You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When calculating the optimal flow the algorithm is correct but seems like the EMD is a little off from what I would correctly get with flow_matrix * distance_matrix
but instead it is 1.57896825463524 (err=0.002170575465)
Types (distance, arr1, arr2): {dtype} float64
System: Mac OS X, 10.13.4
PIP pyemd: 0.5.1
Seems like too big of an error to be explained by floating point precision. Also, for floating point precision error the calculated flow should be off as well, but that seems to be accurate.
The text was updated successfully, but these errors were encountered:
I'm not sure of the cause, but my guess is that it has to do with the iterative min-cost flow algorithm in the underlying C++ library. Unfortunately I don't have time to look into this right now.
When calculating the optimal flow the algorithm is correct but seems like the EMD is a little off from what I would correctly get with flow_matrix * distance_matrix
Distance matrix:
arr1:
arr2:
The final value should be
but instead it is 1.57896825463524 (err=0.002170575465)
Types (distance, arr1, arr2): {dtype} float64
System: Mac OS X, 10.13.4
PIP pyemd: 0.5.1
Seems like too big of an error to be explained by floating point precision. Also, for floating point precision error the calculated flow should be off as well, but that seems to be accurate.
The text was updated successfully, but these errors were encountered: