Optimizer (run no flags)

1 files changed, 358 insertions, 0 deletions

diff --git a/opt.py b/opt.py
new file mode 100644
index 0000000..0f94de4
--- /dev/null
+++ b/opt.py
@@ -0,0 +1,358 @@
+#!/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 NearestNeighbors
+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
+import logging
+from logging import debug
+
+parser = argparse.ArgumentParser()
+parser.add_argument("-t", "--train", help="Use train data instead of query and gallery", action='store_true')
+parser.add_argument("-c", "--conf_mat", help="Show visual confusion matrix", action='store_true')
+parser.add_argument("-k", "--kmean_alt", help="Perform clustering with generalized labels(not actual kmean)", 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="Use standard euclidean distance", 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 k1 for Rerank -p '$k1val' -ARGUMENT REQUIRED, default=9-", type=int, default = 9)
+parser.add_argument("-q", "--rerankb", help="Parameter k2 for rerank -q '$k2val' -ARGUMENT REQUIRED, default=3-", type=int, default = 3)
+parser.add_argument("-l", "--rerankl", help="Coefficient to combine distances(lambda) -l '$lambdaval' -ARGUMENT REQUIRED, default=0.3-", type=float, default = 0.3)
+parser.add_argument("-n", "--neighbors", help="Use customized ranklist size -n 'size' -ARGUMENT REQUIRED, default=1-", type=int, default = 1)
+parser.add_argument("-v", "--verbose", help="Use verbose output", action='store_true')
+parser.add_argument("-s", "--showrank", help="Save ranklist pics id in a txt file. Number of ranklists saved specified as -s '$number' -ARGUMENT REQUIRED, default=0-", type=int, default = 0)
+parser.add_argument("-1", "--normalise", help="Normalise features", action='store_true', default=0)
+parser.add_argument("-M", "--multrank", help="Run for different ranklist sizes equal to M -ARGUMENT REQUIRED, default=1-", type=int, default=1)
+parser.add_argument("-C", "--comparison", help="Set to 2 to obtain a comparison of baseline and improved metric -ARGUMENT REQUIRED, default=1-", type=int, default=1)
+parser.add_argument("--data", help="You can either put the data in a folder called 'data', or specify the location with --data 'path' -ARGUMENT REQUIRED, default='data'-", default='data')
+parser.add_argument("-K", "--kmean", help="Perform Kmean clustering of size specified through -K '$size' -ARGUMENT REQUIRED, default=0-", type=int, default=0)
+parser.add_argument("-P", "--mAP", help="Display Mean Average Precision for ranklist of size -n '$size'", action='store_true')
+parser.add_argument("-2", "--PCA", help="Use PCA with -2 '$n_components' -ARGUMENT REQUIRED, default=0-", type=int, default=0)
+
+args = parser.parse_args()
+
+if args.verbose:
+    logging.basicConfig(level=logging.DEBUG)
+
+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):
+
+    debug("probe shape: %s", probe_data.shape)
+    debug("gallery shape: %s", gallery_data.shape)
+
+    if args.rerank:
+        distances = re_ranking(probe_data, gallery_data, 
+                               args.reranka, args.rerankb, args.rerankl, 
+                               MemorySave = False, Minibatch = 2000)
+    else:
+        if args.mahalanobis:
+            # metric = 'jaccard' is also valid
+            cov_inv = np.linalg.inv(np.cov(gallery_data.T))
+            distances = np.zeros((probe_data.shape[0], gallery_data.shape[0]))
+            for i in range(int(probe_data.shape[0]/10)):
+                print("Comupting from", i*10, "to", (i+1)*10-1)
+                distances[i*10:(i+1)*10-1] = cdist(probe_data[i*10:(i+1)*10-1], gallery_data, 'mahalanobis', VI=cov_inv)
+        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.mAP:
+            precision = np.zeros((probe_label.shape[0], args.neighbors))
+            recall = np.zeros((probe_label.shape[0], args.neighbors))
+            mAP = np.zeros(probe_label.shape[0])
+            max_level_precision = np.zeros((probe_label.shape[0],11))
+            
+            for i in range(probe_label.shape[0]):
+                truth_count=0
+                false_count=0
+                for j in range(args.neighbors):
+                    if probe_label[i] == nneighbors[i][j]:
+                        truth_count+=1
+                        precision[i][j] = truth_count/(j+1)
+                    else:
+                        false_count+=1
+                        precision[i][j]= 1 - false_count/(j+1)
+                if truth_count!=0:
+                    recall_step = 1/truth_count
+                    for j in range(args.neighbors):
+                        if probe_label[i] == nneighbors[i][j]:
+                            recall[i][j:] += recall_step
+                else:
+                    recall[i][:] = 1
+            for i in range(probe_label.shape[0]):
+                for j in range(11):
+                    max_level_precision[i][j] = np.max(precision[i][np.where(recall[i]>=(j/10))])
+                    #print(mAP[i])
+            for i in range(probe_label.shape[0]):
+                #mAP[i] = sum(max_level_precision[i])/11
+                mAP[i] = sum(precision[i])/args.neighbors
+            print('mAP:',np.mean(mAP))
+                    
+    return target_pred
+
+def eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args):
+    
+    if args.train:
+        cam = camId[train_idx]
+        cam = cam.reshape((cam.shape[0],1))
+        labs = labels[train_idx].reshape((labels[train_idx].shape[0],1))
+        tt = np.hstack((train_idx, cam)) 
+        train, test, train_label, test_label = train_test_split(tt, labs, test_size=0.3, random_state=0)
+        #to make it smaller we do a double split
+        del labs
+        del cam
+        train_data = feature_vectors[train[:,0]]
+        test_data = feature_vectors[test[:,0]]
+        train_cam = train[:,1]
+        test_cam = test[:,1]
+        showfiles_train = filelist[train[:,0]]
+        showfiles_test = filelist[train[:,0]]
+        del train
+        del test 
+        del tt
+    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]
+
+    train_idx = train_idx.reshape(train_idx.shape[0])
+    train_model = feature_vectors[train_idx]
+    
+    if(args.PCA):
+        pca=PCA(n_components=args.PCA) #Data variance @100 is 94%
+        train_model=pca.fit_transform(train_model)
+        train_data=pca.transform(train_data)
+        test_data=pca.transform(test_data)
+
+    accuracy = np.zeros((2, args.multrank))
+    test_table = np.arange(1, args.multrank+1)
+
+    if (args.normalise):
+        debug("Normalising data")
+        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_alt):
+        debug("Using Kmeans")
+        train_data, train_label, train_cam = create_kmean_clusters(feature_vectors, labels,gallery_idx,camId)
+        
+    if args.kmean:
+        kmeans = KMeans(n_clusters=args.kmean, random_state=0).fit(train_data)
+        neigh = NearestNeighbors(n_neighbors=1)
+        neigh.fit(kmeans.cluster_centers_)
+        neighbors = neigh.kneighbors(test_data, return_distance=False)
+        target_pred = np.zeros(test_data.shape[0])
+
+        for i in range(test_data.shape[0]):
+            td = test_data[i].reshape(1,test_data.shape[1])
+            tc = np.array([test_cam[i]])
+            tl = np.array([test_label[i]])
+            target_pred[i] = (test_model(train_data[np.where(kmeans.labels_==neighbors[i])], td, train_label[np.where(kmeans.labels_==neighbors[i])], tl, train_cam[np.where(kmeans.labels_==neighbors[i])], tc, showfiles_train[np.where(kmeans.labels_==neighbors[i])], showfiles_test[i], args))
+         
+        accuracy[0] = draw_results(test_label, target_pred)
+    else:
+        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):
+                return 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 NN', 'NN+Reranking'], loc='upper left')
+        plt.xlabel('Top k')
+        plt.ylabel('Identification Accuracy (%)')
+        plt.grid(True)
+        plt.show()
+
+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))
+ 
+    axis = 0
+    search = 0
+    steps = 0
+    vertical = True
+    neg = False
+    outofaxis = False
+    start = np.array([1,1])
+    args.PCA = 10
+    args.train = True
+    args.rerank = True
+    args.reranka = 1
+    args.rerankb = 1
+    opt = np.array([1,1])
+    max_acc = eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args)
+    print('origin')
+    print('vertical')
+    while steps<3:
+        steps+=1
+        while axis<4:
+            axis+=1
+            p = start[0]
+            q = start[1]
+            while search <5:
+                search+=1
+                if vertical:
+                    if neg:
+                        p = start[0] - 2*search
+                        if p < 1:
+                            p = 1
+                            search = 5
+                            outofaxis = True
+                    else:
+                        p = search*2 + start[0]
+                    args.reranka = p
+                    if not outofaxis:
+                        print('p:',p,' q:',q)
+                        acc = eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args)
+                    if acc > max_acc:
+                        print('new p:',p, ' for accuracy:', acc)
+                        max_acc=acc
+                        opt[0] = p
+                        start[0] = p
+                        axis=0
+                        steps=0
+                        search=6
+                else:
+                    if neg:
+                        q = start[1] - 2*search
+                        if q < 1:
+                            q = 1
+                            search = 5
+                            outofaxis = True
+                    else:
+                        q = search*2 + start[1]
+                    args.rerankb = q
+                    if not outofaxis:
+                        print('p:',p,' q:',q)
+                        acc = eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args)
+                    if acc > max_acc:
+                        print('new q:',q, ' for accuracy:', acc)
+                        max_acc=acc
+                        opt[1] = q
+                        start[1] = q
+                        axis=0
+                        steps=0
+                        search=6
+            if search==5:
+                outofaxis = False
+                vertical = not vertical
+                print('vertical:',vertical)
+            search=0
+            if axis==2 or axis == 4:
+                neg = not neg
+        axis=0
+        start[0]+=2
+        start[1]+=2
+        p=start[0]
+        q=start[1]
+        args.reranka = start[0]
+        args.rerankb = start[1]
+        print('p:',p,' q:',q)
+        acc = eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args)
+        if acc > max_acc:
+            print('new p:',p,'new q:',q, ' for accuracy:', acc)
+            max_acc=acc
+            opt[0] = start[0]
+            opt[1] = start[1]
+            steps=0
+            vertical=True
+    print('Maximum Accuracy:',max_acc,' found at p:',opt[0],'|q:',opt[1])  
+
+if __name__ == "__main__":
+    main()
+