How to modify this code to enable compression of 16Bit Images

[vivekgr92]

I am running into a seg fault error when I try to compress a 16 Bit Image. The problem is in Arithmetic Coding. Any help is appreciated

[fab-jul]

That’s not gonna work, the model is trained for 8bit and thus produces probability distributions for that. You would need to:

• change the model to predict a probability for 16bits,
• retrain overall unlikely to work though, as with 16bit you have 65k values per subpixel, and this approach here won’t scale to that.