Hajo Nils Krabbenhöft

Requiring torchaudio

Send and receive windows are how large the buffers are for outgoing and incoming packets. `sndwnd` limits how many packets will be send out until things pause for the next...

PDF text extraction is quite difficult, because one first has to kind of render the PDF to get the positions of all the glyphs and then attempt to reconstruct the...

https://www.arxiv-vanity.com/papers/1910.01526/ too

@flozi00 I personally probably have to pass on releasing an open-source T-T model due to a non-compete covering a closed-source T-T which I built. That said, the last time I...

@YooSungHyun when you have a dataset of audio, you can use a pre-trained wav2vec2 to generate logits for every timestep. Normally, you would then resolve those logits into text using...

http://docs.chainer.org/en/stable/_modules/chainer/links/connection/convolution_2d.html#Convolution2D `wscale` is only used for the initializer. So this `w` is the scale used for initializing the weights with gaussian noise. So w is used only during initialization and...

I think the noise that you've posted as picture 2 is caused from the network having an output that is so strong that it exceeds the (0,255) color range. The...

And for your noise type 1, I believe that this is the color channels interfering with each other, i.e. a -255,255 in the red channel could cancel out a 255,-255...

For type 1 I meant this commit: https://github.com/yusuketomoto/chainer-fast-neuralstyle/commit/528f8fb4dc4f1a93af29d583fe75acf6de182c44 but sadly in my tests, it does remove the dots and instead replaces it with diagonal lines. For the noise type 2,...