def __init__(self, mixed_mag, is_training, reuse, name):
"""
input_tensor: Tensor with shape [batch_size, height, width, channels]
is_training: Boolean - should the model be trained on the current input or not
name: Model instance name
"""
with tf.variable_scope(name):
self.mixed_mag = mixed_mag
with tf.variable_scope('Convolution'):
net = mf.relu(mixed_mag)
net = mf.conv(net, filters=128, kernel_size=5, stride=(1, 1))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
self.conv1 = net
with tf.variable_scope('Primary_Caps'):
net = mf.relu(net)
net = mf.conv(net, filters=128, kernel_size=5, stride=(1, 1))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
self.primary_caps = net
with tf.variable_scope('Seg_Caps'):
net = mf.relu(net)
net = mf.conv(net, filters=16, kernel_size=5, stride=(1, 1))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
self.seg_caps = net
with tf.variable_scope('Mask'):
net = mf.relu(net)
net = mf.conv(mixed_mag, filters=1, kernel_size=5, stride=(1, 1))
self.voice_mask = net
self.output = net
def __init__(self, input_tensor, is_training, reuse, name):
"""
input_tensor: Tensor with shape [batch_size, height, width, channels]
is_training: Boolean - should the model be trained on the current input or not
name: Model instance name
"""
with tf.variable_scope(name):
self.input_tensor = input_tensor
if tf.rank(self.input_tensor) == 3:
self.out_depth = 1
else:
self.out_depth = input_tensor.shape[3].value
with tf.variable_scope('layer_1'):
net = mf.relu(input_tensor)
net = mf.conv(net, filters=128, kernel_size=5, stride=(1, 1))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
self.l1 = net
with tf.variable_scope('layer_2'):
net = mf.relu(net)
net = mf.conv(net, filters=128, kernel_size=5, stride=(1, 1))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
self.l2 = net
with tf.variable_scope('layer_3'):
net = mf.relu(net)
net = mf.conv(net, filters=16, kernel_size=5, stride=(1, 1))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
self.l3 = net
with tf.variable_scope('mask'):
net = mf.relu(net)
net = mf.conv(net,
filters=self.out_depth,
kernel_size=5,
stride=(1, 1))
self.voice_mask = net
self.output = net
def __init__(self, input_tensor, encoder, data_type, is_training, reuse):
self.input_tensor = input_tensor
self.input_depth = self.input_tensor.shape[3]
with tf.variable_scope('decoder'):
with tf.variable_scope('layer-1'):
net = mf.relu(self.input_tensor)
net = mf.deconv(net,
filters=128,
kernel_size=(5, 5, self.input_depth),
stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
net = mf.dropout(net, .5)
with tf.variable_scope('layer-2'):
net = mf.relu(mf.concat(net, encoder.l5))
net = mf.deconv(net,
filters=64,
kernel_size=(5, 5, self.input_depth),
stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
net = mf.dropout(net, .5)
with tf.variable_scope('layer-3'):
net = mf.relu(mf.concat(net, encoder.l4))
net = mf.deconv(net,
filters=32,
kernel_size=(5, 5, self.input_depth),
stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
net = mf.dropout(net, .5)
with tf.variable_scope('layer-4'):
net = mf.relu(mf.concat(net, encoder.l3))
net = mf.deconv(net,
filters=16,
kernel_size=(5, 5, self.input_depth),
stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
with tf.variable_scope('layer-5'):
net = mf.relu(mf.concat(net, encoder.l2))
net = mf.deconv(net,
filters=8,
kernel_size=(5, 5, self.input_depth),
stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
with tf.variable_scope('layer-6'):
if data_type == 'mag_phase_real_imag':
self.out_depth = 2
else:
self.out_depth = encoder.input_tensor.shape[3]
net = mf.relu(mf.concat(net, encoder.l1))
net = mf.deconv(net,
filters=1,
kernel_size=(5, 5, self.out_depth),
stride=(2, 2))
self.output = net
def __init__(self, input_tensor, encoder, data_type, is_training, reuse):
net = input_tensor
with tf.variable_scope('decoder'):
with tf.variable_scope('layer-1'):
net = mf.relu(net)
net = mf.deconv(net, filters=256, kernel_size=5, stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
net = mf.dropout(net, .5)
with tf.variable_scope('layer-2'):
net = mf.relu(mf.concat(net, encoder.l5))
net = mf.deconv(net, filters=128, kernel_size=5, stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
net = mf.dropout(net, .5)
with tf.variable_scope('layer-3'):
net = mf.relu(mf.concat(net, encoder.l4))
net = mf.deconv(net, filters=64, kernel_size=5, stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
net = mf.dropout(net, .5)
with tf.variable_scope('layer-4'):
net = mf.relu(mf.concat(net, encoder.l3))
net = mf.deconv(net, filters=32, kernel_size=5, stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
with tf.variable_scope('layer-5'):
net = mf.relu(mf.concat(net, encoder.l2))
net = mf.deconv(net, filters=16, kernel_size=5, stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
with tf.variable_scope('layer-6'):
if data_type == 'mag_phase_real_imag':
out_shape = 4
else:
out_shape = 2
net = mf.relu(mf.concat(net, encoder.l1))
net = mf.deconv(net,
filters=out_shape,
kernel_size=5,
stride=(2, 2))
self.output = net
def __init__(self, input_tensor, encoder, is_training, reuse):
net = input_tensor
with tf.variable_scope('decoder'):
with tf.variable_scope('layer-1'):
net = mf.relu(net)
net = mf.deconv(net, filters=256, kernel_size=5, stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
net = mf.dropout(net, .5)
with tf.variable_scope('layer-2'):
net = mf.relu(mf.concat(net, encoder.l5))
net = mf.deconv(net, filters=128, kernel_size=5, stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
net = mf.dropout(net, .5)
with tf.variable_scope('layer-3'):
net = mf.relu(mf.concat(net, encoder.l4))
net = mf.deconv(net, filters=64, kernel_size=5, stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
net = mf.dropout(net, .5)
with tf.variable_scope('layer-4'):
net = mf.relu(mf.concat(net, encoder.l3))
net = mf.deconv(net, filters=32, kernel_size=5, stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
with tf.variable_scope('layer-5'):
net = mf.relu(mf.concat(net, encoder.l2))
net = mf.deconv(net, filters=16, kernel_size=5, stride=(2, 2))
net = mf.batch_norm(net, is_training=is_training, reuse=reuse)
with tf.variable_scope('layer-6'):
net = mf.relu(mf.concat(net, encoder.l1))
net = mf.deconv(net,
filters=encoder.input_tensor.shape[3],
kernel_size=5,
stride=(2, 2))
self.output = net
