Home

Awesome

Gaussian YOLOv3

This is an implementation of Gaussian YOLOv3 on Keras and Tensorflow. The project is based on qqwweee/keras-yolo3 and fizyr/keras-retinanet. Thanks for their hard work. The official implementation is jwchoi384/Gaussian_YOLOv3

As in the official implementation, there is a hyper parameter sigma_const. I get best result on Pascal VOC when set it to be 0.3. The best result (mAP<sub>50</sub> 0.8535) is a little better than the one (mAP<sub>50</sub> 0.8500) I got by original YOLOv3. I am not sure whether the improvement is due to random training or benefits from Gaussian logic.

Test

  1. I trained on Pascal VOC2012 trainval.txt + Pascal VOC2007 train.txt, and validated on Pascal VOC2007 val.txt. There are 14041 images for training and 2510 images for validation.

  2. The best evaluation result (score_threshold=0.01, mAP<sub>50</sub>, image_size=416, sigma_const=0.3) on VOC2007 test is 0.8535.

  3. Pretrained official yolo weights on COCO and gaussian yolo weights on Pascal VOC are here.
    baidu netdisk extract code: qgnd google driver

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

image1 image2 image3

Train

build dataset (Pascal VOC, other types please refer to fizyr/keras-retinanet)

train

Evaluate