Add PCA and fix mahalanobis

1 files changed, 13 insertions, 10 deletions

diff --git a/evaluate.py b/evaluate.py
index 3475ef8..208f517 100755
--- a/evaluate.py
+++ b/evaluate.py
@@ -54,7 +54,7 @@ parser.add_argument("-C", "--comparison", help="Set to 2 to obtain a comparison
 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", 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()
 
@@ -73,7 +73,7 @@ def draw_results(test_label, pred_label):
         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):
+def test_model(gallery_data, probe_data, gallery_label, probe_label, gallery_cam, probe_cam, showfiles_train, showfiles_test, train_model, args):
 
     debug("probe shape: %s", probe_data.shape)
     debug("gallery shape: %s", gallery_data.shape)
@@ -85,7 +85,7 @@ def test_model(gallery_data, probe_data, gallery_label, probe_label, gallery_cam
     else:
         if args.mahalanobis:
             # metric = 'jaccard' is also valid
-            cov_inv = np.linalg.inv(np.cov(gallery_data.T))
+            cov_inv = np.linalg.inv(np.cov(train_model.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)
@@ -115,7 +115,7 @@ def test_model(gallery_data, probe_data, gallery_label, probe_label, gallery_cam
                   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]] #
+                nnshowrank[probe_idx][q] = showfiles_train[row[n]]
                 q += 1
                 n += 1
 
@@ -183,7 +183,6 @@ def main():
         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]]
@@ -208,10 +207,14 @@ def main():
         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=300) #Reconstruction error of 2.3% @300
-        train_data=pca.fit_transform(train_data)
+        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))
@@ -223,7 +226,7 @@ def main():
         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)
+        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)
@@ -236,12 +239,12 @@ 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], args))
+            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):
-            target_pred = 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, train_model, args)
             for i in range(args.multrank):
                 accuracy[q][i] = draw_results(test_label, target_pred[i])
             args.rerank = True