def run(): # Prepare data dataset = dp.datasets.MNIST() x, y = dataset.data() x = x.astype(dp.float_)[:, np.newaxis, :, :] y = y.astype(dp.int_) train_idx, test_idx = dataset.split() x_train = x[train_idx] y_train = y[train_idx] x_test = x[test_idx] y_test = y[test_idx] scaler = dp.UniformScaler(high=255.) x_train = scaler.fit_transform(x_train) x_test = scaler.transform(x_test) batch_size = 128 train_input = dp.SupervisedInput(x_train, y_train, batch_size=batch_size) test_input = dp.SupervisedInput(x_test, y_test) # Setup neural network net = dp.NeuralNetwork(layers=[ dp.Convolutional( n_filters=32, filter_shape=(5, 5), weights=dp.Parameter(dp.AutoFiller(), weight_decay=0.0001), ), dp.Activation('relu'), dp.Pool( win_shape=(3, 3), strides=(2, 2), method='max', ), dp.Convolutional( n_filters=64, filter_shape=(5, 5), weights=dp.Parameter(dp.AutoFiller(), weight_decay=0.0001), ), dp.Activation('relu'), dp.Pool( win_shape=(3, 3), strides=(2, 2), method='max', ), dp.Flatten(), dp.FullyConnected( n_output=128, weights=dp.Parameter(dp.AutoFiller()), ), dp.FullyConnected( n_output=dataset.n_classes, weights=dp.Parameter(dp.AutoFiller()), ), dp.MultinomialLogReg(), ], ) # Train neural network def val_error(): return net.error(test_input) trainer = dp.StochasticGradientDescent( max_epochs=15, learn_rule=dp.Momentum(learn_rate=0.01, momentum=0.9), ) trainer.train(net, train_input, val_error) # Visualize convolutional filters to disk for l, layer in enumerate(net.layers): if not isinstance(layer, dp.Convolutional): continue W = np.array(layer.params()[0].array) filepath = os.path.join('mnist', 'conv_layer_%i.png' % l) dp.misc.img_save(dp.misc.conv_filter_tile(W), filepath) # Evaluate on test data error = net.error(test_input) print('Test error rate: %.4f' % error)
weight_decay=0.004, monitor=True), ), dp.Activation('relu'), dp.Pool(**pool_kwargs), dp.Convolutional( n_filters=64, filter_shape=(5, 5), border_mode='same', weights=dp.Parameter(dp.NormalFiller(sigma=0.01), weight_decay=0.004, monitor=True), ), dp.Activation('relu'), dp.Pool(**pool_kwargs), dp.Flatten(), dp.FullyConnected( n_output=64, weights=dp.Parameter(dp.NormalFiller(sigma=0.1), weight_decay=0.004, monitor=True), ), dp.Activation('relu'), dp.FullyConnected( n_output=6, weights=dp.Parameter(dp.NormalFiller(sigma=0.1), weight_decay=0.004, monitor=True), ), dp.MeanSquaredError(), ], )
def run(): # Prepare data batch_size = 128 dataset = dp.datasets.CIFAR10() x, y = dataset.data() y = y.astype(dp.int_) train_idx, test_idx = dataset.split() x_train = preprocess_imgs(x[train_idx]) y_train = y[train_idx] x_test = preprocess_imgs(x[test_idx]) y_test = y[test_idx] train_input = dp.SupervisedInput(x_train, y_train, batch_size=batch_size) test_input = dp.SupervisedInput(x_test, y_test, batch_size=batch_size) # Setup neural network pool_kwargs = { 'win_shape': (3, 3), 'strides': (2, 2), 'border_mode': 'same', 'method': 'max', } nn = dp.NeuralNetwork(layers=[ dp.Convolutional( n_filters=32, filter_shape=(5, 5), border_mode='same', weights=dp.Parameter(dp.NormalFiller(sigma=0.0001), penalty=('l2', 0.004), monitor=True), ), dp.Activation('relu'), dp.Pool(**pool_kwargs), dp.Convolutional( n_filters=32, filter_shape=(5, 5), border_mode='same', weights=dp.Parameter(dp.NormalFiller(sigma=0.01), penalty=('l2', 0.004), monitor=True), ), dp.Activation('relu'), dp.Pool(**pool_kwargs), dp.Convolutional( n_filters=64, filter_shape=(5, 5), border_mode='same', weights=dp.Parameter(dp.NormalFiller(sigma=0.01), penalty=('l2', 0.004), monitor=True), ), dp.Activation('relu'), dp.Pool(**pool_kwargs), dp.Flatten(), dp.FullyConnected( n_output=64, weights=dp.Parameter(dp.NormalFiller(sigma=0.1), penalty=('l2', 0.03)), ), dp.Activation('relu'), dp.FullyConnected( n_output=dataset.n_classes, weights=dp.Parameter(dp.NormalFiller(sigma=0.1), penalty=('l2', 0.03)), ), dp.MultinomialLogReg(), ], ) # Train neural network n_epochs = [8, 8] learn_rate = 0.001 def valid_error(): return nn.error(test_input) for i, max_epochs in enumerate(n_epochs): lr = learn_rate / 10**i trainer = dp.StochasticGradientDescent( max_epochs=max_epochs, learn_rule=dp.Momentum(learn_rate=lr, momentum=0.9), ) trainer.train(nn, train_input, valid_error) # Visualize convolutional filters to disk for l, layer in enumerate(nn.layers): if not isinstance(layer, dp.Convolutional): continue W = np.array(layer.params()[0].values) dp.misc.img_save(dp.misc.conv_filter_tile(W), os.path.join('cifar10', 'convnet_layer_%i.png' % l)) # Evaluate on test data error = nn.error(test_input) print('Test error rate: %.4f' % error)
def run(): # Prepare data batch_size = 128 dataset = dp.datasets.CIFAR10() x, y = dataset.data() y = y.astype(dp.int_) train_idx, test_idx = dataset.split() x_train = preprocess_imgs(x[train_idx]) y_train = y[train_idx] train_input = dp.SupervisedInput(x_train, y_train, batch_size=batch_size) # Setup neural network pool_kwargs = { 'win_shape': (3, 3), 'strides': (2, 2), 'border_mode': 'same', 'method': 'max', } nn = dp.NeuralNetwork(layers=[ dp.Convolutional( n_filters=32, filter_shape=(5, 5), border_mode='same', weights=dp.Parameter(dp.NormalFiller(sigma=0.0001), penalty=('l2', 0.004), monitor=True), ), dp.Activation('relu'), dp.Pool(**pool_kwargs), dp.Convolutional( n_filters=32, filter_shape=(5, 5), border_mode='same', weights=dp.Parameter(dp.NormalFiller(sigma=0.01), penalty=('l2', 0.004), monitor=True), ), dp.Activation('relu'), dp.Pool(**pool_kwargs), dp.Convolutional( n_filters=64, filter_shape=(5, 5), border_mode='same', weights=dp.Parameter(dp.NormalFiller(sigma=0.01), penalty=('l2', 0.004), monitor=True), ), dp.Activation('relu'), dp.Pool(**pool_kwargs), dp.Flatten(), dp.FullyConnected( n_output=64, weights=dp.Parameter(dp.NormalFiller(sigma=0.1), penalty=('l2', 0.03)), ), dp.Activation('relu'), dp.FullyConnected( n_output=dataset.n_classes, weights=dp.Parameter(dp.NormalFiller(sigma=0.1), penalty=('l2', 0.03)), ), dp.MultinomialLogReg(), ], ) dp.misc.profile(nn, train_input)
def run(): # Prepare data dataset = dp.datasets.MNIST() x, y = dataset.data() x = x[:, np.newaxis, :, :].astype(dp.float_) / 255.0 - 0.5 y = y.astype(dp.int_) train_idx, test_idx = dataset.split() x_train = x[train_idx] y_train = y[train_idx] x_test = x[test_idx] y_test = y[test_idx] train_input = dp.SupervisedInput(x_train, y_train, batch_size=128) test_input = dp.SupervisedInput(x_test, y_test) # Setup neural network nn = dp.NeuralNetwork(layers=[ dp.Convolutional( n_filters=20, filter_shape=(5, 5), weights=dp.Parameter(dp.NormalFiller(sigma=0.1), penalty=('l2', 0.00001)), ), dp.Activation('relu'), dp.Pool( win_shape=(2, 2), strides=(2, 2), method='max', ), dp.Convolutional( n_filters=50, filter_shape=(5, 5), weights=dp.Parameter(dp.NormalFiller(sigma=0.1), penalty=('l2', 0.00001)), ), dp.Activation('relu'), dp.Pool( win_shape=(2, 2), strides=(2, 2), method='max', ), dp.Flatten(), dp.FullyConnected( n_output=500, weights=dp.NormalFiller(sigma=0.01), ), dp.FullyConnected( n_output=dataset.n_classes, weights=dp.NormalFiller(sigma=0.01), ), dp.MultinomialLogReg(), ], ) # Train neural network def valid_error(): return nn.error(test_input) trainer = dp.StochasticGradientDescent( max_epochs=15, learn_rule=dp.Momentum(learn_rate=0.1, momentum=0.9), ) trainer.train(nn, train_input, valid_error) # Visualize convolutional filters to disk for layer_idx, layer in enumerate(nn.layers): if not isinstance(layer, dp.Convolutional): continue W = np.array(layer.params()[0].values) dp.misc.img_save( dp.misc.conv_filter_tile(W), os.path.join('mnist', 'convnet_layer_%i.png' % layer_idx)) # Evaluate on test data error = nn.error(test_input) print('Test error rate: %.4f' % error)