convolutional-pose-machines-release icon indicating copy to clipboard operation
convolutional-pose-machines-release copied to clipboard

Published 20 hours ago • verified publisher icon shihenw

high learning rate in later stages

Open coldgemini opened this issue 7 years ago • 1 comments

Hi, why did you use much higher (4X) learning rate from 2 stages and leave only the first stage a small learning rate? If it's kind of a fine tune strategy, why did you not just freeze the first stage? Is it due to some empirical results?

Thank you a lot.

coldgemini avatar Dec 08 '17 08:12 coldgemini

have you download the pretrained model？can you share it with me. because the download site cannot open.thank you very much! [email protected]

1Rookiechang avatar May 17 '18 08:05 1Rookiechang