SRN-Deblur icon indicating copy to clipboard operation
SRN-Deblur copied to clipboard

Published 20 hours ago • verified publisher icon jiangsutx

run time and loss

Open noranali opened this issue 3 years ago • 2 comments

thank you for your code , what is the reason of that the loss is different at every time i restart the run time and run the train ? can you help me please

noranali avatar Jun 29 '22 21:06 noranali

The training process include random process, e.g. random data sequence order, random initialization etc. If you want deterministic process, you need to fix random seed for python random module, numpy random module and tensorflow random seed.

jiangsutx avatar Jun 30 '22 02:06 jiangsutx

thank you for your replay i have read your paper and i found that the code converge at 4000 epochs but colab will be disconnected at 180 epochs . i want to use the final weight as initial . can you help me please ?

noranali avatar Jul 03 '22 16:07 noranali