How to plot output labels from model.val()

[hamedgorji]

Hello everyone,

I utilized the command metrics = model.val(data="Data/data-test.yaml", split='test', save_txt=True) and it created a "labels" folder. Is there an existing command to plot and save all the labels along with their corresponding images, or do I need to write custom code for this?

Thanks

[pderrenger]

@hamedgorji hello! 😊

After running model.val() with save_txt=True, the labels are saved in a "labels" folder in a YOLO format, which is great for further analysis but not directly for visualization.

To visualize and save the labels on the corresponding images, you can use the Predict mode with the save=True argument. This will run inference on your dataset and save the images with the predictions drawn on them. Here's an example of how you can do this:

from ultralytics import YOLO

# Load your trained model
model = YOLO('path/to/your/model.pt')

# Perform prediction on your test dataset and save the images
results = model.predict(source='path/to/your/test/images', save=True)

This will save the images with the predictions in the runs/detect/exp directory by default. You can also specify the project and name parameters to save the results in a custom directory.

I hope this helps! If you have any more questions, feel free to ask. Happy coding! 🚀