Move to lib folder and fix kmeans

4 files changed, 245 insertions, 62 deletions

diff --git a/evaluate.py b/evaluate.py
new file mode 100755
index 0000000..ace647f
--- /dev/null
+++ b/evaluate.py
@@ -0,0 +1,197 @@
+#!/usr/bin/env python
+# Author: Vasil Zlatanov, Nunzio Pucci
+# EE4 Pattern Recognition coursework
+#
+# usage: part2.py [-h] [-t] [-cm] [-km] [-ma] [-e] [-r] [-ka RERANKA]
+#                [-kb RERANKB] [-v]
+
+import matplotlib.pyplot as plt
+from mpl_toolkits.mplot3d import Axes3D
+import sys
+import random
+import os
+import json
+import scipy.io
+from random import randint
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.neighbors import DistanceMetric
+from sklearn.cluster import KMeans
+from sklearn.decomposition import PCA
+from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.metrics import confusion_matrix
+from sklearn.metrics import accuracy_score
+import argparse
+import numpy as np
+from numpy import genfromtxt
+from numpy import linalg as LA
+from timeit import default_timer as timer
+from scipy.spatial.distance import cdist
+sys.path.append('lib')
+from rerank import re_ranking
+from kmean import create_kmean_clusters
+
+parser = argparse.ArgumentParser()
+parser.add_argument("-t", "--train", help="Use test data instead of query", action='store_true')
+parser.add_argument("-c", "--conf_mat", help="Show visual confusion matrix", action='store_true')
+parser.add_argument("-k", "--kmean", help="Perform Kmeans", action='store_true', default=0)
+parser.add_argument("-m", "--mahalanobis", help="Perform Mahalanobis Distance metric", action='store_true', default=0)
+parser.add_argument("-e", "--euclidean", help="Standard euclidean", action='store_true', default=0)
+parser.add_argument("-r", "--rerank", help="Use k-reciprocal rernaking", action='store_true')
+parser.add_argument("-p", "--reranka", help="Parameter 1 for Rerank", type=int, default = 20)
+parser.add_argument("-q", "--rerankb", help="Parameter 2 for rerank", type=int, default = 6)
+parser.add_argument("-l", "--rerankl", help="Coefficient to combine distances", type=int, default = 0.3)
+parser.add_argument("-n", "--neighbors", help="Number of neighbors", type=int, default = 1)
+parser.add_argument("-v", "--verbose", help="Use verbose output", action='store_true')
+parser.add_argument("-s", "--showrank", help="Save ranklist pic id in a txt file", type=int, default = 0)
+parser.add_argument("-2", "--graphspace", help="Graph space", action='store_true', default=0)
+parser.add_argument("-1", "--normalise", help="Normalized features", action='store_true', default=0)
+parser.add_argument("-M", "--multrank", help="Run for different ranklist sizes equal to M", type=int, default=1)
+parser.add_argument("-C", "--comparison", help="Set to 2 to obtain a comparison of baseline and Improved metric", type=int, default=1)
+parser.add_argument("--data", help="Data folder with features data", default='data')
+
+
+args = parser.parse_args()
+
+def verbose(*text):
+    if args.verbose:
+        print(text)
+
+def draw_results(test_label, pred_label):
+    acc_sc = accuracy_score(test_label, pred_label)
+    cm = confusion_matrix(test_label, pred_label)
+    print('Accuracy: ', acc_sc)
+    if (args.conf_mat):
+        plt.matshow(cm, cmap='Blues')
+        plt.colorbar()
+        plt.ylabel('Actual')
+        plt.xlabel('Predicted')
+        plt.show()
+    return acc_sc
+
+def test_model(gallery_data, probe_data, gallery_label, probe_label, gallery_cam, probe_cam, showfiles_train, showfiles_test, args):
+
+    verbose("probe shape:", probe_data.shape)
+    verbose("gallery shape:", gallery_data.shape)
+
+    if args.rerank:
+        distances = re_ranking(probe_data, gallery_data,
+                               args.reranka ,args.rerankb , 0.3,
+                               MemorySave = False, Minibatch = 2000)
+    else:
+        if args.mahalanobis:
+            # metric = 'jaccard' is also valid
+            distances = cdist(probe_data, gallery_data, 'sqeuclidean')
+        else:
+            distances = cdist(probe_data, gallery_data, 'euclidean')
+
+    ranklist = np.argsort(distances, axis=1)
+
+    test_table = np.arange(1, args.multrank+1)
+    target_pred = np.zeros((args.multrank, ranklist.shape[0]))
+    nsize = args.neighbors
+    if (args.multrank != 1):
+        nsize = test_table[args.multrank-1]
+    nneighbors = np.zeros((ranklist.shape[0],nsize))
+    nnshowrank = (np.zeros((ranklist.shape[0],nsize))).astype(object)
+
+
+    for i in range(args.multrank):
+        if args.multrank!= 1:
+            args.neighbors = test_table[i]
+        for probe_idx in range(probe_data.shape[0]):
+            row = ranklist[probe_idx]
+            n = 0
+            q = 0
+            while (q < args.neighbors):
+                while (probe_cam[probe_idx] == gallery_cam[row[n]] and
+                  probe_label[probe_idx] == gallery_label[row[n]]):
+                    n += 1
+                nneighbors[probe_idx][q] = gallery_label[row[n]]
+                nnshowrank[probe_idx][q] = showfiles_train[row[n]] #
+                q += 1
+                n += 1
+
+            if (args.neighbors) and (probe_label[probe_idx] in nneighbors[probe_idx]):
+                target_pred[i][probe_idx] = probe_label[probe_idx]
+            else:
+                target_pred[i][probe_idx] = nneighbors[probe_idx][0]
+
+
+        if (args.showrank):
+            with open("ranklist.txt", "w") as text_file:
+                text_file.write(np.array2string(nnshowrank[:args.showrank]))
+            with open("query.txt", "w") as text_file:
+                text_file.write(np.array2string(showfiles_test[:args.showrank]))
+
+    if args.graphspace:
+            # Colors for distinct individuals
+            cols = ['#{:06x}'.format(randint(0, 0xffffff)) for i in range(1467)]
+            gallery_label_tmp = np.subtract(gallery_label, 1)
+            pltCol = [cols[int(k)] for k in gallery_label_tmp]
+            fig = plt.figure()
+            ax = fig.add_subplot(111, projection='3d')
+            ax.scatter(gallery_data[:, 0], gallery_data[:, 1], gallery_data[:, 2], marker='o', color=pltCol)
+            plt.show()
+    return target_pred
+
+def main():
+    mat = scipy.io.loadmat(os.path.join(args.data,'cuhk03_new_protocol_config_labeled.mat'))
+    camId = mat['camId']
+    filelist = mat['filelist']
+    labels = mat['labels']
+    gallery_idx = mat['gallery_idx'] - 1
+    query_idx = mat['query_idx'] - 1
+    train_idx = mat['train_idx'] - 1
+    with open(os.path.join(args.data,'feature_data.json'), 'r') as read_file:
+        feature_vectors = np.array(json.load(read_file))
+    if args.train:
+        query_idx = train_idx.reshape(train_idx.shape[0])
+        gallery_idx = train_idx.reshape(train_idx.shape[0])
+    else:
+        query_idx = query_idx.reshape(query_idx.shape[0])
+        gallery_idx = gallery_idx.reshape(gallery_idx.shape[0])
+    camId = camId.reshape(camId.shape[0])
+
+    showfiles_train = filelist[gallery_idx]
+    showfiles_test = filelist[query_idx]
+    train_data = feature_vectors[gallery_idx]
+    test_data = feature_vectors[query_idx]
+    train_label = labels[gallery_idx]
+    test_label = labels[query_idx]
+    train_cam = camId[gallery_idx]
+    test_cam = camId[query_idx]
+
+    accuracy = np.zeros((2, args.multrank))
+    test_table = np.arange(1, args.multrank+1)
+
+    if (args.normalise):
+        train_data = np.divide(train_data,LA.norm(train_data, axis=0))
+        test_data = np.divide(test_data, LA.norm(test_data, axis=0))
+    if(args.kmean):
+        train_data, train_label, train_cam = create_kmean_clusters(feature_vectors,
+                                                                   labels,
+                                                                   gallery_idx,
+                                                                   camId)
+    for q in range(args.comparison):
+        target_pred = test_model(train_data, test_data, train_label, test_label, train_cam, test_cam, showfiles_train, showfiles_test, args)
+        for i in range(args.multrank):
+            accuracy[q][i] = draw_results(test_label, target_pred[i])
+        args.rerank = True
+        args.neighbors = 1
+
+    if(args.multrank != 1):
+        plt.plot(test_table[:(args.multrank)], 100*accuracy[0])
+        if(args.comparison!=1):
+            plt.plot(test_table[:(args.multrank)], 100*accuracy[1])
+            plt.legend(['Baseline kNN', 'Improved metric'], loc='upper left')
+        plt.xlabel('k rank')
+        plt.ylabel('Recognition Accuracy (%)')
+        plt.grid(True)
+        plt.show()
+
+
+if __name__ == "__main__":
+    main()
+
diff --git a/kmean.py b/kmean.py
deleted file mode 100644
index 4e9d03e..0000000
--- a/kmean.py
+++ /dev/null
@@ -1,62 +0,0 @@
-import matplotlib.pyplot as plt
-from mpl_toolkits.mplot3d import Axes3D
-import sys
-import random
-import os
-import json
-import scipy.io
-from random import randint
-from sklearn.neighbors import KNeighborsClassifier
-from sklearn.neighbors import DistanceMetric
-from sklearn.cluster import KMeans
-from sklearn.decomposition import PCA
-from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import StandardScaler
-from sklearn.metrics import confusion_matrix
-from sklearn.metrics import accuracy_score
-import argparse
-import numpy as np
-from numpy import genfromtxt
-from numpy import linalg as LA
-from timeit import default_timer as timer
-from scipy.spatial.distance import cdist
-from rerank import re_ranking
-
-def create_kmean_clusters(feature_vectors, labels, gallery_idx, camId):
-    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)
-
-    for i in range(2):
-        km_train_data[i] =  KMeans(n_clusters=int(np.max(labels)),random_state=0).fit(train[i])
-        km_labels[i] = np.zeros(int(np.max(labels))) # clusters size
-        km_idx[i] = km_train_data[i].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[0] = np.ones(km_labels_1.size)
-    clustercam[1] = np.add(np.ones(km_labels_2.size), 1)
-    for j in range(2):
-        for j in range(km_labels_1.size):
-            cl.append(km_train_data[i].cluster_centers_[j])
-            cllab.append(km_labels[i][j])
-
-    train_data = np.array(cl)
-    train_label = np.array(cllab)
-    train_cam = np.concatenate(clustercam, axis=1)
-    return train_data, train_label, train_cam
-        
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/rerank.py b/lib/rerank.py
index 6b20f53..6b20f53 100644
--- a/rerank.py
+++ b/lib/rerank.py