Move to lib folder and fix kmeans

2 files changed, 130 insertions, 0 deletions

diff --git a/lib/kmean.py b/lib/kmean.py
new file mode 100644
index 0000000..2e34702
--- /dev/null
+++ b/lib/kmean.py
@@ -0,0 +1,48 @@
+import numpy as np
+from sklearn.cluster import KMeans
+
+def create_kmean_clusters(feature_vectors, labels, gallery_idx, camId):
+    gallery = ([],[])
+    gallerylab = ([],[])
+    for i in range(gallery_idx.size):
+        cam = camId[gallery_idx[i]] - 1
+        gallery[cam].append(feature_vectors[gallery_idx[i]])
+        gallerylab[cam].append(labels[gallery_idx[i]])
+            
+    
+    train = np.array(gallery)
+    tlabel = np.array(gallerylab)
+
+    km_train_data = []
+    km_idx = []
+    km_labels = []
+
+    for i in range(2):
+        km_train_data.append(KMeans(n_clusters=int(np.max(labels)),random_state=0).fit(train[i]))
+        km_idx.append(km_train_data[i].labels_)
+        km_labels.append(range(np.max(labels)))
+        for j in range(np.max(labels)):
+            class_vote = np.zeros(np.max(labels))
+            for q in range(km_idx[i].size):
+                if km_idx[i][q]==j:
+                    class_vote[int(tlabel[i][q])-1] += 1
+            km_labels[i][j] = np.argmax(class_vote) + 1
+        
+    #MERGE CLUSTERS
+    cl = []
+    cllab = []
+    clustercam = []
+    for i in range(2):
+        clustercam.append(np.add(np.ones(len(km_labels[i])), i))
+        print(len(km_labels[i]))
+        for j in range(len(km_labels[i])):
+            cl.append(km_train_data[i].cluster_centers_[j])
+            cllab.append(km_labels[i][j])
+
+    train_data = np.array(cl)
+    print(train_data.shape)
+    train_label = np.array(cllab)
+    print(train_label.shape)
+    train_cam = np.array([clustercam[i] for i in range(2)]).reshape(train_label.shape[0])
+    print(train_cam.shape)
+    return train_data, train_label, train_cam
diff --git a/lib/rerank.py b/lib/rerank.py
new file mode 100644
index 0000000..6b20f53
--- /dev/null
+++ b/lib/rerank.py
@@ -0,0 +1,82 @@
+from scipy.spatial.distance import cdist
+import numpy as np
+
+def re_ranking(probFea,galFea,k1,k2,lambda_value, MemorySave = False, Minibatch = 2000):
+
+    query_num = probFea.shape[0]
+    all_num = query_num + galFea.shape[0]    
+    feat = np.append(probFea,galFea,axis = 0)
+    feat = feat.astype(np.float16)
+    print('computing original distance')
+    if MemorySave:
+        original_dist = np.zeros(shape = [all_num,all_num],dtype = np.float16)
+        i = 0
+        while True:
+            it = i + Minibatch
+            if it < np.shape(feat)[0]:
+                original_dist[i:it,] = np.power(cdist(feat[i:it,],feat),2).astype(np.float16)
+            else:
+                original_dist[i:,:] = np.power(cdist(feat[i:,],feat),2).astype(np.float16)
+                break
+            i = it
+    else:
+        original_dist = cdist(feat,feat).astype(np.float16)  
+        original_dist = np.power(original_dist,2).astype(np.float16)
+    del feat    
+    gallery_num = original_dist.shape[0]
+    original_dist = np.transpose(original_dist/np.max(original_dist,axis = 0))
+    V = np.zeros_like(original_dist).astype(np.float16)
+    initial_rank = np.argsort(original_dist).astype(np.int32)
+
+    
+    print('starting re_ranking')
+    for i in range(all_num):
+        # k-reciprocal neighbors
+        forward_k_neigh_index = initial_rank[i,:k1+1]
+        backward_k_neigh_index = initial_rank[forward_k_neigh_index,:k1+1]
+        fi = np.where(backward_k_neigh_index==i)[0]
+        k_reciprocal_index = forward_k_neigh_index[fi]
+        k_reciprocal_expansion_index = k_reciprocal_index
+        for j in range(len(k_reciprocal_index)):
+            candidate = k_reciprocal_index[j]
+            candidate_forward_k_neigh_index = initial_rank[candidate,:int(np.around(k1/2))+1]
+            candidate_backward_k_neigh_index = initial_rank[candidate_forward_k_neigh_index,:int(np.around(k1/2))+1]
+            fi_candidate = np.where(candidate_backward_k_neigh_index == candidate)[0]
+            candidate_k_reciprocal_index = candidate_forward_k_neigh_index[fi_candidate]
+            if len(np.intersect1d(candidate_k_reciprocal_index,k_reciprocal_index))> 2/3*len(candidate_k_reciprocal_index):
+                k_reciprocal_expansion_index = np.append(k_reciprocal_expansion_index,candidate_k_reciprocal_index)
+            
+        k_reciprocal_expansion_index = np.unique(k_reciprocal_expansion_index)
+        weight = np.exp(-original_dist[i,k_reciprocal_expansion_index])
+        V[i,k_reciprocal_expansion_index] = weight/np.sum(weight)
+    original_dist = original_dist[:query_num,]    
+    if k2 != 1:
+        V_qe = np.zeros_like(V,dtype=np.float16)
+        for i in range(all_num):
+            V_qe[i,:] = np.mean(V[initial_rank[i,:k2],:],axis=0)
+        V = V_qe
+        del V_qe
+    del initial_rank
+    invIndex = []
+    for i in range(gallery_num):
+        invIndex.append(np.where(V[:,i] != 0)[0])
+    
+    jaccard_dist = np.zeros_like(original_dist,dtype = np.float16)
+
+    for i in range(query_num):
+        temp_min = np.zeros(shape=[1,gallery_num],dtype=np.float16)
+        indNonZero = np.where(V[i,:] != 0)[0]
+        indImages = []
+        indImages = [invIndex[ind] for ind in indNonZero]
+        for j in range(len(indNonZero)):
+            temp_min[0,indImages[j]] = temp_min[0,indImages[j]]+ np.minimum(V[i,indNonZero[j]],V[indImages[j],indNonZero[j]])
+        jaccard_dist[i] = 1-temp_min/(2-temp_min)
+    
+    final_dist = jaccard_dist*(1-lambda_value) + original_dist*lambda_value
+    del original_dist
+    del V
+    del jaccard_dist
+    final_dist = final_dist[:query_num,query_num:]
+        
+    return final_dist
+