CNHNLP

@fyangneil Thank you for your answer. I'm confused about the meaning of maxDist.Can you explain the maxDist how to calculate.Or give some papers to explain it? Thanks a lot.

@fyangneil I am sorry to disturb you again.I use your train.caffemodel to evaluate your testcrop data,but the result is not good.The ODS is 0.502.OIS is 0.519 and AP is just...

@fyangneil I have used your evaltools to get the same result in your paper.Thank you very much!

@YFZh 在计算的时候，图片中的每个像素点也可以看作一个batch

I have the same question. Have you solved it?

> > I have the same question. Have you solved it? > > Not yet I think maybe cuda version. My cuda10.0 is failed

You can increase the learning rate.I get the loss 500+ by using the default learning rate 0.01.But the result is better if you set the learning rate 0.5

I'm also confused.I think caffe doesn't increase the number of images. Have you got some explanations?

@hoopool @quahez @xubo0321 I also find the same question, have you finished? can you give me some suggestion? thank you