def train_shallow(beta):
# inputs
input_shape = (1, 28, 28)
epochs = 20
batch_size = 1
filters = 32
kernel_size = 6
pre_latent_size = 128
latent_size = 32
# define filename
name = 'shallow'
# builder hyperparameter dictionary
hp_dictionary = {
'epochs': epochs,
'batch_size': batch_size,
'beta': beta,
'filters': filters,
'kernel_size': kernel_size,
'loss': 'vae_loss',
'optimizer': 'adam'
}
# define log directory
log_dir = './summaries/' + experiment + '/' + utils.build_hyperparameter_string(
name, hp_dictionary) + '/'
# make VAE
vae = ShallowDenseMNIST(input_shape,
log_dir,
filters=filters,
kernel_size=kernel_size,
pre_latent_size=pre_latent_size,
latent_size=latent_size,
beta=beta)
# compile VAE
from keras import optimizers
optimizer = optimizers.Adam(lr=1e-4)
vae.compile(optimizer=optimizer)
# get dataset
(X_train, _), (X_test, _) = utils.load_mnist()
train_generator = utils.make_generator(X_train, batch_size=batch_size)
test_generator = utils.make_generator(X_test, batch_size=batch_size)
train_size = len(X_train)
test_size = len(X_test)
# print summaries
vae.print_model_summaries()
# fit VAE
steps_per_epoch = int(train_size / batch_size)
validation_steps = int(test_size / batch_size)
vae.fit_generator(train_generator,
epochs=epochs,
steps_per_epoch=steps_per_epoch,
validation_data=test_generator,
validation_steps=validation_steps)
def main():
# inputs
input_shape = (1, 28, 20)
filters = 32
latent_channels = 1
kernel_size = 2
beta = 1.0 # entangled latent space
epochs = 10
batch_size = 1
# log directory
experiment = 'experiment_optimal_network_convolutional_latent_frey'
run = 'cvae_frey_entangled_with_fully_connected_filters_same_borders_15_May_13_50_05_batch_size_1_beta_1.0_epochs_20_filters_32_kernel_size_2_latent_channels_64_loss_vae_loss_optimizer_adam'
log_dir = './summaries/' + experiment + '/' + run + '/'
# define model
vae = FreyOptimalConvolutionalLatentExperimentFullyConnectedFilterVAE(
input_shape,
log_dir,
filters=filters,
latent_channels=latent_channels,
kernel_size=kernel_size,
beta=beta)
# load weights
vae.load_model()
# extract models
model = vae.get_model()
decoder = vae.get_decoder()
encoder = vae.get_encoder()
# get dataset
(X_train, _), (X_test, _) = utils.load_frey()
train_generator = utils.make_generator(X_train, batch_size=batch_size)
test_generator = utils.make_generator(X_test, batch_size=batch_size)
train_size = len(X_train)
test_size = len(X_test)
# show original and reconstruction
# sampling.encode_decode_sample(X_test, model)
# plot filters
# sampling.show_convolutional_layers(X_test, encoder, 8, 8)
# sample from prior
# sampling.decode_prior_samples(5, decoder, latent_shape=(1, 64, 1, 1))
# sample from posterior
num_iter = 1000
sampling.sample_posterior(X_test, model, num_iter, show_every=5)
def seeds_maker():
"""
开始f**k seeds了
生成一个车型的全部请求的url,包含用不同的城市，以及不同的月份
虽然结果都是展示的当前月份
seed = {
'brand_id': xxx,
'brand': xxxx,
'serise_id': xxx,
'serise': xxxx,
'url': xxxxx,
'check_city': xxxx,
'check_year': xxxx,
'check_month': xxxx,
'cookie': {},
'cookie_status': 0,
'data': [],
}
"""
initial_file(seed_file)
epoh = int(file_content(epoh_file))
seed_demo.update({'epoh': epoh + 1})
serise_list = make_generator(serise_file, blank=blank)
for each in serise_list:
construct_seed(each[2], each[1], each[-2], each[0], each[-1])
overwrite_file(epoh_file, str(epoh + 1))
return
def train_convolutional_autoencoder():
# inputs
input_shape = (1, 28, 28)
epochs = 15
batch_size = 1
lr = 1e-4
# define filename
name = 'autoencoder_mnist'
# builder hyperparameter dictionary
hp_dictionary = {
'epochs': epochs,
'batch_size': batch_size,
'lr': lr,
'loss': 'vae_loss',
'optimizer': 'adam'
}
# define log directory
log_dir = './summaries/' + experiment + '/' + utils.build_hyperparameter_string(
name, hp_dictionary) + '/'
# make VAE
autoencoder = ConvolutionalAutoencoder(input_shape, log_dir)
# compile VAE
optimizer = optimizers.Adam(lr=lr)
autoencoder.compile(optimizer=optimizer)
# get dataset
(X_train, _), (X_test, _) = utils.load_mnist()
train_generator = utils.make_generator(X_train, batch_size=batch_size)
test_generator = utils.make_generator(X_test, batch_size=batch_size)
# print summaries
autoencoder.print_model_summaries()
# fit VAE
steps_per_epoch = int(len(X_train) / batch_size)
validation_steps = int(len(X_test) / batch_size)
autoencoder.fit_generator(train_generator,
epochs=epochs,
steps_per_epoch=steps_per_epoch,
validation_data=test_generator,
validation_steps=validation_steps)
def main():
# inputs
img_channels = 1
input_shape = (img_channels, 28, 28)
epochs = 50
batch_size = 1
lr = 1e-4
# define filename
name = 'autoencoder_mnist'
# builder hyperparameter dictionary
hp_dictionary = {
'epochs': epochs,
'batch_size': batch_size,
'lr': lr,
'loss': 'vae_loss',
'optimizer': 'adam'
}
# define log directory
run = 'autoencoder_mnist_31_May_21_44_51_batch_size_1_epochs_15_loss_vae_loss_lr_0.0001_optimizer_adam'
log_dir = './summaries/' + experiment + '/' + run + '/'
# make VAE
autoencoder = DenseAutoencoder(input_shape, log_dir)
# load weights
autoencoder.load_model()
# extract models
model = autoencoder.get_model()
decoder = autoencoder.get_decoder()
encoder = autoencoder.get_encoder()
# get dataset
(X_train, _), (X_test, _) = utils.load_mnist()
train_generator = utils.make_generator(X_train, batch_size=batch_size)
test_generator = utils.make_generator(X_test, batch_size=batch_size)
# show original and reconstruction
sampling.plot_original_and_reconstructions(X_test,
model,
input_shape=input_shape)
plt.show()
def main():
# inputs
input_shape = (1, 28, 20)
filters = 32
latent_filters = 1
kernel_size = 2
pool_size = 2
lr = 1e-4
beta = 1.0
batch_size = 1
# log directory
run = 'cvae_frey_20_May_17_07_04_batch_size_1_beta_1_epochs_20_filters_32_kernel_size_2_latent_filters_1_loss_vae_loss_lr_0.0001_optimizer_adam'
log_dir = './summaries/' + experiment + '/' + run + '/'
# define model
vae = FreyConvolutionalLatentSpaceNoBatchNormVAE(
input_shape,
log_dir,
filters=filters,
latent_filters=latent_filters,
kernel_size=kernel_size,
pool_size=pool_size,
beta=beta)
# load weights
vae.load_model()
# extract models
model = vae.get_model()
decoder = vae.get_decoder()
encoder = vae.get_encoder()
# get dataset
(X_train, _), (X_test, _) = utils.load_frey()
train_generator = utils.make_generator(X_train, batch_size=batch_size)
test_generator = utils.make_generator(X_test, batch_size=batch_size)
train_size = len(X_train)
test_size = len(X_test)
# show original and reconstruction
sampling.encode_decode_sample(X_test, model)
def get_all_serise():
"""
获取所有车系
:return:
"""
id_set = make_set(serise_file, 2, '\t')
all_brands = make_generator(brands_file, blank='\t')
session = RequestAPI()
for each in all_brands:
url = serise_url.format(each[0])
html = session.receive_and_request(url=url,
headers=headers,
method='GET')
if html != 'null_html':
data = parse_json(html)
if data != []:
save_serise_data(each[0], each[1], data, id_set)
# make VAE
vae = ConvolutionalLatentDeepVAE(input_shape,
log_dir,
filters=filters,
latent_filters=latent_filters,
kernel_size=kernel_size,
pool_size=pool_size)
# compile VAE
from keras import optimizers
optimizer = optimizers.Adam(lr=1e-3)
vae.compile(optimizer=optimizer)
# get dataset
(X_train, _), (X_test, _) = utils.load_mnist()
train_generator = utils.make_generator(X_train, batch_size=batch_size)
test_generator = utils.make_generator(X_test, batch_size=batch_size)
train_size = len(X_train)
test_size = len(X_test)
# print summaries
vae.print_model_summaries()
# fit VAE
steps_per_epoch = int(train_size / batch_size)
validation_steps = int(test_size / batch_size)
vae.fit_generator(train_generator,
epochs=epochs,
steps_per_epoch=steps_per_epoch,
validation_data=test_generator,
validation_steps=validation_steps)
def train_reconstruction_only_frey_network_with_image_latent_space(latent_filters):
# inputs
input_shape = (1, 28, 20)
filters = 32
kernel_size = 2
pool_size = 2
beta = 1.0
lr = 1e-4
epochs = 20
batch_size = 1
# define filename
name = 'cvae_frey'
# builder hyperparameter dictionary
hp_dictionary = {
'epochs': epochs,
'batch_size': batch_size,
'filters': filters,
'latent_filters': latent_filters,
'kernel_size': kernel_size,
'beta': beta,
'lr': lr,
'loss': 'vae_loss',
'optimizer': 'adam'
}
# define log directory
log_dir = './summaries/' + experiment + '/' + utils.build_hyperparameter_string(name, hp_dictionary) + '/'
# make VAE
vae = FreyConvolutionalLatentSpaceNoBatchNormVAE(input_shape,
log_dir,
filters=filters,
latent_filters=latent_filters,
kernel_size=kernel_size,
pool_size=pool_size,
beta=beta)
# compile VAE
from keras import optimizers
optimizer = optimizers.Adam(lr=lr)
vae.compile(optimizer=optimizer)
# get dataset
(X_train, _), (X_test, _) = utils.load_frey()
train_generator = utils.make_generator(X_train, batch_size=batch_size)
test_generator = utils.make_generator(X_test, batch_size=batch_size)
train_size = len(X_train)
test_size = len(X_test)
# print summaries
vae.print_model_summaries()
# fit VAE
steps_per_epoch = int(train_size / batch_size)
validation_steps = int(test_size / batch_size)
vae.fit_generator(train_generator,
epochs=epochs,
steps_per_epoch=steps_per_epoch,
validation_data=test_generator,
validation_steps=validation_steps)
def run_convolutional_latent_space_with_same_number_of_parameters():
'''
Latent shape: (128, 5, 3)
Number of parameters in network: 119,521
Number of parameters in latent space: 32,896
'''
# inputs
input_shape = (1, 28, 20)
epochs = 1
batch_size = 1
beta = 1.0
filters = 32
kernel_size = 2
latent_channels = 128
pool_size = 2
# define filename
name = 'cvae_frey_convolutional_latent'
# builder hyperparameter dictionary
hp_dictionary = {
'epochs': epochs,
'batch_size': batch_size,
'beta': beta,
'filters': filters,
'kernel_size': kernel_size,
'latent_channels': latent_channels,
'pool_size': pool_size,
'loss': 'vae_loss',
'optimizer': 'adam'
}
# define log directory
log_dir = './summaries/' + utils.build_hyperparameter_string(
name, hp_dictionary) + '/'
# make VAE
vae = FreyConvolutionalLatentVAE(input_shape,
log_dir,
filters=filters,
kernel_size=kernel_size,
latent_channels=latent_channels,
pool_size=pool_size)
# compile VAE
from keras import optimizers
optimizer = optimizers.Adam(lr=1e-3)
vae.compile(optimizer=optimizer)
# print summaries
vae.print_model_summaries()
# get dataset
(X_train, _), (X_test, _) = utils.load_frey()
train_generator = utils.make_generator(X_train, batch_size=batch_size)
test_generator = utils.make_generator(X_test, batch_size=batch_size)
train_size = len(X_train)
test_size = len(X_test)
# fit VAE
steps_per_epoch = int(train_size / batch_size)
validation_steps = int(test_size / batch_size)
vae.fit_generator(train_generator,
epochs=epochs,
steps_per_epoch=steps_per_epoch,
validation_data=test_generator,
validation_steps=validation_steps)
def train_entangled_frey_network_with_fully_connected_filters_same_borders_no_pooling_less_filters(
):
# inputs
input_shape = (1, 28, 20)
filters = 8
latent_channels = 16
kernel_size = 2
beta = 1.0 # entangled latent space
epochs = 20
batch_size = 1
# define filename
name = 'cvae_frey_entangled_with_fully_connected_filters_same_borders_no_pooling_less_filters'
# builder hyperparameter dictionary
hp_dictionary = {
'epochs': epochs,
'batch_size': batch_size,
'beta': beta,
'filters': filters,
'latent_channels': latent_channels,
'kernel_size': kernel_size,
'loss': 'vae_loss',
'optimizer': 'adam'
}
# define log directory
log_dir = './summaries/experiment_optimal_network_convolutional_latent_frey/' + utils.build_hyperparameter_string(
name, hp_dictionary) + '/'
# make VAE
vae = FreyOptimalConvolutionalLatentExperimentFullyConnectedFilterVAE(
input_shape,
log_dir,
filters=filters,
latent_channels=latent_channels,
kernel_size=kernel_size,
beta=beta)
# compile VAE
from keras import optimizers
optimizer = optimizers.Adam(lr=1e-3)
vae.compile(optimizer=optimizer)
# get dataset
(X_train, _), (X_test, _) = utils.load_frey()
train_generator = utils.make_generator(X_train, batch_size=batch_size)
test_generator = utils.make_generator(X_test, batch_size=batch_size)
train_size = len(X_train)
test_size = len(X_test)
# print summaries
vae.print_model_summaries()
# fit VAE
steps_per_epoch = int(train_size / batch_size)
validation_steps = int(test_size / batch_size)
vae.fit_generator(train_generator,
epochs=epochs,
steps_per_epoch=steps_per_epoch,
validation_data=test_generator,
validation_steps=validation_steps)
def loads_seed_in_generator():
"""返回一个生成器，导入种子
上层在调用的时候
通过 next()函数,一次一次调用
"""
return make_generator(seed_file, '')
