Open andrew-wja opened 6 years ago
To compute the deviation we'd have to store individual measurements, while for the mean it's enough to keep cumulative sums - which is exactly what Caffe does. But I suppose it wouldn't hurt to implement a more detailed measurement output... do you think you could do that and submit a pull request?
Anyway, this (and any more advanced statistics) can already be done manually in Python with time.clock()
(just remember that the first run is likely to be slower due to allocations etc.).
I want just to remark that there is no need to store individual measurements, but just cumulative sum of squared value. Dev. = sqrt( <x^2> - <x>^2 )
@IlyaOvodov But to compute the squared value you need to know the mean time, which you don't know until you got all the measurements.
@Noiredd, no. I mean well known way to calculate dispersion in 1 pass. If you have got sequence {x_i} of random values, obvious way to calculate dispersion implies 2 passes: 1)
@IlyaOvodov Yeah, you're right. It would actually be pretty easy to implement.
Issue summary
caffe time
currently prints only the mean across N iterations for all printed statistics. In order to put error bars on graphs using numbers obtained viacaffe time
there is currently only one option: to executecaffe time
multiple times, with -iterations=1. This yields noisy and inaccurate numbers, and gives a pessimistic view of the runtime of inference in Caffe.It should be a relatively straightforward change to also report the standard deviation for all timings -- the data must already exist in order to compute the mean. This would allow researchers to report the variation in inference time correctly, without having to use -iterations=1.
Steps to reproduce
Execute
caffe time
with any trained model and observe printed timings.Your system configuration
N/A