def test_classification(): # Make dataset n_classes = 2 n_samples = 1000 n_features = 48 x, y = make_classification(n_samples=n_samples, n_features=n_features, n_classes=n_classes, n_informative=n_classes * 2, random_state=1) x = x.astype(dp.float_) y = y.astype(dp.int_) n_train = int(0.8 * n_samples) x_train = x[:n_train] y_train = y[:n_train] x_test = x[n_train:] y_test = y[n_train:] scaler = dp.StandardScaler() x_train = scaler.fit_transform(x_train) x_test = scaler.transform(x_test) # Setup feeds batch_size = 16 train_feed = dp.SupervisedFeed(x_train, y_train, batch_size=batch_size) test_feed = dp.Feed(x_test) # Setup neural network weight_decay = 1e-03 net = dp.NeuralNetwork( layers=[ dp.Affine( n_out=32, weights=dp.Parameter(dp.AutoFiller(), weight_decay=weight_decay), ), dp.ReLU(), dp.Affine( n_out=64, weights=dp.Parameter(dp.AutoFiller(), weight_decay=weight_decay), ), dp.ReLU(), dp.Affine( n_out=n_classes, weights=dp.Parameter(dp.AutoFiller()), ), ], loss=dp.SoftmaxCrossEntropy(), ) # Train neural network learn_rule = dp.Momentum(learn_rate=0.01 / batch_size, momentum=0.9) trainer = dp.GradientDescent(net, train_feed, learn_rule) trainer.train_epochs(n_epochs=10) # Evaluate on test data error = np.mean(net.predict(test_feed) != y_test) print('Test error rate: %.4f' % error) assert error < 0.2
def vgg_net(path, pool_method='max', border_mode='same'): matconvnet = scipy.io.loadmat(path) img_mean = matconvnet['meta'][0][0][2][0][0][2] vgg_layers = matconvnet['layers'][0] layers = [] for layer in vgg_layers: layer = layer[0][0] layer_type = layer[1][0] if layer_type == 'conv': params = layer[2][0] weights = params[0] bias = params[1] weights = np.transpose(weights, (3, 2, 0, 1)).astype(dp.float_) bias = np.reshape(bias, (1, bias.size, 1, 1)).astype(dp.float_) layers.append(conv_layer(weights, bias, border_mode)) elif layer_type == 'pool': layers.append(pool_layer(pool_method, border_mode)) elif layer_type == 'relu': layers.append(dp.ReLU()) elif layer_type == 'softmax': pass else: raise ValueError('invalid layer type: %s' % layer_type) return layers, img_mean
n += 1 # Prepare network feeds batch_size = 128 train_feed = dp.SupervisedSiameseFeed(x1, x2, y, batch_size=batch_size) # Setup network w_gain = 1.5 w_decay = 1e-4 net = dp.SiameseNetwork( siamese_layers=[ dp.Affine( n_out=1024, weights=dp.Parameter(dp.AutoFiller(w_gain), weight_decay=w_decay), ), dp.ReLU(), dp.Affine( n_out=1024, weights=dp.Parameter(dp.AutoFiller(w_gain), weight_decay=w_decay), ), dp.ReLU(), dp.Affine( n_out=2, weights=dp.Parameter(dp.AutoFiller(w_gain)), ), ], loss=dp.ContrastiveLoss(margin=1.0), ) # Train network learn_rate = 0.01 / batch_size
def test_classification(): # Make dataset n_classes = 2 n_samples = 1000 n_features = 48 x, y = make_classification( n_samples=n_samples, n_features=n_features, n_classes=n_classes, n_informative=n_classes*2, random_state=1 ) n_train = int(0.8 * n_samples) n_val = int(0.5 * (n_samples - n_train)) x_train = x[:n_train] y_train = y[:n_train] x_val = x[n_train:n_train+n_val] y_val = y[n_train:n_train+n_val] x_test = x[n_train+n_val:] y_test = y[n_train+n_val:] scaler = dp.StandardScaler() x_train = scaler.fit_transform(x_train) x_val = scaler.transform(x_val) x_test = scaler.transform(x_test) # Setup input batch_size = 16 train_input = dp.SupervisedInput(x_train, y_train, batch_size=batch_size) val_input = dp.Input(x_val) test_input = dp.Input(x_test) # Setup neural network weight_decay = 1e-03 net = dp.NeuralNetwork( layers=[ dp.Affine( n_out=32, weights=dp.Parameter(dp.AutoFiller(), weight_decay=weight_decay), ), dp.ReLU(), dp.Affine( n_out=64, weights=dp.Parameter(dp.AutoFiller(), weight_decay=weight_decay), ), dp.ReLU(), dp.Affine( n_out=n_classes, weights=dp.Parameter(dp.AutoFiller()), ), ], loss=dp.SoftmaxCrossEntropy(), ) # Train neural network def val_error(): return np.mean(net.predict(val_input) != y_val) trainer = dp.GradientDescent( min_epochs=10, learn_rule=dp.Momentum(learn_rate=0.01, momentum=0.9), ) trainer.train(net, train_input, val_error) # Evaluate on test data error = np.mean(net.predict(test_input) != y_test) print('Test error rate: %.4f' % error) assert error < 0.2