def encoder(x, comp_ratio, activation='prelu'):
input_dim = x.shape[-1] #tf.shape(x)[-1]
num_filters = int(np.log2(comp_ratio))
h = x;
if apply_BN:
h = batch_norm(h, 'enc_batch_norm_{}'.format(0))
for i in range(num_filters):
print('enc_layer_number = ', i)
print('h_dim= ', h.get_shape().as_list())
with tf.variable_scope('g_enc'):
h = downconv(h, filter_width=filter_width, name='downconv_{}'.format(i))
if apply_BN:
h = batch_norm(h, 'batch_norm_{}'.format(i))
if activation=='leakyrelu':
h = leakyrelu(h)
else:
with tf.variable_scope('g_enc'):
h , _ = prelu(h, name='prelu_{}'.format(i))
# with tf.variable_scope('g_enc'):
# w_full_enc = tf.get_variable('w_full_enc', [ input_dim / (2**num_filters), input_dim / comp_ratio],
# initializer= tf.random_normal_initializer(stddev=0.01))
# h = full_layer(h, w_full_enc, 'g_enc')
return h
def decoder(x, comp_ratio, activation='leakyrelu', nonlin='segan'): #gated_conv'):
input_dim = x.shape[-1] #tf.shape(x)[-1]
num_filters = int(np.log2(comp_ratio))
h=x;
if apply_BN:
h = batch_norm (h, 'dec_batch_norm_{}'.format(0))
# with tf.variable_scope('g_dec'):
# w_full_dec = tf.get_variable('w_full_dec', [input_dim ,
# input_dim * comp_ratio / (2**num_filters) + 1],
# initializer= tf.random_normal_initializer(stddev=0.02))
# h = full_layer(x, w_full_dec, 'g_dec')
for i in range(num_filters):
print('dec_layer_number = ', i)
print('h_dim= ', h.get_shape().as_list())
with tf.variable_scope('g_dec'):
if nonlin=='segan':
#original segan
h = nn_deconv(h, filter_width=filter_width, name='nn_deconv_{}'.format(i),
dilation=2, init=tf.truncated_normal_initializer(stddev=0.02))
if apply_BN:
h = batch_norm (h, 'batch_norm_{}'.format(i))
if activation=='leakyrelu':
h = leakyrelu(h)
else:
with tf.variable_scope('g_dec'):
h,_ = prelu(h, name='prelu_{}'.format(i))
else:
# Wavenet gated convolutions
h = gated_deconv(h, filter_width=filter_width, name='gated_deconv_{}'.format(i),
dilation=2, init=tf.truncated_normal_initializer(stddev=0.02))
return h
def decoder(x, activation='leakyrelu', nonlin='segan'): #gated_conv'):
# input_dim = x.shape[-1]
num_filters = int(np.log2(comp_ratio))
h = x
for i in range(num_filters):
print('dec_layer_number = ', i)
with tf.variable_scope('g_dec'):
if nonlin == 'segan':
#original segan
h = nn_deconv(
h,
filter_width=filter_width,
name='nn_deconv_{}'.format(i),
dilation=2,
init=tf.truncated_normal_initializer(stddev=0.02))
h = batch_norm(h, 'batch_norm_{}'.format(i))
if activation == 'leakyrelu':
h = leakyrelu(h)
else:
with tf.variable_scope('g_dec'):
h, _ = prelu(h, name='prelu_{}'.format(i))
else:
# Wavenet gated convolutions
h = gated_deconv(
h,
filter_width=filter_width,
name='gated_deconv_{}'.format(i),
dilation=2,
init=tf.truncated_normal_initializer(stddev=0.02))
return h
def decoder(x,
comp_ratio,
activation='leakyrelu',
nonlin='segan'): #gated_conv'):
input_dim = x.shape[-1] #tf.shape(x)[-1]
num_filters = int(np.log2(comp_ratio))
h = x
if apply_BN:
h = batch_norm(h, 'dec_batch_norm_{}'.format(0))
for i in range(num_filters):
print('dec_layer_number = ', i)
print('h_dim= ', h.get_shape().as_list())
with tf.variable_scope('g_dec'):
if nonlin == 'segan':
#original segan
h = mf_nn_deconv(
h,
output_dim=2**(num_filters - i - 1),
filter_width=filter_width,
name='nn_deconv_{}'.format(i),
dilation=4,
init=tf.truncated_normal_initializer(stddev=0.02))
if apply_BN:
h = batch_norm(h, 'batch_norm_{}'.format(i))
if activation == 'leakyrelu':
h = leakyrelu(h)
else:
with tf.variable_scope('g_dec'):
h, _ = prelu(h, name='prelu_{}'.format(i))
else:
# Wavenet gated convolutions
h = gated_deconv(
h,
filter_width=filter_width,
name='gated_deconv_{}'.format(i),
dilation=2,
init=tf.truncated_normal_initializer(stddev=0.02))
# making h of size [num_batch, input_dim]
h = tf.squeeze(h, axis=-1)
return h
def encoder(x, comp_ratio, activation='prelu'):
input_dim = x.shape[-1] #x.get_shape().as_list()[-1]
num_filters = int(np.log2(comp_ratio))
h = x
if apply_BN:
h = batch_norm(h, 'enc_batch_norm_{}'.format(0))
for i in range(num_filters):
print('enc_layer_number = ', i)
print('h_dim= ', h.get_shape().as_list())
with tf.variable_scope('g_enc'):
h = mf_downconv(h,
output_dim=2**i,
stride=4,
filter_width=filter_width,
name='downconv_{}'.format(i))
if apply_BN:
h = batch_norm(h, 'batch_norm_{}'.format(i))
if activation == 'leakyrelu':
h = leakyrelu(h)
else:
with tf.variable_scope('g_enc'):
h, _ = prelu(h, name='prelu_{}'.format(i))
return h
def encoder(x, activation='prelu'):
num_filters = int(np.log2(comp_ratio))
h = x
hs = []
for i in range(num_filters):
print('enc_layer_number = ', i)
hs.append(h)
with tf.variable_scope('g_enc'):
h = downconv(h,
filter_width=filter_width,
name='downconv_{}'.format(i))
h = batch_norm(h, 'batch_norm_{}'.format(i))
if activation == 'leakyrelu':
h = leakyrelu(h)
else:
with tf.variable_scope('g_enc'):
h, _ = prelu(h, name='prelu_{}'.format(i))
return h, hs
def side_net(hs, mode):
# input_dim = hs[0].get_shape().as_list()[-1]
num_filters = len(hs)
# code_lengths = input_dim/50 * np.power(2, range(num_filters,0,-1))
# print('code_lengths', code_lengths)
ps_q = []
for i in range(len(hs)):
with tf.variable_scope('g_side_' + str(i)):
h_temp = downconv(hs[i],
filter_width=filter_width /
(2**(num_filters - i)),
stride=2**(comp_ratio - i),
name='downconv')
# h_temp = downconv(hs[i], filter_width=filter_width, stride=2,
# name='downconv')
h_temp = batch_norm(h_temp, 'batch_norm_{}'.format(i))
ps_q.append(binary_quantizer(h_temp, mode))
return ps_q