def __init__(self, images=None, targets=None, name='network'):
"""
Class constructor. Creates the model and all the connections.
"""
with tf.variable_scope(name + '_feed') as scope:
self.images = images
self.name = name
self.back_prop = None
# Unflatten Layer
images_square = unflatten_layer(self.images)
visualize_images(images_square)
# Placeholder probability for dropouts.
self.dropout_prob = tf.placeholder_with_default(
input=tf.constant(1.0, dtype=tf.float32),
shape=None,
name='dropout_probability')
self.targets = targets
if self.targets is None:
self.targets = tf.placeholder(tf.float32,
shape=[None, 10],
name='targets')
self.obj = 0.
self.parmas = []
self._build() # This method needs to be written in the new class.
def __init__(self,
images,
expert,
novice,
labels,
input_params=None,
name='judge'):
"""
Class constructor. Creates the model and all the connections.
"""
self.labels = labels
with tf.variable_scope(name) as scope:
self.images = images
self.name = name
# Unflatten Layer
images_square = unflatten_layer(self.images)
visualize_images(images_square)
# Placeholder probability for dropouts.
#self.dropout_prob = tf.placeholder(tf.float32,
self.dropout_prob = tf.placeholder_with_default(
input=tf.constant(1.0, dtype=tf.float32),
shape=None,
name='dropout_probability')
# Dropout Layer 1
dropped_out = dropout_layer(input=self.images,
prob=self.dropout_prob,
name='dropout_1')
# Embedding layers
expert_embed, params = dot_product_layer(
input=expert,
neurons=INFERENCE_EMBED,
name='expert_embed_inference')
novice_embed, params = dot_product_layer(
input=novice,
neurons=INFERENCE_EMBED,
params=params,
name='novice_embed_inference')
process_params(params, name=self.name)
image_embed, params = dot_product_layer(input=self.images,
neurons=IMAGE_EMBED,
name='embed_image')
process_params(params, name=self.name)
merged_expert = tf.concat([expert_embed, image_embed], 1)
merged_novice = tf.concat([novice_embed, image_embed], 1)
# Merged Expert Dropout Layer 1
merged_expert_dropout_1 = dropout_layer(
input=merged_expert,
prob=self.dropout_prob,
name='merged_expert_dropout_1')
# Merged Novice Dropout Layer 1
merged_novice_dropout_1 = dropout_layer(
input=merged_novice,
prob=self.dropout_prob,
name='merged_novice_dropout_1')
# Merged Expert Dot Product Layer 1
merged_expert_fc1_out, params = dot_product_layer(
input=merged_expert_dropout_1,
neurons=MERGED_D1,
name='merged_expert_d1')
# Merged Novice Dot Product Layer 1
merged_novice_fc1_out, params = dot_product_layer(
input=merged_novice_dropout_1,
params=params,
neurons=MERGED_D1,
name='merged_novice_d1')
process_params(params, name=self.name)
# Merged Expert Dropout Layer 2
merged_expert_dropout_2 = dropout_layer(
input=merged_expert_fc1_out,
prob=self.dropout_prob,
name='merged_expert_dropout_2')
# Merged Novice Dropout Layer 2
merged_novice_dropout_2 = dropout_layer(
input=merged_novice_fc1_out,
prob=self.dropout_prob,
name='merged_novice_dropout_2')
# Merged Expert Dot Product Layer 2
merged_expert_fc2_out, params = dot_product_layer(
input=merged_expert_dropout_2,
neurons=MERGED_D2,
name='merged_expert_d2')
# Merged Novice Dot Product Layer 2
merged_novice_fc2_out, params = dot_product_layer(
input=merged_novice_dropout_2,
params=params,
neurons=MERGED_D2,
name='merged_novice_d2')
process_params(params, name=self.name)
self.judgement_expert, params = dot_product_layer(
input=merged_expert_fc2_out,
neurons=1,
activation='sigmoid',
name='expert_probability')
self.judgement_novice, params = dot_product_layer(
input=merged_novice_fc2_out,
neurons=1,
params=params,
activation='sigmoid',
name='novice_probability')
process_params(params, name=self.name)
def __init__(self, images, name='expert'):
"""
Class constructor. Creates the model and allthe connections.
"""
with tf.variable_scope(name) as scope:
self.images = images
self.name = name
# Unflatten Layer
images_square = unflatten_layer(self.images)
visualize_images(images_square)
# Conv Layer 1
conv1_out, params = conv_2d_layer(input=images_square,
neurons=EXPERT_C1,
filter_size=EXPERT_F1,
name='conv_1',
visualize=True)
process_params(params, name=self.name)
pool1_out = max_pool_2d_layer(input=conv1_out, name='pool_1')
lrn1_out = local_response_normalization_layer(pool1_out,
name='lrn_1')
# Conv Layer 2
conv2_out, params = conv_2d_layer(input=lrn1_out,
neurons=EXPERT_C2,
filter_size=EXPERT_F2,
name='conv_2')
process_params(params, name=self.name)
pool2_out = max_pool_2d_layer(input=conv2_out, name='pool_2')
lrn2_out = local_response_normalization_layer(pool2_out,
name='lrn_2')
flattened = flatten_layer(lrn2_out)
# Placeholder probability for dropouts.
self.dropout_prob = tf.placeholder_with_default(
input=tf.constant(1.0, dtype=tf.float32),
shape=None,
name='dropout_probability')
# Dropout Layer 1
flattened_dropout = dropout_layer(input=flattened,
prob=self.dropout_prob,
name='dropout_1')
# Dot Product Layer 1
fc1_out, params = dot_product_layer(input=flattened_dropout,
neurons=EXPERT_D1,
name='dot_1')
process_params(params, name=self.name)
# Dropout Layer 2
fc1_out_dropout = dropout_layer(input=fc1_out,
prob=self.dropout_prob,
name='dropout_2')
# Dot Product Layer 2
fc2_out, params = dot_product_layer(input=fc1_out_dropout,
neurons=EXPERT_D2,
name='dot_2')
process_params(params, name=self.name)
# Dropout Layer 3
fc2_out_dropout = dropout_layer(input=fc2_out,
prob=self.dropout_prob,
name='dropout_3')
# Logits layer
self.logits, params = dot_product_layer(input=fc2_out_dropout,
neurons=C,
activation='identity',
name='logits_layer')
process_params(params, name=self.name)
# Softmax layer
self.inference, self.predictions = softmax_layer(
input=self.logits, name='softmax_layer')
# Temperature Softmax layer
self.temperature_softmax, _ = softmax_layer(
input=self.logits,
temperature=TEMPERATURE,
name='temperature_softmax_layer')
def __init__(self, images, input_params=None, name='novice'):
"""
Class constructor. Creates the model and allthe connections.
"""
with tf.variable_scope(name) as scope:
self.images = images
self.name = name
# self.decoder = decoder
# Unflatten Layer
images_square = unflatten_layer(self.images)
visualize_images(images_square)
# Placeholder probability for dropouts.
#self.dropout_prob = tf.placeholder(tf.float32,
self.dropout_prob = tf.placeholder_with_default(
input=tf.constant(1.0, dtype=tf.float32),
shape=None,
name='dropout_probability')
# Dropout Layer 1
dropped_out = dropout_layer(input=self.images,
prob=self.dropout_prob,
name='dropout_1')
# Dot Product Layer 1
par = None
# Dot Product Layer 1
if input_params is not None:
par = input_params[0]
fc1_out, params = dot_product_layer(input=dropped_out,
neurons=NOVICE_D1,
params=par,
name='dot_1')
process_params(params, name=self.name)
# d1_params = params
# Unflatten Layer
visualize_1D_filters(params[0])
# Dropout Layer 2
fc1_out_dropout = dropout_layer(input=fc1_out,
prob=self.dropout_prob,
name='dropout_2')
# Dot Product Layer 2
par = None
# Dot Product Layer 1
if input_params is not None:
par = input_params[1]
fc2_out, params = dot_product_layer(input=fc1_out_dropout,
neurons=NOVICE_D2,
params=par,
name='dot_2')
process_params(params, name=self.name)
# d2_params = params
# Dropout Layer 3
fc2_out_dropout = dropout_layer(input=fc2_out,
prob=self.dropout_prob,
name='dropout_3')
# Logits layer
self.logits, params = dot_product_layer(input=fc2_out_dropout,
neurons=C,
activation='identity',
name='logits_layer')
process_params(params, name=self.name)
# Softmax layer
self.inference, self.predictions = softmax_layer(
input=self.logits, name='softmax_layer')
# Temperature Softmax layer
self.temperature_softmax, _ = softmax_layer(
input=self.logits,
temperature=TEMPERATURE,
name='temperature_softmax_layer')
def _build(self):
"""
This method builds the network architecture.
"""
with tf.variable_scope(self.name + '_architecutre') as scope:
images_square = unflatten_layer(self.images)
visualize_images(images_square)
# Conv Layer 1
conv1_out, params = conv_2d_layer(input=images_square,
neurons=CONV_1_N,
filter_size=CONV_1_FILT,
name='enc_conv_1',
visualize=True)
process_params(params, name=self.name)
e1_params = params
pool1_out = max_pool_2d_layer(input=conv1_out, name='enc_pool_1')
# lrn1_out = local_response_normalization_layer (pool1_out, name = 'lrn_1' )
# Conv Layer 2
conv2_out, params = conv_2d_layer(input=pool1_out,
neurons=CONV_2_N,
filter_size=CONV_2_FILT,
name='enc_conv_2')
process_params(params, name=self.name)
e2_params = params
pool2_out = max_pool_2d_layer(input=conv2_out, name='enc_pool_2')
# lrn2_out = local_response_normalization_layer (pool2_out, name = 'lrn_2' )
flattened = flatten_layer(pool2_out)
# Dropout Layer 1
flattened_dropout = dropout_layer(input=flattened,
prob=self.dropout_prob,
name='enc_dropout_1')
# Dot Product Layer 1
fc1_out, params = dot_product_layer(input=flattened_dropout,
neurons=HIDDEN_1,
name='enc_dot_1')
process_params(params, name=self.name)
e3_params = params
# Dropout Layer 2
fc1_out_dropout = dropout_layer(input=fc1_out,
prob=self.dropout_prob,
name='enc_dropout_2')
# Dot Product Layer 2
fc2_out, params = dot_product_layer(input=fc1_out_dropout,
neurons=HIDDEN_2,
name='enc_dot_2')
process_params(params, name=self.name)
e4_params = params
# Dropout Layer 3
fc2_out_dropout = dropout_layer(input=fc2_out,
prob=self.dropout_prob,
name='enc_dropout_3')
# Dot Product Layer 2
self.codeword, params = dot_product_layer(
input=fc2_out_dropout,
neurons=CODEWORD_LENGTH,
activation=CODE_ACTIVATION,
name='enc_dot_2')
process_params(params, name=self.name)
process_codeword_normalization_regularizer(
self.codeword,
coeff=AUTOENCODER_CODEWORD_COEFF,
name=self.name)
e5_params = params
# tf.summary.histogram('codewords', self.codeword)
# self.hash = threshold_layer ( input = self.codeword,
# name = 'hash')
# process_hash_regularizer(self.codeword, coeff = AUTOENCODER_HASH_COEFF,
# name = self.name)
# Decoder ...
decoder_1_out, params = dot_product_layer(
input=self.codeword,
neurons=HIDDEN_2,
params=[tf.transpose(e5_params[0]), None],
name='decoder_dot_1')
d1_params = params
process_params([params[1]], name=self.name)
dec_1_out_dropout = dropout_layer(input=decoder_1_out,
prob=self.dropout_prob,
name='dec_dropout_1')
decoder_2_out, params = dot_product_layer(
input=dec_1_out_dropout,
neurons=HIDDEN_1,
params=[tf.transpose(e4_params[0]), None],
name='decoder_dot_2')
d2_params = params
process_params([params[1]], name=self.name)
# dropout 2
dec_2_out_dropout = dropout_layer(input=decoder_2_out,
prob=self.dropout_prob,
name='dec_dropout_2')
decoder_3_out, params = dot_product_layer(
input=dec_2_out_dropout,
neurons=1250,
params=[tf.transpose(e3_params[0]), None],
name='decoder_dot_3')
d3_params = params
process_params([params[1]], name=self.name)
# DeConv Layer 1
# The output shapes need to be changed according to architecture.
dec_3_square = unflatten_layer(decoder_3_out, channels=CONV_2_N)
upsample_1 = upsampling_layer(dec_3_square,
size=(10, 10),
name='dec_upsampling_1')
deconv1_out, params = deconv_2d_layer(
input=upsample_1,
neurons=CONV_1_N,
filter_size=CONV_2_FILT,
output_shape=(12, 12),
# n_outs = MINI_BATCH_SIZE,
stride=(1, 1, 1, 1),
params=[e2_params[0], None],
name='dec_deconv_1')
process_params([params[1]], name=self.name)
d4_params = params
# DeConv Layer 2
upsample_2 = upsampling_layer(deconv1_out,
size=(24, 24),
name='dec_upsampling_2')
decoded_images_square, params = deconv_2d_layer(
input=upsample_2,
neurons=1,
filter_size=CONV_1_FILT,
stride=(1, 1, 1, 1),
output_shape=(28, 28),
# n_outs = MINI_BATCH_SIZE,
params=[e1_params[0], None],
activation='tanh',
name='dec_deconv_2')
process_params([params[1]], name=self.name)
d5_params = params
self.decoded = flatten_layer(decoded_images_square,
in_shp=[-1, 28, 28, 1])
visualize_images(decoded_images_square, name='decoded')
# This is because transpose don't initialize.
self.params = [[e5_params[0], d1_params[1]],
[e4_params[0], d2_params[1]],
[e3_params[0], d3_params[1]],
[e2_params[0], d4_params[1]],
[e1_params[0], d5_params[1]]]
with tf.variable_scope(self.name + '_objectives') as scope:
with tf.variable_scope(self.name + '_decoder_error') as scope:
reconstruction_error = rmse(self.images, self.decoded)
tf.add_to_collection(self.name + '_objectives',
reconstruction_error)
tf.summary.scalar('reconstruction_error', reconstruction_error)
self._cook_optimizer(lr=AUTOENCODER_LR,
optimizer=AUTOENCODER_OPTIMIZER,
l1_coeff=AUTOENCODER_L1_COEFF,
l2_coeff=AUTOENCODER_WEIGHT_DECAY_COEFF)
def _build(self, z, targets=None, input_params=None):
"""
This method builds the network architecture.
Args:
input_params: list of paramers.
"""
with tf.variable_scope(self.name + '_architecture') as scope:
with tf.variable_scope('generator') as scope:
self.z = z
self.targets = targets
# Dot Product Layer 1
par = input_params[0]
process_params(par, name=self.name)
par[0] = tf.transpose(par[0])
# Decoder ...
decoder_1_out, params = dot_product_layer(
input=self.z,
neurons=HIDDEN_2,
params=par,
name='gen_decoder_dot_1')
g1_params = params
dec_1_out_dropout = dropout_layer(input=decoder_1_out,
prob=self.dropout_prob,
name='gen_dropout_1')
# Dot Product Layer 2
par = input_params[1]
process_params(par, name=self.name)
par[0] = tf.transpose(par[0])
decoder_2_out, params = dot_product_layer(
input=dec_1_out_dropout,
neurons=HIDDEN_1,
params=par,
name='gen_decoder_dot_2')
g2_params = params
dec_2_out_dropout = dropout_layer(input=decoder_2_out,
prob=self.dropout_prob,
name='gen_dropout_2')
# Dot Product Layer 3
par = input_params[2]
process_params(par, name=self.name)
par[0] = tf.transpose(par[0])
decoder_3_out, params = dot_product_layer(
input=dec_2_out_dropout,
neurons=1250,
params=par,
name='gen_decoder_dot_0')
g3_params = params
dec_3_square = unflatten_layer(decoder_3_out,
channels=CONV_2_N,
name='gen_unflatten')
upsample_1 = upsampling_layer(dec_3_square,
size=(10, 10),
name='gen_upsampling_1')
# Convolution layer 1
par = input_params[3]
process_params(par, name=self.name)
deconv1_out, params = deconv_2d_layer(input=upsample_1,
neurons=CONV_1_N,
filter_size=CONV_2_FILT,
output_shape=(12, 12),
params=par,
name='deconv_1')
g4_params = params
# DeConv Layer 2
par = input_params[4]
process_params(par, name=self.name)
upsample_2 = upsampling_layer(deconv1_out,
size=(24, 24),
name='gen_upsampling_2')
generated_images_square, params = deconv_2d_layer(
input=upsample_2,
neurons=1,
filter_size=CONV_1_FILT,
stride=(1, 1, 1, 1),
output_shape=(28, 28),
params=par,
activation='tanh',
name='conv_2')
g5_params = params
self.generation = flatten_layer(generated_images_square,
in_shp=[-1, 28, 28, 1])
visualize_images(generated_images_square,
name='generated_images')
self.params = [
g1_params, g2_params, g3_params, g4_params, g5_params
]