I train the data, it really use GPU. but when val, it become slow. The interface show calculation mAP. deal with 100 images with several hours. Do you know where the problem is?
Are you sure that you used GPU? it should work for both training and val.
try to check the Makefile and set the following:
GPU=1
CUDNN=1
CUDNN_HALF=1
OPENCV=1
I train the data, it really use GPU. but when val, it become slow. The interface show calculation mAP. deal with 100 images with several hours. Do you know where the problem is?