def downstage_resBlock(x, stage_id, keep_prob, stage_num=5):
"""
Vnet左侧的压缩路径的一个stage层
:param x: 该stage的输入
:param stage_id: int,表示第几个stage，原论文中从上到下依次是1-5
:param keep_prob: dropout保留元素的概率，如果不需要则设置为1
:param stage_num: stage_num是Vnet设置的stage总数
:return: stage下采样后的输出和stage下采样前的输出，下采样前的输出需要与Vnet右侧的扩展路径连接，所以需要输出保存。
"""
x0 = x # x0是stage的原始输入
# Vnet每个stage的输入会进行特定次数的卷积操作，1~3个stage分别执行1~3次卷积，3以后的stage均执行3次卷积
# 每个stage的通道数(卷积核个数或叫做feature map数量)依次增加两倍，从16，32，64，128到256
for _ in range(3 if stage_id > 3 else stage_id):
x = PReLU()(BatchNormalization()(Conv2D(
16 * (2**(stage_id - 1)),
5,
activation=None,
padding='same',
kernel_initializer='he_normal')(x)))
print('conv_down_stage_%d:' % stage_id,
x.get_shape().as_list()) #输出收缩路径中每个stage内的卷积
x_add = PReLU()(add([x0, x]))
x_add = Dropout(keep_prob)(x_add)
if stage_id < stage_num:
x_downsample = PReLU()(BatchNormalization()(Conv2D(
16 * (2**stage_id),
2,
strides=(2, 2),
activation=None,
padding='same',
kernel_initializer='he_normal')(x_add)))
return x_downsample, x_add # 返回每个stage下采样后的结果,以及在相加之后的结果
else:
return x_add, x_add # 返回相加之后的结果，为了和上面输出保持一致，所以重复输出
def up_resBlock(forward_conv,input_conv,stage):#扩展路径
conv=concatenate([forward_conv,input_conv],axis = -1)
print('conv_concatenate:',conv.get_shape().as_list())
for _ in range(3 if stage>3 else stage):
conv=PReLU()(BatchNormalization()(Conv2D(16*(2**(stage-1)), 5, activation = None, padding = 'same', kernel_initializer = 'he_normal')(conv)))
print('conv_up_stage_%d:' %stage,conv.get_shape().as_list())#输出扩展路径中每个stage内的卷积
conv_add=PReLU()(add([input_conv,conv]))
if stage>1:
conv_upsample=PReLU()(BatchNormalization()(Conv2DTranspose(16*(2**(stage-2)),2,strides=(2, 2),padding='valid',activation = None,kernel_initializer = 'he_normal')(conv_add)))
return conv_upsample
else:
return conv_add
def generator2(self):
def make_z(shape, mean=0., std=1., name='z'):
z = tf.random_normal(shape, mean=mean, stddev=std,name=name, dtype=tf.float32)
return z
def WaveNetResidualConv1D(num_filters, kernel_size, dilation_rate):
def build_residual_block(input):
sigm_conv1d = AtrousConvolution1D(num_filters, kernel_size, dilation_rate=dilation_rate,padding="same", activation="sigmoid")(input)
tanh_conv1d = AtrousConvolution1D(num_filters, kernel_size, dilation_rate=dilation_rate,padding="same", activation="tanh")(input)
multiplyLayers = Multiply()([sigm_conv1d, tanh_conv1d])
skip_connection = Conv1D(1, 1)(multiplyLayers)
residual = Add()([input, skip_connection])
return residual, skip_connection
return build_residual_block
def UpConv1DModule(input, filters, filters_size=5, dropout = 0.0):
def Conv1DTranspose(input, filters, filters_size, strides=2, padding='same'):
x = Lambda(lambda x: K.expand_dims(x, axis=2))(input)
x = Conv2DTranspose(filters=filters, kernel_size=(filters_size, 1), strides=(strides, 1), padding=padding)(x)
x = Lambda(lambda x: K.squeeze(x, axis=2))(x)
return x
x = Conv1DTranspose(input, filters, filters_size)
x = UpSampling1D(size=2)(x)
x = BatchNormalization(momentum=0.8)(x)
return x
input_sound = Input(shape=(1,self.sound_length))
kwidth = 31
enc_layers = 7
h_i = input_sound
skip_out = True
skips = []
g_enc_depths = [16, 32, 32, 64, 64, 128, 128, 256, 256, 512, 1024]
for layer_idx, layer_depth in enumerate(g_enc_depths):
h_i_dwn = Conv1D(layer_depth, kwidth, data_format='channels_first')(h_i)
h_i = h_i_dwn
if layer_idx < len(g_enc_depths) - 1:
skips.append(h_i)
h_i = PReLU()(h_i)
# z = make_z((input_sound.get_shape().as_list()[0], 1, 16384))
# h_i = concatenate([z, h_i])
g_dec_depths = g_enc_depths[:-1][::-1] + [1]
for layer_idx, layer_depth in enumerate(g_dec_depths):
h_i_dim = h_i.get_shape().as_list()
h_i_dcv = UpConv1DModule(h_i, layer_depth, kwidth)
h_i = h_i_dcv
if layer_idx < len(g_dec_depths) - 1:
h_i = PReLU()(h_i)
skip_ = skips[-(layer_idx + 1)]
h_i = concatenate([Permute((2,1))(h_i), skip_],axis=2)
else:
h_i = Activation('tanh')(h_i)
return Model(input_sound,h_i)
