Question about training

[MarvelousV]

❔Question

Hi, I am trying to train images with image size 960x540 and validate the weights through a different image size 1920x1080, could you please tell me what I should to do for paramters "img-size" to make it happen? Is it something like "--img-size [640, 1080]"? Thanks in advance.

Additional context

[github-actions[bot]]

Hello @MarvelousV, thank you for your interest in our work! Ultralytics has open-sourced YOLOv5 at https://github.com/ultralytics/yolov5, featuring faster, lighter and more accurate object detection. YOLOv5 is recommended for all new projects.

To continue with this repo, please visit our Custom Training Tutorial to get started, and see our Google Colab Notebook, Docker Image, and GCP Quickstart Guide for example environments.

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 model or data training question, please note that Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

[glenn-jocher]

python train.py --img 960 1920

[glenn-jocher]

@joel5638 --img 512 288 would train at 512 and test at 288

[glenn-jocher]

@joel5638 you can use --img 512 --rect to omit mosaic, image will be 512 on long side and minimum padded on short side.

[glenn-jocher]

@joel5638 --rect does rectangular training. See https://github.com/ultralytics/yolov3/issues/232

[joel5638]

@glenn-jocher Hi Glenn, how do we change the aspect ratio to 16:9 for training?

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[glenn-jocher]

@joel5638 hi there! To train with a 16:9 aspect ratio, you can set the --img-size parameter to any resolution that maintains that ratio, such as 1280 720 for a 720p resolution. The training will automatically adjust the images to fit this aspect ratio with padding as needed. Happy training! 😊👍