how to write data cfg file?

[hitbuyi]

trafficstars

Search before asking

• [x] I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

mydata ├── dataSet ├── image ├── label └── label_xml where dataSet includes trainval.txt,val.txt, image is png image, label includes txt lablefiles, how to write data cfg ymal files?

Additional

No response

[UltralyticsAssistant]

👋 Hello @hitbuyi, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide a minimum reproducible example to help us debug it.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our Tips for Best Training Results.

Requirements

Python>=3.8.0 with all requirements.txt installed including PyTorch>=1.8. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training, validation, inference, export and benchmarks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

This is an automated response. An Ultralytics engineer will review your question and assist you soon 😊

[pderrenger]

To create a YAML configuration file for your dataset structure, you'll need to specify the dataset path and split information. Here's an example based on your folder structure:

# mydata.yaml
path: /path/to/mydata  # dataset root dir
train: dataSet/trainval.txt  # path to train images list (relative to 'path')
val: dataSet/val.txt  # path to val images list (relative to 'path')

# Classes
nc: 80  # number of classes
names: ['person', 'bicycle', 'car', ...]  # class names

Make sure your trainval.txt and val.txt files contain relative paths to your images in the image folder, and that your label files in the label folder follow the YOLO format with corresponding filenames to your images.

[hitbuyi]

To create a YAML configuration file for your dataset structure, you'll need to specify the dataset path and split information. Here's an example based on your folder structure:

mydata.yaml

path: /path/to/mydata # dataset root dir train: dataSet/trainval.txt # path to train images list (relative to 'path') val: dataSet/val.txt # path to val images list (relative to 'path')

Classes

nc: 80 # number of classes names: ['person', 'bicycle', 'car', ...] # class names Make sure your trainval.txt and val.txt files contain relative paths to your images in the image folder, and that your label files in the label folder follow the YOLO format with corresponding filenames to your images.

I think it should be /images/ and /labels/, image files should be placed inimagesfolder, and labels should be placed inlabelsfolder

[pderrenger]

You're absolutely right! For YOLOv5 to work properly, your dataset structure should follow the standard convention with images and labels folders. You'll need to rename your image folder to images and your label folder to labels, then update your YAML accordingly:

# mydata.yaml
path: /path/to/mydata  # dataset root dir
train: images/train  # or dataSet/trainval.txt if using txt files
val: images/val      # or dataSet/val.txt if using txt files

# Classes
nc: 80  # number of classes
names: ['person', 'bicycle', 'car', ...]  # class names

This ensures YOLOv5 can automatically find the corresponding label files in the labels folder for each image in the images folder.