I have a question regarding the evaluation of Openimages. I noticed that in your open-source Annotationo file, some validation categories have only 1~2 samples , making it difficult to accurately calculate the mAP. I was wondering if you have taken a subset for calculation, and if it would be convenient for you to open-source this?
I will be waiting for your answers :)
Best wishes!
I have a question regarding the evaluation of Openimages. I noticed that in your open-source Annotationo file, some validation categories have only 1~2 samples , making it difficult to accurately calculate the mAP. I was wondering if you have taken a subset for calculation, and if it would be convenient for you to open-source this?
I will be waiting for your answers :)
Best wishes!