def stack_decoder_layers(init):
model = Sequential(init_method=init)
model.add(Dense(256, activation='relu', input_shape=(latent_dim, )))
model.add(BatchNormalization())
model.add(Dense(512, activation='relu'))
model.add(BatchNormalization())
model.add(Dense(img_dim, activation='sigmoid'))
return model
def stack_discriminator_layers(init):
model = Sequential(init_method=init)
model.add(Dense(256, input_shape=(img_dim, )))
model.add(Activation('leaky_relu', alpha=0.2))
model.add(Dropout(0.25))
model.add(Dense(128))
model.add(Activation('leaky_relu', alpha=0.2))
model.add(Dropout(0.25))
model.add(Dense(2, activation='sigmoid'))
return model
def stack_generator_layers(init):
model = Sequential(init_method=init)
model.add(Dense(128, input_shape=(latent_dim, )))
model.add(Activation('leaky_relu'))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(256))
model.add(Activation('leaky_relu'))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(512))
model.add(Activation('leaky_relu'))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(img_dim, activation='tanh'))
return model
def stack_discriminator_layers(init):
model = Sequential(init_method=init)
model.add(
Conv2D(64, kernel_size=(5, 5), padding='same', input_shape=img_dims))
model.add(Activation('leaky_relu'))
model.add(Dropout(0.25))
model.add(Conv2D(128, kernel_size=(5, 5), padding='same'))
model.add(Activation('leaky_relu'))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(2))
model.add(Activation('sigmoid'))
return model
def stack_generator_layers(init):
model = Sequential(init_method=init)
model.add(Dense(128 * 7 * 7, input_shape=(latent_dim, )))
model.add(Activation('leaky_relu'))
model.add(BatchNormalization(momentum=0.8))
model.add(Reshape((128, 7, 7)))
model.add(UpSampling2D())
model.add(Conv2D(64, kernel_size=(5, 5), padding='same'))
model.add(BatchNormalization(momentum=0.8))
model.add(Activation('leaky_relu'))
model.add(UpSampling2D())
model.add(Conv2D(img_channels, kernel_size=(5, 5), padding='same'))
model.add(Activation('tanh'))
return model
model = Sequential(init_method='he_uniform')
model.add(
Conv2D(filters=32,
kernel_size=(3, 3),
activation='relu',
input_shape=(1, 8, 8),
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))
model.add(BatchNormalization())
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(BatchNormalization())
model.add(Dense(10, activation='softmax')) # 10 digits classes
model.compile(loss='categorical_crossentropy', optimizer=opt)
model_epochs = 12
fit_stats = model.fit(train_data.reshape(-1, 1, 8, 8),
one_hot(train_label),
batch_size=128,
epochs=model_epochs,
validation_data=(test_data.reshape(-1, 1, 8, 8),
one_hot(test_label)),
shuffle_data=True)
predictions = unhot(model.predict(test_data.reshape(-1, 1, 8, 8), True))
data.target,
test_size = 0.3,
random_seed = 3)
# plot samples of training data
plot_img_samples(train_data, train_label, dataset = 'cifar', channels = 3)
reshaped_image_dims = 3 * 32 * 32 # ==> (channels * height * width)
reshaped_train_data = z_score(train_data.reshape(train_data.shape[0], reshaped_image_dims).astype('float32'))
reshaped_test_data = z_score(test_data.reshape(test_data.shape[0], reshaped_image_dims).astype('float32'))
# optimizer definition
opt = register_opt(optimizer_name = 'adam', momentum = 0.01, lr = 0.0001)
model = Sequential()
model.add(Dense(1024, input_shape = (3072, )))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(Dense(100))
model.add(Activation('softmax'))
model.compile(loss = 'cce', optimizer = opt)
from ztlearn.dl.models import Sequential
from ztlearn.dl.optimizers import register_opt
from ztlearn.dl.layers import LSTM, Flatten, Dense
text = open('../../data/text/tinyshakespeare.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)
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_epochs = 2
fit_stats = model.fit(train_data,
train_label,
batch_size=128,
epochs=model_epochs,
validation_data=(test_data, test_label))
plot_metric('Loss', model_epochs, fit_stats['train_loss'],
fit_stats['valid_loss'])
plot_metric('Accuracy', model_epochs, fit_stats['train_acc'],
fit_stats['valid_acc'])
fashion_mnist.data,
fashion_mnist.target.astype('int'),
test_size=0.33,
random_seed=5,
cut_off=None)
# plot samples of training data
plot_tiled_img_samples(train_data[:40], train_label[:40], dataset='mnist')
# optimizer definition
# opt = register_opt(optimizer_name = 'nestrov', momentum = 0.01, lr = 0.0001)
opt = register_opt(optimizer_name='adam', momentum=0.001, lr=0.001)
# model definition
model = Sequential()
model.add(Dense(512, activation='relu', input_shape=(784, )))
model.add(Dropout(0.25))
model.add(BatchNormalization())
model.add(Dense(10, activation='relu')) # 10 digits classes
model.compile(loss='cce', optimizer=opt)
model.summary()
model_epochs = 5
fit_stats = model.fit(train_data,
one_hot(train_label),
batch_size=128,
epochs=model_epochs,
validation_data=(test_data, one_hot(test_label)),
shuffle_data=True)
from ztlearn.utils import *
from ztlearn.dl.layers import Dense
from ztlearn.dl.models import Sequential
from ztlearn.optimizers import register_opt
from ztlearn.datasets.iris import fetch_iris
data = fetch_iris()
train_data, test_data, train_label, test_label = train_test_split(
data.data, data.target, test_size=0.3, random_seed=5)
# optimizer definition
opt = register_opt(optimizer_name='adam', momentum=0.1, learning_rate=0.01)
# model definition
model = Sequential()
model.add(Dense(10, activation='sigmoid', input_shape=(train_data.shape[1], )))
model.add(Dense(3, activation='sigmoid')) # 3 iris_classes
model.compile(loss='categorical_crossentropy', optimizer=opt)
model.summary('iris mlp')
model_epochs = 25
fit_stats = model.fit(train_data,
one_hot(train_label),
batch_size=10,
epochs=model_epochs,
validation_data=(test_data, one_hot(test_label)),
shuffle_data=True)
# eval_stats = model.evaluate(test_data, one_hot(train_label))
predictions = unhot(model.predict(test_data))
sentences_tokens, vocab_size, longest_sentence = get_sentence_tokens(paragraph)
sentence_targets = one_hot(np.array([1, 1, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1]))
train_data, test_data, train_label, test_label = train_test_split(sentences_tokens,
sentence_targets,
test_size = 0.2,
random_seed = 5)
# optimizer definition
opt = register_opt(optimizer_name = 'adamax', momentum = 0.01, lr = 0.001)
model = Sequential()
model.add(Embedding(vocab_size, 2, input_length = longest_sentence))
model.add(RNN(5, activation = 'tanh', bptt_truncate = 2, input_shape = (2, longest_sentence)))
model.add(Flatten())
model.add(Dense(2, activation = 'softmax'))
model.compile(loss = 'bce', optimizer = opt)
model.summary('embedded sentences rnn')
"""
NOTE:
batch size should be equal the size of embedding
vectors and divisible by the training set size
"""
model_epochs = 500
fit_stats = model.fit(train_data,
train_label,
batch_size = 2,
epochs = model_epochs,
x, y, seq_len = gen_mult_sequence_xtym(3000, 10, 10)
train_data, test_data, train_label, test_label = train_test_split(
x, y, test_size=0.3)
# plot samples of training data
print_seq_samples(train_data, train_label, 0)
# optimizer definition
opt = register_opt(optimizer_name='adam', momentum=0.01, learning_rate=0.01)
# model definition
model = Sequential()
model.add(RNN(5, activation='tanh', bptt_truncate=5, input_shape=(9, seq_len)))
model.add(Flatten())
model.add(Dense(seq_len, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer=opt)
model.summary('seq rnn')
model_epochs = 15
fit_stats = model.fit(train_data,
train_label,
batch_size=100,
epochs=model_epochs,
validation_data=(test_data, test_label))
print_seq_results(model.predict(test_data), test_label, test_data)
model_name = model.model_name
plot_metric('loss',
# plot samples of training data
plot_img_samples(train_data, train_label, dataset = 'cifar', channels = 3)
reshaped_image_dims = 3 * 1024 # ==> (channels * (height * width))
reshaped_train_data = z_score(train_data.reshape(train_data.shape[0], reshaped_image_dims).astype('float32'))
reshaped_test_data = z_score(test_data.reshape(test_data.shape[0], reshaped_image_dims).astype('float32'))
# optimizer definition
opt = register_opt(optimizer_name = 'adam', momentum = 0.01, lr = 0.0001)
# model definition
model = Sequential()
model.add(RNN(256, activation = 'tanh', bptt_truncate = 5, input_shape = (3, 1024)))
model.add(Flatten())
model.add(Dense(100, activation = 'softmax')) # 10 digits classes
model.compile(loss = 'categorical_crossentropy', optimizer = opt)
model.summary(model_name = 'cifar-100 rnn')
model_epochs = 10 # add more epochs
fit_stats = model.fit(reshaped_train_data.reshape(-1, 3, 1024),
one_hot(train_label),
batch_size = 128,
epochs = model_epochs,
validation_data = (reshaped_test_data.reshape(-1, 3, 1024), one_hot(test_label)),
shuffle_data = True)
predictions = unhot(model.predict(reshaped_test_data.reshape(-1, 3, 1024), True))
print_results(predictions, test_label)
plot_img_results(test_data, test_label, predictions, dataset = 'cifar', channels = 3)
