Annotation offline tool for yolov5 seg

[rohitdileep]

Search before asking

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

Question

Hi , can anyone recommend offline annotation tools for yolov5 instance segmentation.

Additional

No response

[github-actions[bot]]

👋 Hello @rohitdileep, 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 screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://ultralytics.com or email support@ultralytics.com.

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. 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.

[olibartfast]

Hi I'm using https://github.com/wkentaro/labelme However then you must implement a (python) script to convert from Labelme json to Yolov5 segmentation txt format

[ryouchinsa]

How about combining 2 scripts?

1. Labelme JSON files to a COCO JSON file using labelme2coco.py https://github.com/wkentaro/labelme/blob/main/examples/instance_segmentation/labelme2coco.py

2. A COCO JSON file to YOLO text files using general_json2yolo.py https://github.com/ultralytics/JSON2YOLO/blob/master/general_json2yolo.py

RectLabel is an offline image annotation tool for object detection and segmentation. Although this is not an open source program, with RectLabel you can read/write/export the YOLO segmentation format.

class_index x1 y1 x2 y2 x3 y3 ...
0 0.180027 0.287930 0.181324 0.280698 0.183726 0.270573 ...

[github-actions[bot]]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com/hub
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!

[mughal41]

@ryouchinsa did u find the script for offline annotation? @olibartfast can u please specify which script you use? did u convert lableme annotations to coco and then to yolov5 format?

[olibartfast]

I did write myself a script to convert from txt yolo coordinates to json labelme format and backwards

[Addoxx]

Hi @olibartfast, I am trying to convert Yolo txt format to labelme JSON format but all the polygon values are normalized in Yolo txt format, and my segmentation masks end up as a small bunch of dots. How did you manage to invert the normalization?

Looking forward to your reply.

Regards, Adhok

[glenn-jocher]

Hi @Addoxx, when converting YOLO txt format to Labelme JSON format, you need to de-normalize the polygon coordinates to match the original image size.

To invert the normalization, you can multiply the normalized polygon coordinates by the width and height of the image. This will bring the coordinates back to the original scale.

Here's some sample code on how to de-normalize the polygon coordinates:

# Assuming you have the normalized polygon coordinates in the variable 'polygon'
width, height = image_width, image_height  # Replace with the actual image width and height

denormalized_polygon = []
for x, y in polygon:
    denormalized_x = x * width
    denormalized_y = y * height
    denormalized_polygon.append([denormalized_x, denormalized_y])

# Use 'denormalized_polygon' in your conversion from YOLO to Labelme format

Make sure to replace 'image_width' and 'image_height' with the actual width and height of your image.

I hope this helps! Let me know if you have any further questions.

Regards, Glenn Jocher

[Addoxx]

Glenn,

I was able to invert the normalization and project the coordinates on the original scale. Thanks a lot for your input!

Cheers

[glenn-jocher]

@Addoxx glad to hear that you were able to successfully invert the normalization and project the coordinates on the original scale! You're welcome and I'm happy that I could assist you.

If you have any more questions or need further assistance, feel free to ask. Cheers and happy coding!