Cristian Bodnar

Results 4 issues of Cristian Bodnar

I see that this implementation (and all the others I've seen online) use a batch size of 16. The paper also mentions this as the default batch size they tried....

It would be useful to have a typecheck on the return value at compile time. Right now if I have ` func smth(a int) int { //some code here }...

Would it be possible to write an algorithm like NEAT which evolves the topology of a neural network in Fold? From my understanding, Fold does not support dynamic computation graphs...

### Zarr version v3.1.3 ### Numcodecs version 0.16.3 ### Python Version 3.12 ### Operating System Linux ### Installation uv ### Description Using pcodec with zarr results in ``` zarr.errors.UnknownCodecError: Unknown...

bug