from ztlearn.objectives import ObjectiveFunction as objective data = datasets.load_boston() # print(data['DESCR']) # take the boston data boston_data = data['data'] input_data = z_score( boston_data[:, [5]]) # work with only one of the features: RM input_label = data['target'] train_data, test_data, train_label, test_label = train_test_split( input_data, input_label, test_size=0.3) # optimizer definition opt = register_opt(optimizer_name='sgd', momentum=0.01, learning_rate=0.001) # model definition model = PolynomialRegression(degree=5, epochs=100, optimizer=opt, penalty='elastic', penalty_weight=0.5, l1_ratio=0.3) fit_stats = model.fit(train_data, train_label) targets = np.expand_dims(test_label, axis=1) predictions = np.expand_dims(model.predict(test_data), axis=1) mse = objective('mean_squared_error').forward(predictions, targets) print('Mean Squared Error: {:.2f}'.format(mse))
train_data, test_data, train_label, test_label = train_test_split( mnist.data, mnist.target.astype('int'), test_size=0.33, random_seed=5, cut_off=2000) # normalize to range [0, 1] train_data = range_normalize(train_data.astype('float32'), 0, 1) test_data = range_normalize(test_data.astype('float32'), 0, 1) # plot samples of training data plot_img_samples(train_data[:40], train_label[:40], dataset='mnist') # optimizer definition opt = register_opt(optimizer_name='adam', momentum=0.01, lr=0.001) # model definition model = Sequential(init_method='he_uniform') model.add( Conv2D(filters=32, kernel_size=(3, 3), activation='relu', input_shape=(1, 28, 28), padding='same')) model.add(Dropout(0.25)) model.add(BatchNormalization()) model.add( Conv2D(filters=64, kernel_size=(3, 3), activation='relu', padding='same')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Dropout(0.25))
from ztlearn.dl.layers import LSTM, Dense, Flatten from ztlearn.datasets.fashion import fetch_fashion_mnist fashion_mnist = fetch_fashion_mnist() train_data, test_data, train_label, test_label = train_test_split( fashion_mnist.data, fashion_mnist.target.astype('int'), test_size=0.3, random_seed=15, cut_off=2000) # plot samples of training data plot_img_samples(train_data[:40], train_label[:40], dataset='mnist') # optimizer definition opt = register_opt(optimizer_name='rmsprop', momentum=0.01, lr=0.001) # model definition model = Sequential() model.add(LSTM(128, activation='tanh', input_shape=(28, 28))) model.add(Flatten()) model.add(Dense(10, activation='softmax')) # 10 digits classes model.compile(loss='categorical_crossentropy', optimizer=opt) model.summary('fashion mnist lstm') model_epochs = 100 fit_stats = model.fit(train_data.reshape(-1, 28, 28), one_hot(train_label), batch_size=128, epochs=model_epochs,
latent_dim = 100 batch_size = 128 half_batch = int(batch_size * 0.5) verbose = True init_type = 'he_uniform' gen_epoch = 500 gen_noise = np.random.normal(0, 1, (36, latent_dim)) # 36 as batch size and is also the number of sample to be generated at the prediction stage model_epochs = 8000 model_name = 'mnist_gan' model_stats = {'d_train_loss': [], 'd_train_acc': [], 'g_train_loss': [], 'g_train_acc': []} d_opt = register_opt(optimizer_name = 'adam', beta1 = 0.5, lr = 0.001) g_opt = register_opt(optimizer_name = 'adam', beta1 = 0.5, lr = 0.0001) def stack_generator_layers(init): model = Sequential(init_method = init) model.add(Dense(256, input_shape = (latent_dim,))) model.add(Activation('relu')) model.add(BatchNormalization(momentum = 0.8)) model.add(Dense(512)) model.add(Activation('relu')) model.add(BatchNormalization(momentum = 0.8)) model.add(Dense(1024)) model.add(Activation('relu')) model.add(BatchNormalization(momentum = 0.8)) model.add(Dense(img_dim, activation = 'tanh'))
verbose = True init_type = 'he_uniform' gen_epoch = 50 gen_noise = np.random.normal( 0, 1, (36, latent_dim)) # for tiles 6 by 6 i.e (36) image generation model_epochs = 600 model_stats = { 'd_train_loss': [], 'd_train_acc': [], 'g_train_loss': [], 'g_train_acc': [] } d_opt = register_opt(optimizer_name='adam', beta1=0.5, learning_rate=0.0002) g_opt = register_opt(optimizer_name='adam', beta1=0.5, learning_rate=0.0002) def stack_generator_layers(init): model = Sequential(init_method=init) model.add(Dense(64 * 2 * 2, input_shape=(latent_dim, ))) model.add(Activation('leaky_relu')) model.add(BatchNormalization(momentum=0.8)) model.add(Reshape((64, 2, 2))) model.add(UpSampling2D()) model.add(Conv2D(32, kernel_size=(3, 3), padding='same')) model.add(BatchNormalization(momentum=0.8)) model.add(Activation('leaky_relu')) model.add(UpSampling2D()) model.add(Conv2D(img_channels, kernel_size=(3, 3), padding='same'))
# -*- coding: utf-8 -*- from ztlearn.utils import * from ztlearn.dl.models import Sequential from ztlearn.optimizers import register_opt from ztlearn.dl.layers import LSTM, Flatten, Dense text = open('../../../ztlearn/datasets/text/tinyshakespeare_short.txt').read().lower() x, y, len_chars = gen_char_sequence_xtym(text, maxlen = 30, step = 1) del text train_data, test_data, train_label, test_label = train_test_split(x, y, test_size = 0.4) # optimizer definition opt = register_opt(optimizer_name = 'rmsprop', momentum = 0.1, learning_rate = 0.01) # model definition model = Sequential() model.add(LSTM(128, activation = 'tanh', input_shape = (30, len_chars))) model.add(Flatten()) model.add(Dense(len_chars, activation = 'softmax')) model.compile(loss = 'categorical_crossentropy', optimizer = opt) model.summary('shakespeare lstm') model_epochs = 20 fit_stats = model.fit(train_data, train_label, batch_size = 128, epochs = model_epochs,