Annotation file data formats is not mentioned and also the class name

VisDrone / VisDrone-Dataset

The dataset for drone based detection and tracking is released, including both image/video, and annotations.

1.19k stars 152 forks source link

Annotation file data formats is not mentioned and also the class name #4

Open Samjith888 opened 4 years ago

Samjith888 commented 4 years ago

I have downloaded the dataset but the annotation data format is not mentioned and the class name too,]

How to identify data format inside the annotation file ? (Eg : xmin,ymin,xmax,ymax)

neeveermoree commented 4 years ago

@Samjith888 https://github.com/VisDrone/VisDrone2018-DET-toolkit Check here

zhengmiao1 commented 4 years ago

This notation doesn't seem quite right----ignored regions(0), pedestrian(1), people(2), bicycle(3), car(4), van(5), truck(6), tricycle(7), awning-tricycle(8), bus(9), motor(10), others(11) After I finished my training, I recognized the car as a bicycle

neeveermoree commented 3 years ago

@lingkongyingsun I am a bit late =). May be you misinterpreted your model output.

ganesh0074 commented 1 year ago

you need to convert that to yolo format, its available in yolov5 repository