pranaymanocha / PerceptualAudio

Perceptual Metrics of Audio - perceptually relevant loss function. DPAM and CDPAM

Home Page:https://pixl.cs.princeton.edu/pubs/Manocha_2020_ADP/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Tensorflow 2 compatible

lukewys opened this issue · comments

Hi, thanks very much for your great code and paper. I was wondering if the code provides here is Tensorflow 2 compatible. It seems that the code uses tensorflow.contrib.slim which is not supported in Tensorflow 2 anymore. Perhaps you could note that in readme. Thanks!

Hi,
Thanks for the comments. The repo indeed doesn't support tf2.0. I currently don't have the bandwidth to convert the repo to being, tf2.0 compatible but I guess tf2.0 has dilation operation support inbuilt, so it should not probably take too much time to port the code. However, if anyone else is up for it, I'll be happy to take a look at it.

Thanks!