context-encoder icon indicating copy to clipboard operation
context-encoder copied to clipboard

Published 20 hours ago • verified publisher icon pathak22

Questions about test code

Open 2018hello opened this issue 6 years ago • 0 comments

hi 1 I have a question about the loadSize, why should we use 129 not just 128? 2 why should we use overlapPred? 3 I have a image which fineSize is 32*32. If I want to train this fineSize, then I just change new dataset and fineSize in code.? 4 If I want to train my dataset, how should I adjust the parameter to get best results? Thank you so much!

2018hello avatar Jan 26 '19 15:01 2018hello