1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
|
# -*- coding: utf-8 -*-
"""
Solvers for the original linear program OT problem
"""
# Author: Remi Flamary <remi.flamary@unice.fr>
#
# License: MIT License
import numpy as np
# import compiled emd
from .emd_wrap import emd_c, emd2_c
from ..utils import parmap
import multiprocessing
def emd(a, b, M, numItermax=10000):
"""Solves the Earth Movers distance problem and returns the OT matrix
.. math::
\gamma = arg\min_\gamma <\gamma,M>_F
s.t. \gamma 1 = a
\gamma^T 1= b
\gamma\geq 0
where :
- M is the metric cost matrix
- a and b are the sample weights
Uses the algorithm proposed in [1]_
Parameters
----------
a : (ns,) ndarray, float64
Source histogram (uniform weigth if empty list)
b : (nt,) ndarray, float64
Target histogram (uniform weigth if empty list)
M : (ns,nt) ndarray, float64
loss matrix
numItermax : int
Maximum number of iterations made by the LP solver.
Returns
-------
gamma: (ns x nt) ndarray
Optimal transportation matrix for the given parameters
Examples
--------
Simple example with obvious solution. The function emd accepts lists and
perform automatic conversion to numpy arrays
>>> import ot
>>> a=[.5,.5]
>>> b=[.5,.5]
>>> M=[[0.,1.],[1.,0.]]
>>> ot.emd(a,b,M)
array([[ 0.5, 0. ],
[ 0. , 0.5]])
References
----------
.. [1] Bonneel, N., Van De Panne, M., Paris, S., & Heidrich, W.
(2011, December). Displacement interpolation using Lagrangian mass
transport. In ACM Transactions on Graphics (TOG) (Vol. 30, No. 6, p.
158). ACM.
See Also
--------
ot.bregman.sinkhorn : Entropic regularized OT
ot.optim.cg : General regularized OT"""
a = np.asarray(a, dtype=np.float64)
b = np.asarray(b, dtype=np.float64)
M = np.asarray(M, dtype=np.float64)
# if empty array given then use unifor distributions
if len(a) == 0:
a = np.ones((M.shape[0], ), dtype=np.float64)/M.shape[0]
if len(b) == 0:
b = np.ones((M.shape[1], ), dtype=np.float64)/M.shape[1]
return emd_c(a, b, M, numItermax)
def emd2(a, b, M, numItermax=10000, processes=multiprocessing.cpu_count()):
"""Solves the Earth Movers distance problem and returns the loss
.. math::
\gamma = arg\min_\gamma <\gamma,M>_F
s.t. \gamma 1 = a
\gamma^T 1= b
\gamma\geq 0
where :
- M is the metric cost matrix
- a and b are the sample weights
Uses the algorithm proposed in [1]_
Parameters
----------
a : (ns,) ndarray, float64
Source histogram (uniform weigth if empty list)
b : (nt,) ndarray, float64
Target histogram (uniform weigth if empty list)
M : (ns,nt) ndarray, float64
loss matrix
numItermax : int
Maximum number of iterations made by the LP solver.
Returns
-------
gamma: (ns x nt) ndarray
Optimal transportation matrix for the given parameters
Examples
--------
Simple example with obvious solution. The function emd accepts lists and
perform automatic conversion to numpy arrays
>>> import ot
>>> a=[.5,.5]
>>> b=[.5,.5]
>>> M=[[0.,1.],[1.,0.]]
>>> ot.emd2(a,b,M)
0.0
References
----------
.. [1] Bonneel, N., Van De Panne, M., Paris, S., & Heidrich, W.
(2011, December). Displacement interpolation using Lagrangian mass
transport. In ACM Transactions on Graphics (TOG) (Vol. 30, No. 6, p.
158). ACM.
See Also
--------
ot.bregman.sinkhorn : Entropic regularized OT
ot.optim.cg : General regularized OT"""
a = np.asarray(a, dtype=np.float64)
b = np.asarray(b, dtype=np.float64)
M = np.asarray(M, dtype=np.float64)
# if empty array given then use unifor distributions
if len(a) == 0:
a = np.ones((M.shape[0], ), dtype=np.float64)/M.shape[0]
if len(b) == 0:
b = np.ones((M.shape[1], ), dtype=np.float64)/M.shape[1]
if len(b.shape)==1:
return emd2_c(a, b, M, numItermax)
else:
nb=b.shape[1]
#res=[emd2_c(a,b[:,i].copy(),M, numItermax) for i in range(nb)]
def f(b):
return emd2_c(a,b,M, numItermax)
res= parmap(f, [b[:,i] for i in range(nb)],processes)
return np.array(res)
|
