search

hunglc007 / tensorflow-yolov4-tflite

YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite
https://github.com/hunglc007/tensorflow-yolov4-tflite
MIT License
2.23k stars 1.24k forks source link

Error in anchors for Yolov4 tiny #440

Open aniket611 opened 2 years ago

aniket611 commented 2 years ago

The anchors defined for YOLOv4 tiny network are different than those given in original YOLOv4 tiny in darknet. https://github.com/AlexeyAB/darknet/blob/master/cfg/yolov4-tiny.cfg Original anchors are: anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319 In config.py, the anchors are: __C.YOLO.ANCHORS_TINY = [23,27, 37,58, 81,82, 81,82, 135,169, 344,319]

This can create wrong outputs if model is trained on darknet and this repo is used for model conversion and inference. If these settings are as per some specific application then we can close this issue.

TZECHIN6 commented 2 years ago

Hi, if this finding is true, can i simply change the anchors values to solve this ?