Tony Robinson

Thank you very much for your prompt reply and fix. I am running again now and will come back to you as soon as I have itteration 300000 complete.

I've now got results at iteration 300,000 which I'll atttach below. The dynamic range of the colours isn't my main concern, it's the non-physical distortions that make these images stand...

Well, I have to say that I'm impressed by your remote debuggnig skills. My immediate reaction was to think that I wouldn't be so stupid as not to use the...

Thanks for your interest. The error does persist even with a single ticker. What's more it's slow to change between being correct and being wrong. Here is more debug: ```...

If it's deliberate it's a very very strange decision. The step change between 6.2 and 7.4 is great, and I see bigger changes elsewhere. Earlier I believed this didn't show...

Well, the boundary between good and bad data is always in the same place so, in theory, you could make multiple calls to get all the data. I've considered this,...

That would be me. The script worked 100%, it's just what I needed - very many thanks. I like the command line and being able to see exactly what is...

@stefan123t 'can you provide some more detail on how you ran DaFlasher under Linux'? I didn't run DaFlasher under Linux. The work being discussed in this thread is 'Script to...

My opinion is that VQVAE2 achieves it's results with PixelSnail. The main function of VQVAE2 seems to be to reduce the number of things to model with PixelSnail. Fundamentally all...

They look really good to me, better than what I've got (though I did run on 128*128 to match my GPU). Here is one simple suggestion that worked for me. ...