An error that may lead to a high precision drop.
samson-wang opened this issue · 1 comments
samson-wang commented
Hi guys,
I have trained a model by multipathnet version frcnn on my own dataset with only one foreground class. Compared to the original frcnn model, which has AP at 0.93 on the same training and validation dataset, the multipath version only get AP around 0.7.
After many debug, I think the problem is that the coordinates preprocess mistakes. I change the corresponding code, then the AP go high to 0.94. I will give more details later.
samson-wang commented
samson-wang@522a894#diff-2ebe969b75ddaebef2a30717b15de628
This trick get the high AP result. At least for faster-rcnn model.