'Incorrect positions of bounding boxes while testing my Yolov4 custom model

I'm trying to train a Yolov4 darknet custom model but having problems when testing the model: Incorrect bounding boxes

Some information:

Dataset: 12,000 images.

Dimensions of images: 1920x1080

Classes: 6

Training: Local machine with a GPU gtx 960 running under linux.

My configuration of (yolov4-custom.cfg):

batch=64

subdivisions=64

width=416

height=416

filters=33

classes=6

obj.data file: obj.data file image ob.names containes all of the 6 classes that i´m using

Results: chart.png Training process

Testing Yolov4-custom_last.weights: Testing weights I adjusted the threshold with values from 0.40 to 0.90 and got same results

Do you know what might be the problem?

Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Solution	Source