CNN-for-single-channel-speech-enhancement icon indicating copy to clipboard operation
CNN-for-single-channel-speech-enhancement copied to clipboard

Published 20 hours ago • verified publisher icon zhr1201

why validation_samples = 848824?

Open deeplearningzhy opened this issue 6 years ago • 3 comments

Thanks for your sharing,but I am confused that why validation_samples = 848824? I download the TIMIT data set, for train set are 4680 waves,for test set are 1620 waves,for Nonspeech are 100 types of noise,could you please help me to figure out why validation samples are 848824? Thank you very much!

deeplearningzhy avatar Dec 04 '18 13:12 deeplearningzhy

@deeplearningzhy do you deal with the problem? I also confused about that.

ffxz avatar Jan 04 '19 09:01 ffxz

Sorry about the delay, I just used the number of validation samples in my validation set, of course you can set the number to a new value once you set up your own validation set

zhr1201 avatar Jan 04 '19 09:01 zhr1201

@zhr1201 the number of validation_samples is random? I can set it without calculating?

ffxz avatar Jan 04 '19 09:01 ffxz