Import test_model and draw_results from evaluate.

Rewrite mAP return in test_model

2 files changed, 25 insertions, 159 deletions

diff --git a/evaluate.py b/evaluate.py
index 99e5eed..b178abc 100755
--- a/evaluate.py
+++ b/evaluate.py
@@ -128,7 +128,7 @@ def test_model(gallery_data, probe_data, gallery_label, probe_label, gallery_cam
         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])
+            AP = np.zeros(probe_label.shape[0])
             max_level_precision = np.zeros((probe_label.shape[0],11))
             
             for i in range(probe_label.shape[0]):
@@ -152,9 +152,10 @@ def test_model(gallery_data, probe_data, gallery_label, probe_label, gallery_cam
                 for j in range(11):
                     max_level_precision[i][j] = np.max(precision[i][np.where(recall[i]>=(j/10))])
             for i in range(probe_label.shape[0]):
-                mAP[i] = sum(max_level_precision[i])/11
-            print('mAP:',np.mean(mAP))
-                    
+                AP[i] = sum(max_level_precision[i])/11
+            mAP = np.mean(AP) 
+            print('mAP:',mAP)
+            return target_pred, mAP
     return target_pred
 
 def main():
@@ -231,12 +232,18 @@ def main():
             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], train_model, args))
-         
+            if args.mAP:
+                target_pred[i], mAP = (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], train_model, args))
+            else: 
+                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], train_model, args))
+ 
         accuracy[0] = draw_results(test_label, target_pred)
     else:
         for q in range(args.comparison+1):
-            target_pred = test_model(train_data, test_data, train_label, test_label, train_cam, test_cam, showfiles_train, showfiles_test, train_model, args)
+            if args.mAP:
+                target_pred, mAP = test_model(train_data, test_data, train_label, test_label, train_cam, test_cam, showfiles_train, showfiles_test, train_model, args)
+            else:
+                target_pred = test_model(train_data, test_data, train_label, test_label, train_cam, test_cam, showfiles_train, showfiles_test, train_model, args)
             for i in range(args.multrank):
                 accuracy[q][i] = draw_results(test_label, target_pred[i])
             args.rerank = True
diff --git a/opt.py b/opt.py
index fb5c089..28de96f 100755
--- a/opt.py
+++ b/opt.py
@@ -8,21 +8,14 @@
 #               [-K KMEAN] [-A] [-P PCA]
 
 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
@@ -30,11 +23,14 @@ 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
+from evaluate import test_model
+from evaluate import draw_results 
 
 parser = argparse.ArgumentParser()
 
@@ -63,108 +59,6 @@ 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:
-            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))])
-            for i in range(probe_label.shape[0]):
-                mAP[i] = sum(max_level_precision[i])/11
-            print('mAP:',np.mean(mAP))
-            return np.mean(mAP)
-        
-    return target_pred
-
 def eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args):
     
     if args.train:
@@ -188,7 +82,6 @@ def eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args)
         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]
@@ -197,7 +90,6 @@ def eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args)
         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]
     
@@ -210,48 +102,15 @@ def eval(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args)
     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)
+    for q in range(args.comparison+1):
+        if args.mAP:
+            return test_model(train_data, test_data, train_label, test_label, train_cam, test_cam, showfiles_train, showfiles_test, train_model, args)
         
-    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+1):
-            if args.mAP:
-                return test_model(train_data, test_data, train_label, test_label, train_cam, test_cam, showfiles_train, showfiles_test, args)
-            
-            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):
-            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()
+        target_pred = test_model(train_data, test_data, train_label, test_label, train_cam, test_cam, showfiles_train, showfiles_test, train_model, args)
+        for i in range(args.multrank):
+            return draw_results(test_label, target_pred[i])
+        args.rerank = True
+        args.neighbors = 1
 
 def kopt(camId, filelist, labels, gallery_idx, train_idx, feature_vectors, args):
     axis = 0