shijianyuan

Hi. @suzhenghang @soeaver . How do you implement multi-scale traing in Caffe?

Hi, @coolhebei I met the same problem with you . Have you solve it？ could you give me some help?

hello, @mtsakaguchi have you solved the problem? I met the same problem as yours. After trained, the model segment almost every target into person (except background). I have add "class_weighting",...

@episodesky using tensorboard

@foralliance I meet the same problem. have you solve it? I use ImageDataLayer to test voc12-test dataset. but i got a bad result .

@moothes each score is around 0.01-0.04, it's bad. I hadn't shuffle the test set. And i think whether shuffle doesn't matter.

I use ImageDataLayer to test voc12-test, mAP=0.75640

ImageDataLayer is one layer of Caffe to load image to CNN

Hi. Have you address this problem? If you have done, could you tell me?