Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on GradientFlow: Training ImageNet in 1.5 Minutes on 512 GPUs. Parent comment
I work in the field, and the way it works is like this, in this order:
1) Someone works out how to do something
2) Someone works out how to improve the accuracy
3) The accuracy maxes out
4) People improve training efficiency.
We see this over and over again. Take a look at the FastAI results on ImageNet training speed for example.
There are no comments on this comment yet.
I work in the field, and the way it works is like this, in this order:
1) Someone works out how to do something
2) Someone works out how to improve the accuracy
3) The accuracy maxes out
4) People improve training efficiency.
We see this over and over again. Take a look at the FastAI results on ImageNet training speed for example.