Closed xizero00 closed 7 years ago
Yes, some detail is lost by rounding to an integer when predicting at a lower output resolution. We address this with a sort of "hacky" solution when postprocessing found here: https://github.com/anewell/pose-hg-train/blob/master/src/util/pose.lua#L85 This provides sufficient localization precision for our purposes.
@anewell Thank you very much.
Hi newell:
I notice that transform function causes the inaccuracy
the type of return value is int this will introduce the inaccuracy.
You can find that the variable diff's norm is very big in the following testing code. That's a big problem.
In the train.lua, you use the following code to overcome this problem when it's validating or testing Am I right?