Robert Giaquinto

Just a warning about using Adam with CLR: I wouldn’t do the LR range test with Adam, the momentum will throw off the results and not give the best max...

@mdhimes That's a good point, there isn't any reason the base LR would differ too significantly when testing with Adam. I've had bad results running my LR Range test with...

I was also surprised accuracy is often shown in the LR range test plots. Accuracy isn’t a proper scoring rule, validation loss should be much more stable and informative.

I haven't come up with a way to plot samples from all of the density estimation models yet. Right now the density estimation models mainly work on tabular data from...