How do I test a custom image with annotations on a trained YOLO V5 model, so that I can get precision, recall and AP of model from the custom image?

Question

When I finished training the YOLO V5 model, evaluation metrics such as precision, recall, and AP (average precision) of the model on the validation data were shown. Is it possible to view those evaluation metrics from a trained model against a new images? (note: the new image has its annotation file)

Sorry if this is a dumb question. Thanks!

Mikel B · Answer

To evaluate on you existing data:

python val.py --weights yolov5s.pt --data your_dataset.yaml --img 640

To evaluate on new data:

python val.py --weights yolov5s.pt --data your_new_dataset.yaml --img 640

How do I test a custom image with annotations on a trained YOLO V5 model, so that I can get precision, recall and AP of model from the custom image?

1 Answers