diff options
Diffstat (limited to 'train.py')
| -rwxr-xr-x | train.py | 29 |
1 files changed, 19 insertions, 10 deletions
@@ -15,6 +15,7 @@ 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 +from sklearn.utils import check_array import argparse import numpy as np @@ -29,7 +30,7 @@ def normalise_faces(average_face, faces): # Split data into training and testing sets def test_split(n_faces, raw_faces, split, seed): random.seed(seed) - n_cases = 52 + n_cases = 10 n_pixels = 2576 raw_faces_split = np.split(raw_faces,n_cases) @@ -72,9 +73,9 @@ args = parser.parse_args() M = args.eigen raw_faces = genfromtxt(args.data, delimiter=',') -targets = np.repeat(np.arange(10),52) +targets = np.repeat(np.arange(52),10) -n_faces = 10 +n_faces = 52 faces_train, faces_test, target_train, target_test = test_split(n_faces, raw_faces, args.split, args.seed) @@ -89,7 +90,8 @@ explained_variances = () if args.pca or args.pca_r: # faces_pca containcts the principial components or the M most variant eigenvectors average_face = np.mean(faces_train, axis=0) - deviations = np.std(faces_train, axis=0) + deviations_tr = np.std(faces_train, axis=0) + deviations_tst = np.std(faces_train, axis=0) faces_train = normalise_faces(average_face, faces_train) faces_test = normalise_faces(average_face, faces_test) if (args.pca_r): @@ -105,15 +107,16 @@ if args.pca or args.pca_r: e_vals = np.flip(e_vals)[:M] e_vecs = np.fliplr(e_vecs).T[:M] - deviations = np.flip(deviations) + deviations_tr = np.flip(deviations_tr) + deviations_tst = np.flip(deviations_tst) faces_train = np.dot(faces_train, e_vecs.T) faces_test = np.dot(faces_test, e_vecs.T) if (args.reconstruct): - rec_vec = np.add(average_face, np.dot(faces_train[args.reconstruct], e_vecs) * deviations) + rec_vec = np.add(average_face, np.dot(faces_train[args.reconstruct], e_vecs) * deviations_tr) + rec_faces_test = np.add(average_face, np.dot(faces_test, e_vecs) * deviations_tst) rec_error = LA.norm(np.subtract(raw_faces_train[args.reconstruct], rec_vec)) - print(rec_error) ar = plt.subplot(2, 1, 1) ar.imshow(rec_vec.reshape([46,56]).T, cmap = 'gist_gray') ar = plt.subplot(2, 1, 2) @@ -146,14 +149,20 @@ if args.principal: if args.grapheigen: # Colors for distinct individuals - cols = ['#{:06x}'.format(randint(0, 0xffffff)) for i in range(10)] + cols = ['#{:06x}'.format(randint(0, 0xffffff)) for i in range(52)] pltCol = [cols[int(k)] for k in target_train] plt.scatter(faces_train[:, 0], faces_train[:, 1], color=pltCol) plt.show() classifier = KNeighborsClassifier(n_neighbors=args.neighbors) -classifier.fit(faces_train, target_train) -target_pred = classifier.predict(faces_test) +if (args.reconstruct): + classifier.fit(raw_faces_train, target_train) + target_pred = classifier.predict(rec_faces_test) + #Better Passing n_neighbors = 1 +else: + classifier.fit(faces_train, target_train) + target_pred = classifier.predict(faces_test) + #Better n_neighbors = 2 cm = confusion_matrix(target_test, target_pred) print(cm) |