releases

Thanks for their hard work. This project is released under the Apache License. Please take their licenses into consideration too when use this project.

Train

build dataset

  1. Pascal VOC
    • Download VOC2007 and VOC2012, copy all image files from VOC2007 to VOC2012.
    • Append VOC2007 train.txt to VOC2012 trainval.txt.
    • Overwrite VOC2012 val.txt by VOC2007 val.txt.
  2. MSCOCO 2017
    • Download images and annotations of coco 2017
    • Copy all images into datasets/coco/images, all annotations into datasets/coco/annotations
  3. Other types please refer to fizyr/keras-retinanet)

train

Evaluate

  1. PASCAL VOC

    • python3 eval/common.py to evaluate pascal model by specifying model path there.
    • The best evaluation results (score_threshold=0.01, mAP<sub>50</sub>) on VOC2007 test are:
    phi0
    mAP<sub>50</sub>0.7896
    weights size17M
  2. MSCOCO

    • python3 eval/coco.py to evaluate coco model by specifying model path there.

Test

python3 inference.py to test your image by specifying image path and model path there.

image1 image2 image3