Viet Hoang

STL10 with default hyper-params experients yields the similar results (90.8203% with batch size 256 yet 91.7969% with batch size 128)

Thank you for your instant help. I know that the results of SegNet and MTAN are similar but can I ask how big the gap between their learning curves are?

Thank you for your responses, I'm closing the issue now

Hey @ngocbh, could you please show me how to run this project?

dcm @ngocbh

thanks @ngocbh

hi @ngocbh

@chiennv2000, @chaupham1709, @hsgser

im mồm đi Chiến, diễn ít thôi

Hi, thank you for your response. I got it, so maybe it denied since I do not have the access rights which you do have. Would you mind copying it...