Remove unnecessary parameter

Author: Leo gautheron

ot/da.py

@@ -11,7 +11,7 @@
 from .optim import gcg
 
 
-def sinkhorn_lpl1_mm(a,labels_a, b, M, reg, eta=0.1,numItermax = 10,numInnerItermax = 200,stopInnerThr=1e-9,unlabelledValue=-99,verbose=False,log=False):
+def sinkhorn_lpl1_mm(a,labels_a, b, M, reg, eta=0.1,numItermax = 10,numInnerItermax = 200,stopInnerThr=1e-9,verbose=False,log=False):
     """
     Solve the entropic regularization optimal transport problem with nonconvex group lasso regularization
 
@@ -55,8 +55,6 @@ def sinkhorn_lpl1_mm(a,labels_a, b, M, reg, eta=0.1,numItermax = 10,numInnerIter
         Max number of iterations (inner sinkhorn solver)
     stopInnerThr : float, optional
         Stop threshold on error (inner sinkhorn solver) (>0)
-    unlabelledValue : int, optional
-        this value in array labels_a means this is an unlabelled example
     verbose : bool, optional
         Print information along iterations
     log : bool, optional
@@ -84,41 +82,28 @@ def sinkhorn_lpl1_mm(a,labels_a, b, M, reg, eta=0.1,numItermax = 10,numInnerIter
     ot.optim.cg : General regularized OT
 
     """
-    p=0.5
+    p = 0.5
     epsilon = 1e-3
 
-    # init data
-    Nini = len(a)
-    Nfin = len(b)
-
     indices_labels = []
     classes = np.unique(labels_a)
     for c in classes:
         idxc, = np.where(labels_a == c)
         indices_labels.append(idxc)
 
-    W=np.zeros(M.shape)
+    W = np.zeros(M.shape)
 
     for cpt in range(numItermax):
         Mreg = M + eta*W
-        transp=sinkhorn(a,b,Mreg,reg,numItermax=numInnerItermax, stopThr=stopInnerThr)
-        # the transport has been computed. Check if classes are really separated
-        W = np.ones((Nini,Nfin))
-        all_majs = []
-        idx_unlabelled = -1
+        transp = sinkhorn(a, b, Mreg, reg, numItermax=numInnerItermax,
+                          stopThr=stopInnerThr)
+        # the transport has been computed. Check if classes are really
+        # separated
+        W = np.ones(M.shape)
         for (i, c) in enumerate(classes):
-            if c != unlabelledValue:
-                majs = np.sum(transp[indices_labels[i]], axis=0)
-                majs = p*((majs+epsilon)**(p-1))
-                W[indices_labels[i]] = majs
-                all_majs.append(majs)
-            else:
-                idx_unlabelled = i
-
-        # now we majorize the unlabelled (if there are any) by the min of
-        # the majorizations. do it only for unlabbled data
-        if idx_unlabelled != -1:
-            W[indices_labels[idx_unlabelled]] = np.min(all_majs, axis=0)
+            majs = np.sum(transp[indices_labels[i]], axis=0)
+            majs = p*((majs+epsilon)**(p-1))
+            W[indices_labels[i]] = majs
 
     return transp
 

ot/gpu/da.py

@@ -69,11 +69,9 @@ def pairwiseEuclideanGPU(a, b, returnAsGPU=False, squared=False):
 
 def sinkhorn_lpl1_mm(a, labels_a, b, M_GPU, reg, eta=0.1, numItermax=10,
                      numInnerItermax=200, stopInnerThr=1e-9,
-                     unlabelledValue=-99, verbose=False, log=False):
+                     verbose=False, log=False):
     p = 0.5
     epsilon = 1e-3
-
-    # init data
     Nfin = len(b)
 
     indices_labels = []
@@ -94,37 +92,18 @@ def sinkhorn_lpl1_mm(a, labels_a, b, M_GPU, reg, eta=0.1, numItermax=10,
         # separated
         W_GPU.assign(1)
         W_GPU = W_GPU.transpose()
-        all_majs_GPU = []
-        idx_unlabelled = -1
         for (i, c) in enumerate(classes):
-            if c != unlabelledValue:
-                (_, nbRow) = indices_labels[i].shape
-                tmpC_GPU = cudamat.empty((Nfin, nbRow)).assign(0)
-                transp_GPU.transpose().select_columns(indices_labels[i],
-                                                      tmpC_GPU)
-                majs_GPU = tmpC_GPU.sum(axis=1).add(epsilon)
-                cudamat.pow(majs_GPU, (p-1))
-                majs_GPU.mult(p)
-                all_majs_GPU.append(majs_GPU)
-
-                tmpC_GPU.assign(0)
-                tmpC_GPU.add_col_vec(majs_GPU)
-                W_GPU.set_selected_columns(indices_labels[i], tmpC_GPU)
-            else:
-                idx_unlabelled = i
-
-        # now we majorize the unlabelled (if there are any) by the min of
-        # the majorizations. do it only for unlabbled data
-        if idx_unlabelled != -1:
-            all_majs = np.array([m_GPU.asarray() for m_GPU in all_majs_GPU])
-            minMaj_GPU = (cudamat.CUDAMatrix(all_majs).min(axis=0)
-                          .transpose())
-            (_, nbRow) = indices_labels[idx_unlabelled].shape
+            (_, nbRow) = indices_labels[i].shape
             tmpC_GPU = cudamat.empty((Nfin, nbRow)).assign(0)
+            transp_GPU.transpose().select_columns(indices_labels[i], tmpC_GPU)
+            majs_GPU = tmpC_GPU.sum(axis=1).add(epsilon)
+            cudamat.pow(majs_GPU, (p-1))
+            majs_GPU.mult(p)
+
+            tmpC_GPU.assign(0)
+            tmpC_GPU.add_col_vec(majs_GPU)
+            W_GPU.set_selected_columns(indices_labels[i], tmpC_GPU)
 
-            tmpC_GPU.add_col_vec(minMaj_GPU)
-            W_GPU.set_selected_columns(indices_labels[idx_unlabelled],
-                                       tmpC_GPU)
         W_GPU = W_GPU.transpose()
 
     return transp_GPU.asarray()