def generative_model(self, batch, additional_inputs_tf):
self.gen_epoch = additional_inputs_tf[0]
self.gen_b_identity = additional_inputs_tf[1]
if len(batch['observed']['properties']['flat'])>0:
for e in batch['observed']['properties']['flat']: e['dist']='dirac'
else:
for e in batch['observed']['properties']['image']: e['dist']='dirac'
self.gen_input_sample = batch['observed']['data']
self.gen_input_dist = distributions.ProductDistribution(sample_properties = batch['observed']['properties'], params = self.gen_input_sample)
try: self.n_time = batch['observed']['properties']['flat'][0]['size'][1]
except: self.n_time = batch['observed']['properties']['image'][0]['size'][1]
try: self.gen_batch_size_tf = tf.shape(self.input_sample['flat'])[0]
except: self.gen_batch_size_tf = tf.shape(self.input_sample['image'])[0]
self.gen_pre_prior_param = self.PriorMap.forward((tf.zeros(shape=(self.gen_batch_size_tf, 1)),))
self.gen_pre_prior_dist = distributions.DiagonalGaussianDistribution(params = self.gen_pre_prior_param)
self.gen_pre_prior_latent_code = self.gen_pre_prior_dist.sample()
self.gen_pre_prior_latent_code_log_pdf = self.gen_pre_prior_dist.log_pdf(self.gen_pre_prior_latent_code)
self.gen_flow_param_list = self.FlowMap.forward()
self.gen_flow_object = transforms.SerialFlow([\
transforms.NonLinearIARFlow(self.gen_flow_param_list[0], self.config['n_latent']),
transforms.NonLinearIARFlow(self.gen_flow_param_list[1], self.config['n_latent']),
transforms.NonLinearIARFlow(self.gen_flow_param_list[2], self.config['n_latent']),
transforms.NonLinearIARFlow(self.gen_flow_param_list[3], self.config['n_latent']),
transforms.NonLinearIARFlow(self.gen_flow_param_list[4], self.config['n_latent']),
])
self.gen_prior_latent_code, self.gen_prior_latent_code_log_pdf = self.gen_flow_object.inverse_transform(self.gen_pre_prior_latent_code, self.gen_pre_prior_latent_code_log_pdf)
self.gen_obs_sample_param = self.Generator.forward(self.gen_prior_latent_code[:, np.newaxis, :])
self.gen_obs_sample_dist = distributions.ProductDistribution(sample_properties = batch['observed']['properties'], params = self.gen_obs_sample_param)
self.gen_obs_sample = self.gen_obs_sample_dist.sample(b_mode=True)
else:
flow_parameters_list[i] = 1*tf.layers.dense(inputs = flow_param_input, units = curr_flow_class.required_num_parameters(n_dim), use_bias = True, activation = None)
serial_flow_list = []
for j in range(batch_size_np):
normalizing_flow_list = []
for i in range(len(flow_class_list)):
curr_param = None
if flow_parameters_list[i] is not None:
curr_param = flow_parameters_list[i][j, np.newaxis, :]
curr_flow_class = flow_class_list[i]
normalizing_flow_list.append(curr_flow_class(input_dim=n_dim, parameters=curr_param))
if curr_flow_class == transforms.NonLinearIARFlow:
normalizing_flow_list.append(transforms.GeneralInverseFlow(transform=normalizing_flow_list[-2]))
serial_flow_list.append(transforms.SerialFlow(normalizing_flow_list))
################################################################################################################################################################
def nonlinear_pixel_transformation_clousure(batch_input_pixels, b_inverse=False):
# input = [tf.shape(input_pixels)[0] (corresponding the individual pixels in a grid of output image), 2]
# output = [batch_size_tf, 2, tf.shape(input_pixels)[0]]
# serial_flow does not allow different transformations for each image in the batch
# See the note in linear_pixel_transformation_clousure for understanding the transformation.
output_pixels_list = []
for j in range(batch_size_np):
if b_inverse: curr_output_pixels, _ = serial_flow_list[j].inverse_transform(batch_input_pixels[j,:,:], None)
else: curr_output_pixels, _ = serial_flow_list[j].transform(batch_input_pixels[j,:,:], None)
output_pixels_list.append(curr_output_pixels[np.newaxis,:,:])
units=flow_class_1.required_num_parameters(n_dim),
use_bias=False,
activation=None)
normalizing_flow_list.append(
flow_class_1(input_dim=n_dim, parameters=flow_class_1_parameters))
flow_class_2_parameters = None
if flow_class_2.required_num_parameters(n_dim) > 0:
flow_class_2_parameters = 1 * tf.layers.dense(
inputs=tf.ones(shape=(1, 1)),
units=flow_class_2.required_num_parameters(n_dim),
use_bias=False,
activation=None)
normalizing_flow_list.append(
flow_class_2(input_dim=n_dim, parameters=flow_class_2_parameters))
serial_flow = transforms.SerialFlow(normalizing_flow_list)
start_mean = tf.zeros(shape=(batch_size_tf, n_dim))
start_log_var = tf.log(tf.ones(shape=(batch_size_tf, n_dim)) * 1)
start_dist = distributions.DiagonalGaussianDistribution(
params=tf.concat([start_mean, start_log_var], axis=1))
x_log_pdf = start_dist.log_pdf(x_input_tf)
x_transformed, x_transformed_log_pdf = serial_flow.transform(
x_input_tf, x_log_pdf)
# weights = [0.33, 0.33, 1-0.33-0.33]
# mean_1 = tf.zeros(shape=(batch_size_tf, n_dim))+np.asarray([-0.5, -0.5])[np.newaxis, :]
# mean_2 = tf.zeros(shape=(batch_size_tf, n_dim))+np.asarray([-0.5, +0.5])[np.newaxis, :]
# mean_3 = tf.zeros(shape=(batch_size_tf, n_dim))+np.asarray([+0.5, -0.5])[np.newaxis, :]
# log_var_1 = tf.log(tf.ones(shape=(batch_size_tf, n_dim))*0.3)
def inference(self, batch, additional_inputs_tf):
self.epoch = additional_inputs_tf[0]
self.b_identity = additional_inputs_tf[1]
if len(batch['observed']['properties']['flat']) > 0:
for e in batch['observed']['properties']['flat']:
e['dist'] = 'dirac'
else:
for e in batch['observed']['properties']['image']:
e['dist'] = 'dirac'
self.input_sample = batch['observed']['data']
self.input_dist = distributions.ProductDistribution(
sample_properties=batch['observed']['properties'],
params=self.input_sample)
if not self.bModules: self.generate_modules(batch)
try:
self.n_time = batch['observed']['properties']['flat'][0]['size'][1]
except:
self.n_time = batch['observed']['properties']['image'][0]['size'][
1]
try:
self.batch_size_tf = tf.shape(self.input_sample['flat'])[0]
except:
self.batch_size_tf = tf.shape(self.input_sample['image'])[0]
#############################################################################
# GENERATOR
self.flow_param_list = self.FlowMap.forward(batch)
self.wolf_param_list = self.WolfMap.forward(batch)
n_output = np.prod(
batch['observed']['properties']['image'][0]['size'][2:])
# Euclidean_flow_class = transforms.PiecewisePlanarScalingFlow
# Euclidean_flow_class = transforms.RealNVPFlow
Euclidean_flow_class = transforms.NonLinearIARFlow
self.pre_flow_object = transforms.SerialFlow([\
Euclidean_flow_class(input_dim=self.config['n_latent'], parameters=self.wolf_param_list[0]),
transforms.SpecificRotationFlow(input_dim=self.config['n_latent']),
Euclidean_flow_class(input_dim=self.config['n_latent'], parameters=self.wolf_param_list[1]),
transforms.SpecificRotationFlow(input_dim=self.config['n_latent']),
Euclidean_flow_class(input_dim=self.config['n_latent'], parameters=self.wolf_param_list[2]),
])
self.flow_object = transforms.SerialFlow([\
Euclidean_flow_class(input_dim=self.config['n_latent'], parameters=self.flow_param_list[0]),
transforms.SpecificRotationFlow(input_dim=self.config['n_latent']),
Euclidean_flow_class(input_dim=self.config['n_latent'], parameters=self.flow_param_list[1]),
transforms.RiemannianFlow(input_dim=self.config['n_latent'], output_dim=n_output, n_input_NOM=self.config['rnf_prop']['n_input_NOM'], n_output_NOM=self.config['rnf_prop']['n_output_NOM'], parameters=self.flow_param_list[-2]),
transforms.CompoundRotationFlow(input_dim=n_output, parameters=self.flow_param_list[-1]),
])
self.prior_param = self.PriorMap.forward(
(tf.zeros(shape=(self.batch_size_tf, 1)), ))
self.prior_dist = distributions.DiagonalGaussianDistribution(
params=self.prior_param)
self.prior_latent_code = self.prior_dist.sample()
self.pre_prior_latent_code, _ = self.pre_flow_object.inverse_transform(
self.prior_latent_code, tf.zeros(shape=(self.batch_size_tf, 1)))
self.transformed_prior_latent_code, _ = self.flow_object.transform(
self.pre_prior_latent_code,
tf.zeros(shape=(self.batch_size_tf, 1)))
self.obs_sample_param = {
'flat':
None,
'image':
tf.reshape(self.transformed_prior_latent_code, [
-1, 1, *batch['observed']['properties']['image'][0]['size'][2:]
])
}
self.obs_sample_dist = distributions.ProductDistribution(
sample_properties=batch['observed']['properties'],
params=self.obs_sample_param)
self.obs_sample = self.obs_sample_dist.sample(b_mode=True)
if not os.path.exists(
str(Path.home()) + '/ExperimentalResults/FixedSamples/'):
os.makedirs(
str(Path.home()) + '/ExperimentalResults/FixedSamples/')
if os.path.exists(
str(Path.home()) +
'/ExperimentalResults/FixedSamples/np_constant_prior_sample_' +
str(self.prior_latent_code.get_shape().as_list()[-1]) +
'.npz'):
np_constant_prior_sample = np.load(
str(Path.home()) +
'/ExperimentalResults/FixedSamples/np_constant_prior_sample_' +
str(self.prior_latent_code.get_shape().as_list()[-1]) + '.npz')
else:
np_constant_prior_sample = np.random.normal(
loc=0.,
scale=1.,
size=[400,
self.prior_latent_code.get_shape().as_list()[-1]])
np.save(
str(Path.home()) +
'/ExperimentalResults/FixedSamples/np_constant_prior_sample_' +
str(self.prior_latent_code.get_shape().as_list()[-1]) + '.npz',
np_constant_prior_sample)
self.constant_prior_latent_code = tf.constant(
np.asarray(np_constant_prior_sample), dtype=np.float32)
self.constant_pre_prior_latent_code, _ = self.pre_flow_object.inverse_transform(
self.constant_prior_latent_code,
tf.zeros(shape=(self.batch_size_tf, 1)))
self.constant_transformed_prior_latent_code, _ = self.flow_object.transform(
self.constant_pre_prior_latent_code,
tf.zeros(shape=(self.batch_size_tf, 1)))
self.constant_obs_sample_param = {
'flat':
None,
'image':
tf.reshape(self.constant_transformed_prior_latent_code, [
-1, 1, *batch['observed']['properties']['image'][0]['size'][2:]
])
}
self.constant_obs_sample_dist = distributions.ProductDistribution(
sample_properties=batch['observed']['properties'],
params=self.constant_obs_sample_param)
self.constant_obs_sample = self.constant_obs_sample_dist.sample(
b_mode=True)
# if self.config['n_latent'] == 2:
# grid_scale = 3
# x = np.linspace(-grid_scale, grid_scale, 20)
# y = np.linspace(grid_scale, -grid_scale, 20)
# xv, yv = np.meshgrid(x, y)
# np_constant_prior_grid_sample = np.concatenate((xv.flatten()[:, np.newaxis], yv.flatten()[:, np.newaxis][:]), axis=1)
# self.constant_grid_prior_latent_code = tf.constant(np.asarray(np_constant_prior_grid_sample), dtype=np.float32)
# self.constant_grid_pre_prior_latent_code, _ = self.pre_flow_object.inverse_transform(self.constant_grid_prior_latent_code, tf.zeros(shape=(self.batch_size_tf, 1)))
# self.constant_grid_transformed_prior_latent_code, _ = self.flow_object.transform(self.constant_grid_pre_prior_latent_code, tf.zeros(shape=(self.batch_size_tf, 1)))
# self.constant_grid_obs_sample_param = {'flat': None, 'image': tf.reshape(self.constant_grid_transformed_prior_latent_code, [-1, 1, *batch['observed']['properties']['image'][0]['size'][2:]])}
# self.constant_grid_obs_sample_dist = distributions.ProductDistribution(sample_properties = batch['observed']['properties'], params = self.constant_grid_obs_sample_param)
# self.constant_grid_obs_sample = self.constant_grid_obs_sample_dist.sample(b_mode=True)
#############################################################################
# ENCODER
if self.config['encoder_mode'] == 'Deterministic':
self.epsilon = None
if self.config['encoder_mode'] == 'Gaussian' or self.config[
'encoder_mode'] == 'GaussianLeastVariance' or self.config[
'encoder_mode'] == 'UnivApprox' or 'UnivApproxNoSpatial' in self.config[
'encoder_mode'] or self.config[
'encoder_mode'] == 'UnivApproxSine':
self.epsilon_param = self.EpsilonMap.forward(
(tf.zeros(shape=(self.batch_size_tf, 1)), ))
self.epsilon_dist = distributions.DiagonalGaussianDistribution(
params=self.epsilon_param)
self.epsilon = self.epsilon_dist.sample()
self.pre_posterior_latent_code_expanded, self.pre_posterior_latent_code_det_expanded = self.Encoder.forward(
self.input_sample, noise=self.epsilon)
self.pre_posterior_latent_code = self.pre_posterior_latent_code_expanded[:,
0, :]
self.posterior_latent_code, self.posterior_delta_log_pdf = self.pre_flow_object.transform(
self.pre_posterior_latent_code,
tf.zeros(shape=(self.batch_size_tf, 1)))
self.posterior_log_pdf = self.prior_dist.log_pdf(
self.posterior_latent_code)
self.pre_posterior_log_pdf = self.posterior_log_pdf - self.posterior_delta_log_pdf
# self.pre_posterior_latent_code, self.pre_posterior_log_pdf = self.pre_flow_object.inverse_transform(self.posterior_latent_code, self.posterior_log_pdf)
self.transformed_pre_posterior_latent_code, self.transformed_pre_posterior_log_pdf = self.flow_object.transform(
self.pre_posterior_latent_code, self.pre_posterior_log_pdf)
self.reconst_param = {
'flat':
None,
'image':
tf.reshape(self.transformed_pre_posterior_latent_code, [
-1, 1, *batch['observed']['properties']['image'][0]['size'][2:]
])
}
self.reconst_dist = distributions.ProductDistribution(
sample_properties=batch['observed']['properties'],
params=self.reconst_param)
self.reconst_sample = self.reconst_dist.sample(b_mode=True)
self.interpolated_posterior_latent_code = helper.interpolate_latent_codes(
self.posterior_latent_code, size=self.batch_size_tf // 2)
# self.interpolated_pre_posterior_latent_code, _ = self.pre_flow_object.inverse_transform(tf.reshape(self.interpolated_posterior_latent_code, [-1, self.interpolated_posterior_latent_code.get_shape().as_list()[-1]]), tf.zeros(shape=(self.batch_size_tf, 1)))
# self.interpolated_transformed_posterior_latent_code, _ = self.flow_object.transform(self.interpolated_pre_posterior_latent_code, tf.zeros(shape=(self.batch_size_tf, 1)))
# self.interpolated_obs = {'flat': None, 'image': tf.reshape(self.interpolated_transformed_posterior_latent_code, [-1, 10, *batch['observed']['properties']['image'][0]['size'][2:]])}
self.interpolated_obs = {
'flat':
None,
'image':
tf.tile(
self.input_sample['image'][:self.batch_size_tf //
2, :, :, :, :], [1, 10, 1, 1, 1])
}
self.enc_reg_cost = -tf.reduce_mean(
self.transformed_pre_posterior_log_pdf)
self.cri_reg_cost = -tf.reduce_mean(self.pre_posterior_log_pdf)
#############################################################################
# REGULARIZER
self.reg_target_dist = self.reconst_dist
self.reg_target_sample = self.reconst_sample
self.reg_dist = self.reconst_dist
self.reg_sample = self.reconst_sample
#############################################################################
# OBJECTIVES
self.OT_primal = self.sample_distance_function(self.input_sample,
self.reconst_sample)
self.mean_OT_primal = tf.reduce_mean(self.OT_primal)
if '0' in self.config['timers']:
lambda_t = helper.hardstep(
(self.epoch - float(self.config['timers']['0']['start'])) /
float(self.config['timers']['0']['timescale']) + 1e-5)
overall_cost = self.mean_OT_primal + lambda_t * self.config[
'enc_reg_strength'] * self.enc_reg_cost
else:
overall_cost = self.mean_OT_primal + self.config[
'enc_reg_strength'] * self.enc_reg_cost
# self.cri_cost = self.cri_reg_cost
# self.cri_cost = self.config['enc_reg_strength']*self.enc_reg_cost
self.cri_cost = self.enc_reg_cost
self.enc_cost = overall_cost
self.gen_cost = overall_cost
if flow_class_2.required_num_parameters(n_dim) > 0:
with tf.variable_scope("eft_second"+str(i), reuse=False):
flow_class_2_parameters = 1*tf.layers.dense(inputs = flow_param_input, units = flow_class_2.required_num_parameters(n_dim), use_bias = False, activation = None)
if flow_class_2_parameters.get_shape()[0].value is not None and flow_class_2_parameters.get_shape()[0].value == 1: batch_tile_2 = im_target_np.shape[0]
else: batch_tile_2 = 1
flow_class_2_parameters_tiled = tf.reshape(tf.tile(flow_class_2_parameters[:,np.newaxis,:], [batch_tile_2, im_target_np.shape[1]*im_target_np.shape[2], 1]), [-1, flow_class_2_parameters.get_shape()[-1].value])
flow_class_2_parameters_sampled_tiled = tf.reshape(tf.tile(flow_class_2_parameters[:,np.newaxis,:], [batch_tile_2, n_location_samples, 1]), [-1, flow_class_2_parameters.get_shape()[-1].value])
flow_class_2_parameters_location_tiled = tf.reshape(tf.tile(flow_class_2_parameters[:,np.newaxis,:], [batch_tile_2, loc_batch_size, 1]), [-1, flow_class_2_parameters.get_shape()[-1].value])
normalizing_flow_list.append(flow_class_2(input_dim=n_dim, parameters=flow_class_2_parameters_tiled))
normalizing_flow_sampled_list.append(flow_class_2(input_dim=n_dim, parameters=flow_class_2_parameters_sampled_tiled))
normalizing_flow_location_list.append(flow_class_2(input_dim=n_dim, parameters=flow_class_2_parameters_location_tiled))
serial_flow = transforms.SerialFlow(normalizing_flow_list)
serial_flow_sampled = transforms.SerialFlow(normalizing_flow_sampled_list)
serial_flow_location = transforms.SerialFlow(normalizing_flow_location_list)
location_input_tiled = tf.reshape(tf.tile(location_input_tf[np.newaxis, :, :], [batch_tile_2, 1, 1]), [-1, location_input_tf.get_shape()[-1].value])
location_transformed_raw, _ = serial_flow_location.inverse_transform(location_input_tiled, None)
location_transformed_tf = tf.reshape(location_transformed_raw, [batch_tile_2, loc_batch_size, location_input_tf.get_shape()[-1].value])
def clousure_of_closure(serial_flow):
def nonlinear_pixel_transformation_clousure(batch_input_pixels):
# input = [tf.shape(input_pixels)[0] (corresponding the individual pixels in a grid of output image), 2]
# output = [batch_size_tf, 2, tf.shape(input_pixels)[0]]
# serial_flow does not allow different transformations for each image in the batch
# See the note in linear_pixel_transformation_clousure for understanding the transformation.
input_pixels_flat = tf.reshape(batch_input_pixels, [-1, batch_input_pixels.get_shape()[-1].value])
output_pixels_flat, _ = serial_flow.transform(input_pixels_flat, None)
def inference(self, batch, additional_inputs_tf):
self.epoch = additional_inputs_tf[0]
self.b_identity = additional_inputs_tf[1]
if len(batch['observed']['properties']['flat'])>0:
for e in batch['observed']['properties']['flat']: e['dist']='dirac'
else:
for e in batch['observed']['properties']['image']: e['dist']='dirac'
self.input_sample = batch['observed']['data']
self.input_dist = distributions.ProductDistribution(sample_properties = batch['observed']['properties'], params = self.input_sample)
if not self.bModules: self.generate_modules(batch)
try: self.n_time = batch['observed']['properties']['flat'][0]['size'][1]
except: self.n_time = batch['observed']['properties']['image'][0]['size'][1]
try: self.batch_size_tf = tf.shape(self.input_sample['flat'])[0]
except: self.batch_size_tf = tf.shape(self.input_sample['image'])[0]
#############################################################################
# GENERATOR
self.pre_prior_param = self.PriorMap.forward((tf.zeros(shape=(self.batch_size_tf, 1)),))
# self.pre_prior_dist = distributions.UniformDistribution(params = self.pre_prior_param)
self.pre_prior_dist = distributions.DiagonalBetaDistribution(params = self.pre_prior_param)
self.pre_prior_latent_code = self.pre_prior_dist.sample()
self.pre_prior_latent_code_log_pdf = self.pre_prior_dist.log_pdf(self.pre_prior_latent_code)
self.ambient_prior_param = self.PriorMapBetaInverted.forward((tf.zeros(shape=(self.batch_size_tf, 1)),))
self.ambient_prior_dist = distributions.DiagonalBetaDistribution(params = self.ambient_prior_param)
self.flow_param_list = self.FlowMap.forward()
# self.flow_object = transforms.SerialFlow([ \
# transforms.InverseOpenIntervalDimensionFlow(input_dim=self.config['n_latent']),
# transforms.NonLinearIARFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[0]),
# transforms.SpecificOrderDimensionFlow(input_dim=self.config['n_latent']),
# transforms.NonLinearIARFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[1]),
# transforms.SpecificOrderDimensionFlow(input_dim=self.config['n_latent']),
# transforms.NonLinearIARFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[2]),
# transforms.SpecificOrderDimensionFlow(input_dim=self.config['n_latent']),
# transforms.NonLinearIARFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[3]),
# # transforms.SpecificOrderDimensionFlow(input_dim=self.config['n_latent']),
# # transforms.NonLinearIARFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[4]),
# # transforms.SpecificOrderDimensionFlow(input_dim=self.config['n_latent']),
# # transforms.NonLinearIARFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[5]),
# # transforms.SpecificOrderDimensionFlow(input_dim=self.config['n_latent']),
# # transforms.NonLinearIARFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[6]),
# transforms.OpenIntervalDimensionFlow(input_dim=self.config['n_latent']),
# ])
# self.flow_object = transforms.SerialFlow([ \
# transforms.InverseOpenIntervalDimensionFlow(input_dim=self.config['n_latent']),
# transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[0]),
# transforms.HouseholdRotationFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[7]),
# transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[1]),
# transforms.HouseholdRotationFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[8]),
# transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[2]),
# transforms.HouseholdRotationFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[9]),
# transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[3]),
# transforms.HouseholdRotationFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[10]),
# transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[4]),
# transforms.HouseholdRotationFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[11]),
# transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[5]),
# transforms.HouseholdRotationFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[12]),
# transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[6]),
# transforms.OpenIntervalDimensionFlow(input_dim=self.config['n_latent']),
# ])
self.flow_object = transforms.SerialFlow([ \
transforms.InverseOpenIntervalDimensionFlow(input_dim=self.config['n_latent']),
transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[0]),
transforms.SpecificOrderDimensionFlow(input_dim=self.config['n_latent']),
transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[1]),
transforms.SpecificOrderDimensionFlow(input_dim=self.config['n_latent']),
transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[2]),
transforms.SpecificOrderDimensionFlow(input_dim=self.config['n_latent']),
transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[3]),
# transforms.SpecificOrderDimensionFlow(input_dim=self.config['n_latent']),
# transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[4]),
# transforms.SpecificOrderDimensionFlow(input_dim=self.config['n_latent']),
# transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[5]),
# transforms.SpecificOrderDimensionFlow(input_dim=self.config['n_latent']),
# transforms.RealNVPFlow(input_dim=self.config['n_latent'], parameters=self.flow_param_list[6]),
transforms.OpenIntervalDimensionFlow(input_dim=self.config['n_latent']),
])
self.gen_flow_object = self.flow_object
self.prior_latent_code, self.prior_latent_code_log_pdf = self.flow_object.inverse_transform(self.pre_prior_latent_code, self.pre_prior_latent_code_log_pdf)
self.obs_sample_param = self.Generator.forward(self.prior_latent_code[:, np.newaxis, :])
self.obs_sample_dist = distributions.ProductDistribution(sample_properties = batch['observed']['properties'], params = self.obs_sample_param)
self.obs_sample = self.obs_sample_dist.sample(b_mode=True)
if not os.path.exists(str(Path.home())+'/ExperimentalResults/FixedSamples/'): os.makedirs(str(Path.home())+'/ExperimentalResults/FixedSamples/')
# if os.path.exists(str(Path.home())+'/ExperimentalResults/FixedSamples/np_constant_uniform11_prior_sample_'+str(self.pre_prior_latent_code.get_shape().as_list()[-1])+'.npz'):
if os.path.exists(str(Path.home())+'/ExperimentalResults/FixedSamples/np_constant_uniform01_prior_sample_'+str(self.pre_prior_latent_code.get_shape().as_list()[-1])+'.npz'):
# np_constant_prior_sample = np.load(str(Path.home())+'/ExperimentalResults/FixedSamples/np_constant_uniform11_prior_sample_'+str(self.pre_prior_latent_code.get_shape().as_list()[-1])+'.npz')
np_constant_prior_sample = np.load(str(Path.home())+'/ExperimentalResults/FixedSamples/np_constant_uniform01_prior_sample_'+str(self.pre_prior_latent_code.get_shape().as_list()[-1])+'.npz')
else:
# np_constant_prior_sample = np.random.uniform(low=-1., high=1., size=[400, self.pre_prior_latent_code.get_shape().as_list()[-1]])
np_constant_prior_sample = np.random.uniform(low=0., high=1., size=[400, self.pre_prior_latent_code.get_shape().as_list()[-1]])
# np.save(str(Path.home())+'/ExperimentalResults/FixedSamples/np_constant_uniform11_prior_sample_'+str(self.pre_prior_latent_code.get_shape().as_list()[-1])+'.npz', np_constant_prior_sample)
np.save(str(Path.home())+'/ExperimentalResults/FixedSamples/np_constant_uniform01_prior_sample_'+str(self.pre_prior_latent_code.get_shape().as_list()[-1])+'.npz', np_constant_prior_sample)
self.constant_pre_prior_latent_code = tf.constant(np.asarray(np_constant_prior_sample), dtype=np.float32)
self.constant_prior_latent_code, _ = self.flow_object.inverse_transform(self.constant_pre_prior_latent_code, tf.zeros(shape=(self.batch_size_tf, 1)))
self.constant_obs_sample_param = self.Generator.forward(self.constant_prior_latent_code[:, np.newaxis, :])
self.constant_obs_sample_dist = distributions.ProductDistribution(sample_properties = batch['observed']['properties'], params = self.constant_obs_sample_param)
self.constant_obs_sample = self.constant_obs_sample_dist.sample(b_mode=True)
if self.config['n_latent'] == 2:
# x = np.linspace(-1, 1, 20)
# y = np.linspace(1, -1, 20)
x = np.linspace(0, 1, 20)
y = np.linspace(1, 0, 20)
xv, yv = np.meshgrid(x, y)
np_constant_prior_grid_sample = np.concatenate((xv.flatten()[:, np.newaxis], yv.flatten()[:, np.newaxis][:]), axis=1)
self.constant_prior_grid_latent_code = tf.constant(np.asarray(np_constant_prior_grid_sample), dtype=np.float32)
self.constant_obs_grid_sample_param = self.Generator.forward(self.constant_prior_grid_latent_code[:, np.newaxis, :])
self.constant_obs_grid_sample_dist = distributions.ProductDistribution(sample_properties = batch['observed']['properties'], params = self.constant_obs_grid_sample_param)
self.constant_obs_grid_sample = self.constant_obs_grid_sample_dist.sample(b_mode=True)
#############################################################################
# ENCODER
self.epsilon_param = self.PriorMap.forward((tf.zeros(shape=(self.batch_size_tf, 1)),))
self.epsilon_dist = distributions.DiagonalGaussianDistribution(params=self.epsilon_param)
if self.config['encoder_mode'] == 'Deterministic':
self.epsilon = None
if self.config['encoder_mode'] == 'Gaussian' or self.config['encoder_mode'] == 'UnivApprox' or self.config['encoder_mode'] == 'UnivApproxNoSpatial' or self.config['encoder_mode'] == 'UnivApproxSine':
self.epsilon = self.epsilon_dist.sample()
# self.pre_posterior_latent_code = 0.95*tf.nn.tanh(self.Encoder.forward(self.input_sample, noise=self.epsilon))[:,0,:]
# self.pre_posterior_latent_code = 0.9*tf.nn.sigmoid(self.Encoder.forward(self.input_sample, noise=self.epsilon))[:,0,:]+0.05
self.pre_posterior_latent_code = 0.8*tf.nn.sigmoid(self.Encoder.forward(self.input_sample, noise=self.epsilon))[:,0,:]+0.1
self.nball_param = tf.concat([self.pre_posterior_latent_code, 0.05*tf.ones(shape=(self.batch_size_tf, 1))], axis=1)
self.nball_dist = distributions.UniformBallDistribution(params=self.nball_param)
self.posterior_latent_code = self.nball_dist.sample()
self.posterior_latent_code_log_pdf = -np.log(50000)+self.nball_dist.log_pdf(self.posterior_latent_code)
self.transformed_posterior_latent_code, self.transformed_posterior_latent_code_log_pdf = self.flow_object.transform(self.posterior_latent_code, self.posterior_latent_code_log_pdf)
self.hollow_nball_param = tf.concat([self.pre_posterior_latent_code, 0.05*tf.ones(shape=(self.batch_size_tf, 1)), 0.1*tf.ones(shape=(self.batch_size_tf, 1))], axis=1)
self.hollow_nball_dist = distributions.UniformHollowBallDistribution(params=self.hollow_nball_param)
self.hollow_posterior_latent_code = self.hollow_nball_dist.sample()
self.hollow_posterior_latent_code_log_pdf = -np.log(50000)+self.hollow_nball_dist.log_pdf(self.hollow_posterior_latent_code)
self.transformed_hollow_posterior_latent_code, self.transformed_hollow_posterior_latent_code_log_pdf = self.flow_object.transform(self.hollow_posterior_latent_code, self.hollow_posterior_latent_code_log_pdf)
self.ambient_param = self.AmbientMap.forward((tf.zeros(shape=(self.batch_size_tf, 1)),))
self.ambient_dist = distributions.UniformDistribution(params = self.ambient_param)
self.ambient_latent_code = self.ambient_dist.sample()
self.ambient_latent_code_log_pdf = self.ambient_dist.log_pdf(self.ambient_latent_code)
self.transformed_ambient_latent_code, self.transformed_ambient_latent_code_log_pdf = self.flow_object.transform(self.ambient_latent_code, self.ambient_latent_code_log_pdf)
self.KL_transformed_prior_per = self.transformed_posterior_latent_code_log_pdf-self.pre_prior_dist.log_pdf(self.transformed_posterior_latent_code)
self.KL_transformed_hollow_prior_per = self.transformed_hollow_posterior_latent_code_log_pdf-self.ambient_prior_dist.log_pdf(self.transformed_hollow_posterior_latent_code)
self.KL_transformed_ambient_prior_per = self.transformed_ambient_latent_code_log_pdf-self.ambient_prior_dist.log_pdf(self.transformed_ambient_latent_code)
self.KL_transformed_prior = tf.reduce_mean(self.KL_transformed_prior_per)
self.KL_transformed_hollow_prior = tf.reduce_mean(self.KL_transformed_hollow_prior_per)
self.KL_transformed_ambient_prior = tf.reduce_mean(self.KL_transformed_ambient_prior_per)
self.interpolated_posterior_latent_code = helper.interpolate_latent_codes(self.posterior_latent_code, size=self.batch_size_tf//2)
self.interpolated_obs = self.Generator.forward(self.interpolated_posterior_latent_code)
self.reconst_param = self.Generator.forward(self.posterior_latent_code[:, np.newaxis, :])
self.reconst_dist = distributions.ProductDistribution(sample_properties = batch['observed']['properties'], params = self.reconst_param)
self.reconst_sample = self.reconst_dist.sample(b_mode=True)
### Primal Penalty
#############################################################################
# REGULARIZER
self.reg_target_dist = self.reconst_dist
self.reg_target_sample = self.reconst_sample
self.reg_dist = self.reconst_dist
self.reg_sample = self.reconst_sample
#############################################################################
# OBJECTIVES
# Divergence
# if self.config['divergence_mode'] == 'GAN' or self.config['divergence_mode'] == 'NS-GAN':
# self.div_cost = -(tf.reduce_mean(tf.log(tf.nn.sigmoid(self.div_posterior)+10e-7))+tf.reduce_mean(tf.log(1-tf.nn.sigmoid(self.div_prior)+10e-7)))
# if self.config['divergence_mode'] == 'WGAN-GP':
# uniform_dist = distributions.UniformDistribution(params = tf.concat([tf.zeros(shape=(self.batch_size_tf, 1)), tf.ones(shape=(self.batch_size_tf, 1))], axis=1))
# uniform_w = uniform_dist.sample()
# self.trivial_line = uniform_w[:,np.newaxis,:]*self.pre_posterior_latent_code_expanded+(1-uniform_w[:,np.newaxis,:])*self.prior_latent_code_expanded
# self.div_trivial_line = self.Diverger.forward(self.trivial_line)
# self.trivial_line_grad = tf.gradients(tf.reduce_sum(self.div_trivial_line), [self.trivial_line])[0]
# self.trivial_line_grad_norm = helper.safe_tf_sqrt(tf.reduce_sum(self.trivial_line_grad**2, axis=-1, keep_dims=False)[:,:,np.newaxis])
# self.trivial_line_grad_norm_1_penalties = ((self.trivial_line_grad_norm-1)**2)
# self.div_reg_cost = tf.reduce_mean(self.trivial_line_grad_norm_1_penalties)
# # self.div_cost = -(tf.reduce_mean(self.div_posterior)-tf.reduce_mean(self.div_prior))+10*self.div_reg_cost
# self.div_cost = (self.KL_transformed_prior+self.KL_transformed_ambient_prior+self.KL_transformed_hollow_prior)
self.div_cost = (self.KL_transformed_prior+self.KL_transformed_hollow_prior)
# ### Encoder
# b_use_timer, timescale, starttime = False, 10, 5
self.OT_primal = self.sample_distance_function(self.input_sample, self.reconst_sample)
self.mean_OT_primal = tf.reduce_mean(self.OT_primal)
# if b_use_timer:
# self.mean_POT_primal = self.mean_OT_primal+helper.hardstep((self.epoch-float(starttime))/float(timescale))*self.config['enc_reg_strength']*self.enc_reg_cost
# else:
# self.mean_POT_primal = self.mean_OT_primal+self.config['enc_reg_strength']*self.enc_reg_cost
# self.enc_cost = self.mean_POT_primal
self.enc_cost = self.mean_OT_primal
# ### Critic
# # self.cri_cost = helper.compute_MMD(self.pre_prior_latent_code, self.prior_latent_code)
# if self.config['divergence_mode'] == 'NS-GAN':
# self.cri_cost = -tf.reduce_mean(tf.log(tf.nn.sigmoid(self.div_prior)+10e-7))+self.config['enc_reg_strength']*helper.compute_MMD(self.pre_prior_latent_code, self.prior_latent_code)
# elif self.config['divergence_mode'] == 'GAN':
# self.cri_cost = tf.reduce_mean(tf.log(1-tf.nn.sigmoid(self.div_prior)+10e-7))+self.config['enc_reg_strength']*helper.compute_MMD(self.pre_prior_latent_code, self.prior_latent_code)
# elif self.config['divergence_mode'] == 'WGAN-GP':
# self.cri_cost = -tf.reduce_mean(self.div_prior)+self.config['enc_reg_strength']*helper.compute_MMD(self.pre_prior_latent_code, self.prior_latent_code)
### Generator
self.gen_cost = self.mean_OT_primal
################################# TF training ##################################################################
if use_gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
print("os.environ['CUDA_VISIBLE_DEVICES'], ", os.environ['CUDA_VISIBLE_DEVICES'])
x_input = tf.placeholder(tf.float32, [None, n_out])
batch_size_tf = tf.shape(x_input)[0]
n_RF_parameter = transforms.RiemannianFlow.required_num_parameters(n_latent, n_out, n_input_CPO, n_output_CPO)
n_HF_parameter = transforms.HouseholdRotationFlow.required_num_parameters(n_out)
riemannian_flow_parameters = 1*tf.layers.dense(inputs = tf.ones(shape=(1, 1)), units = n_RF_parameter, use_bias = False, activation = None)
householder_flow_parameters = 1*tf.layers.dense(inputs = tf.ones(shape=(1, 1)), units = n_HF_parameter, use_bias = False, activation = None)
riemannian_flow = transforms.RiemannianFlow(input_dim=n_latent, output_dim=n_out, n_input_CPO=n_input_CPO, n_output_CPO=n_output_CPO, parameters=riemannian_flow_parameters)
householder_flow = transforms.HouseholdRotationFlow(input_dim=n_out, parameters=householder_flow_parameters)
serial_flow = transforms.SerialFlow([riemannian_flow, householder_flow])
prior_param = tf.zeros((batch_size_tf, 2*n_latent), tf.float32)
prior_dist = distributions.DiagonalGaussianDistribution(params=prior_param)
lay_1 = tf.layers.dense(inputs = x_input, units = 200, use_bias = True, activation = tf.nn.relu)
lay_2 = lay_1+tf.layers.dense(inputs = lay_1, units = 200, use_bias = True, activation = tf.nn.relu)
lay_3 = lay_2+tf.layers.dense(inputs = lay_2, units = 200, use_bias = True, activation = tf.nn.relu)
lay_4 = lay_3+tf.layers.dense(inputs = lay_3, units = 200, use_bias = True, activation = tf.nn.relu)
z_x = tf.layers.dense(inputs = lay_4, units = n_latent, use_bias = True, activation = None)
log_pdf_z_x = prior_dist.log_pdf(z_x)
x_rec, log_pdf_x_rec = serial_flow.transform(z_x, log_pdf_z_x)
rec_cost = 100*tf.reduce_mean(tf.reduce_sum((x_rec-x_input)**2, axis=1))
# rec_cost = tf.reduce_mean(tf.reduce_sum((x_rec-x_input)**2, axis=1))
optimizer = tf.train.AdamOptimizer(learning_rate=0.001, beta1=0.1, beta2=0.1, epsilon=1e-08)
