qubvel-org / segmentation_models.pytorch

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
https://smp.readthedocs.io/
MIT License
9.72k stars 1.68k forks source link

How can I get the final evaluation metrics #901

Open wangluoWSG opened 3 months ago

wangluoWSG commented 3 months ago

Hello! How can I obtain the final evaluation metrics, such as accuracy (ACC), recall, F1-score, etc., after the testing of a model has been completed?

qubvel commented 3 months ago

Hi, not sure I got the question, you can look at binary segmentation example in examples folder to see how to compute metrics.