Visual Intelligence Summit: Oct 22 in San Francisco Get your ticket

Scaled-YOLOv4 TXT

Scaled-YOLOv4 uses a variant on the Darknet TXT format with an additional data.yaml configuration file.

Overview

Scaled-YOLOv4 was released in December 2020 and improves on YOLOv4 and YOLOv5 to achieve state of the art performance on the COCO dataset. It uses the same format as YOLOv5, which is a modified version of YOLO Darknet's TXT annotation format, but we've split it out into a separate download format for clarity.

We have a how to train Scaled-YOLOv4 tutorial available that consumes this format and provide many public datasets in Scaled-YOLOv4 format.

Format Description

Below, learn the structure of Scaled-YOLOv4 TXT.

001.txt
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
data.yaml
train: ../train/images
val: ../valid/images

nc: 3
names: ['head', 'helmet', 'person']
Start where you are

Speak with an AI expert

Our team will help you start solving business problems on the first call.

  • Solution architecting
  • Live demonstration
  • Pricing and specifications
  • Feasibility assessment

Over 16,000 organizations build with Roboflow.

Rivian
Pella
Chobani
USG Corporation
BNSF Railway
American Woodmark
Outcomes
Patrick Industries
Peer Robotics