YOLOv9 PyTorch TXT

Overview

In February 2024, Chien-Yao Wang, I-Hau Yeh, and Hong-Yuan Mark Liao, introduced YOLOv9, a computer vision model architecture that outperforms existing YOLO models, including YOLOv7 and YOLOv8.

This page describes the data format you will need to use to train a YOLOv9 model. Note: YOLOv9 uses the same format as YOLOv7.

Roboflow supports converting 30+ different object detection annotation formats into the TXT format that YOLOv9 needs and we automatically generate your YAML config file for you. Plus, all 90,000+ datasets available on Roboflow Universe are available in YOLOv7 format for seamless use in custom training.

Format Description

Below, learn the structure of YOLOv9 PyTorch TXT.

Each image has one txt file with a single line for each bounding box. The format of each row is

class_id center_x center_y width height

where fields are space delimited, and the coordinates are normalized from zero to one.

Note: To convert to normalized xywh from pixel values, divide x (and width) by the image's width and divide y (and height) by the image's height.

1 0.617 0.3594420600858369 0.114 0.17381974248927037
1 0.094 0.38626609442060084 0.156 0.23605150214592274
1 0.295 0.3959227467811159 0.13 0.19527896995708155
1 0.785 0.398068669527897 0.07 0.14377682403433475
1 0.886 0.40879828326180256 0.124 0.18240343347639484
1 0.723 0.398068669527897 0.102 0.1609442060085837
1 0.541 0.35085836909871243 0.094 0.16952789699570817
1 0.428 0.4334763948497854 0.068 0.1072961373390558
1 0.375 0.40236051502145925 0.054 0.1351931330472103
1 0.976 0.3927038626609442 0.044 0.17167381974248927

The `data.yaml` file contains configuration values used by the model to locate images and map class names to class_id's.

train: ../train/images
val: ../valid/images

nc: 3
names: ['head', 'helmet', 'person']