Learning it cause I believe it will be valuable in the future.

Sure python is just the glue, and we won’t actually see much difference in terms of speed. But executing models as simple binaries without dependencies is more valuable than people think for scalability.

Some days yes, others I’m so busy I forget and realize the next day

Started with Keras, wtf is this. Moved to PyTorch, oh this is so nice.

Don’t plan to ever come back.

No magic hyperparameter is going to do the trick here.

Your only real option is to try to find a dataset that approaches the real distribution, or to try to somehow augment your data to make it look more like it (although this is very challenging to do without introducing even more bias).