Chris Novello

Tried the resize code posted above for 128x128 and finding that the Discriminator flatlines to 0.0000 around size 10. Anything I might be missing? Changed the discriminator & generator code...

+1 same on this one!

Exciting thread here! fwiw: I re-recorded one of the entries from VCTK in my own voice, and got [decent babble results](https://soundcloud.com/paperkettle/wavenet-babble-test-trained-a-neural-network-to-speak-with-my-voice). I used the VCTK txt and recording style with...

following up... > Kevin Lee > i had an idea just now about what the issue probably is. > https://github.com/donmccurdy/aframe-physics-system/blob/6cb498263f0ac6401b5784bce24a5b827e3e7ffc/src/components/body/ammo-body.js#L380 > > there's this check for the parent of the...

+1 having the same problem! test.lua works for me when I use the supplied model but then not with my own models. It appears I'm successfully training? train.lua outputs checkpoint...

got it working by using the johnson model rather than pyramid. seems like maybe the pyramid doesn't match up with the test.lua code? will look into this more but any...

Good call on the image size - now the code executes and outputs images (tho some of my early models just output solid black images). Is it that the models...