recall calculation

[XiaodanLi001]

https://github.com/PkuRainBow/Hard-Aware-Deeply-Cascaded-Embedding_release/blob/e2f5462aab0ed1c9d6a85503bf7d42eac632d5b1/src_code/test_deep_fashion.py#L29

Hi, I was wondering how you calculated the recall. In fact, in your code, if you query K images and once you get one correct, and this is a 100% recall in your code. But as far as I know, recall@K means if you have N images in the gallery corresponding to the anchor and you find M images correct in these K images, the recall@K=M/N and precision=N/K. But in your code, once M is not zero, your recall got to be 1. Can you explain this for me? I'm really confused. Thank you a lot.