search

LiQiufu / WaveCNet

the code for WaveCNet
123 stars 16 forks source link

No IDWT layer used in main procedure #4

Open momo1986 opened 3 years ago

momo1986 commented 3 years ago

Thanks a lot for sharing. Looks like in the paper, there are three steps: 1) Do DWT operation 2) Directly forward low-frequency elements, and filter high-frequency elements. 3) IDWT to reconstruct the signal.

My question is how to combine the IDWT operation with the end-to-end CNNs?

Thanks & Regards! Momo

LiQiufu commented 3 years ago

I applied DWT and IDWT in DeepLab or U-Net for image segmentation. https://github.com/LiQiufu/WaveSNet

momo1986 commented 3 years ago

@LiQiufu Li, thanks.

Therefore, for classification task, only dwt module can work fine. Is my understanding wrong?

Also very grateful to your reply.

Regards! Momo

LiQiufu commented 3 years ago

IDWT is for data up-sampling, while no up-sampling operation is used in the deep networks for image classification. So, I don't think it is a good idea to do IDWT in classification.

momo1986 commented 3 years ago

@LiQiufu , I am grateful to your nice reply.

Hopes you are all good.

Best Regards! Momo