Hacker News Reader

Even after the edit, it's a bit confusing in that, without looking at the table, you get the impression that FP16 is slower than FP32.

Perhaps it has been edited. Now the table contains the following title "Training performance in images processed per second".

A "Higher is better" might still be interesting although redundant.

Even after being edited, it's still wrong. It shows the significantly lower Inception4 performance as a "40% speedup" instead of 40% of baseline images/sec.

"Training performance in images processed per second"?

Do you mean this table which has a caption over it that reads "Training performance in images processed per second" ?? Looks pretty self-explanatory.