def define_stacked_model(members): for i in range(len(members)): # update all layers in all models to not be trainable model = members[i] for layer in model.layers: layer.trainable = False layer._name = 'ensemble_' + str(i+1) + '_' + layer.name # avoid 'unique layer name' issue ensemble_visible = [model.input for model in members] # define multi-headed input ensemble_outputs = [model.output for model in members] # concatenate merge output from each model merge = concatenate(ensemble_outputs) hidden = Dense(10, activation='relu')(merge) output = Dense(3, activation='softmax')(hidden) model = Model(inputs=ensemble_visible, outputs=output) plot_model(model, show_shapes=True, to_file='model_graph.png') # plot graph of ensemble model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) # compile return model
def CreateModel(self):
'''
定义CNN/LSTM/CTC模型，使用函数式模型
输入层：200维的特征值序列，一条语音数据的最大长度设为1600（大约16s）
隐藏层一：3*3卷积层
隐藏层二：池化层，池化窗口大小为2
隐藏层三：Dropout层，需要断开的神经元的比例为0.2，防止过拟合
隐藏层四：循环层、LSTM/GRU层
隐藏层五：Dropout层，需要断开的神经元的比例为0.2，防止过拟合
隐藏层六：全连接层，神经元数量为self.MS_OUTPUT_SIZE，使用softmax作为激活函数，
输出层：自定义层，即CTC层，使用CTC的loss作为损失函数，实现连接性时序多输出
'''
# 每一帧使用13维mfcc特征及其13维一阶差分和13维二阶差分表示，最大信号序列长度为1500
input_data = Input(name='the_input',
shape=(self.AUDIO_LENGTH, self.AUDIO_FEATURE_LENGTH,
1))
layer_h1 = Conv2D(32, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(input_data) # 卷积层
layer_h1 = Dropout(0.1)(layer_h1)
layer_h2 = Conv2D(32, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h1) # 卷积层
layer_h3 = MaxPooling2D(pool_size=2, strides=None,
padding="valid")(layer_h2) # 池化层
#layer_h3 = Dropout(0.2)(layer_h2) # 随机中断部分神经网络连接，防止过拟合
layer_h3 = Dropout(0.2)(layer_h3)
layer_h4 = Conv2D(64, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h3) # 卷积层
layer_h4 = Dropout(0.2)(layer_h4)
layer_h5 = Conv2D(64, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h4) # 卷积层
layer_h6 = MaxPooling2D(pool_size=2, strides=None,
padding="valid")(layer_h5) # 池化层
layer_h6 = Dropout(0.3)(layer_h6)
layer_h7 = Conv2D(128, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h6) # 卷积层
layer_h7 = Dropout(0.3)(layer_h7)
layer_h8 = Conv2D(128, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h7) # 卷积层
layer_h9 = MaxPooling2D(pool_size=2, strides=None,
padding="valid")(layer_h8) # 池化层
layer_h9 = Dropout(0.3)(layer_h9)
layer_h10 = Conv2D(128, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h9) # 卷积层
layer_h10 = Dropout(0.4)(layer_h10)
layer_h11 = Conv2D(128, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h10) # 卷积层
layer_h12 = MaxPooling2D(pool_size=1, strides=None,
padding="valid")(layer_h11) # 池化层
#test=Model(inputs = input_data, outputs = layer_h6)
#test.summary()
layer_h13 = Reshape((200, 3200))(layer_h12) #Reshape层
layer_h13 = Dropout(0.4)(layer_h13)
layer_h14 = Dense(128,
activation="relu",
use_bias=True,
kernel_initializer='he_normal')(layer_h13) # 全连接层
layer_h14 = Dropout(0.4)(layer_h14)
inner = layer_h14
#layer_h5 = LSTM(256, activation='relu', use_bias=True, return_sequences=True)(layer_h4) # LSTM层
rnn_size = 128
gru_1 = GRU(rnn_size,
return_sequences=True,
kernel_initializer='he_normal',
name='gru1')(inner)
gru_1b = GRU(rnn_size,
return_sequences=True,
go_backwards=True,
kernel_initializer='he_normal',
name='gru1_b')(inner)
gru1_merged = add([gru_1, gru_1b])
gru_2 = GRU(rnn_size,
return_sequences=True,
kernel_initializer='he_normal',
name='gru2')(gru1_merged)
gru_2b = GRU(rnn_size,
return_sequences=True,
go_backwards=True,
kernel_initializer='he_normal',
name='gru2_b')(gru1_merged)
gru2 = concatenate([gru_2, gru_2b])
#layer_h12 = GRU(128,activation='tanh', recurrent_activation='hard_sigmoid', use_bias=True, kernel_initializer='he_normal', recurrent_initializer='orthogonal', bias_initializer='zeros', return_sequences=True)(layer_h11)
layer_h15 = Dropout(0.4)(gru2)
layer_h16 = Dense(128,
activation="relu",
use_bias=True,
kernel_initializer='he_normal')(layer_h15) # 全连接层
layer_h16 = Dropout(0.5)(layer_h16) # 随机中断部分神经网络连接，防止过拟合
layer_h17 = Dense(self.MS_OUTPUT_SIZE,
use_bias=True,
kernel_initializer='he_normal')(layer_h16) # 全连接层
y_pred = Activation('softmax', name='Activation0')(layer_h17)
model_data = Model(inputs=input_data, outputs=y_pred)
#model_data.summary()
labels = Input(name='the_labels',
shape=[self.label_max_string_length],
dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
# tensorflow.keras doesn't currently support loss funcs with extra parameters
# so CTC loss is implemented in a lambda layer
#layer_out = Lambda(ctc_lambda_func,output_shape=(self.MS_OUTPUT_SIZE, ), name='ctc')([y_pred, labels, input_length, label_length])#(layer_h6) # CTC
loss_out = Lambda(self.ctc_lambda_func, output_shape=(1, ),
name='ctc')(
[y_pred, labels, input_length, label_length])
model = Model(inputs=[input_data, labels, input_length, label_length],
outputs=loss_out)
model.summary()
# clipnorm seems to speeds up convergence
#sgd = SGD(lr=0.0001, decay=1e-6, momentum=0.9, nesterov=True, clipnorm=5)
ada_d = Adadelta(lr=0.01, rho=0.95, epsilon=1e-06)
#model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=sgd)
model.compile(loss={
'ctc': lambda y_true, y_pred: y_pred
},
optimizer=ada_d)
# captures output of softmax so we can decode the output during visualization
test_func = K.function([input_data], [y_pred])
print('[*提示] 创建模型成功，模型编译成功')
return model, model_data
def CreateModel(self):
'''
定义CNN/LSTM/CTC模型，使用函数式模型
输入层：200维的特征值序列，一条语音数据的最大长度设为1600（大约16s）
隐藏层：卷积池化层，卷积核大小为3x3，池化窗口大小为2
隐藏层：全连接层
输出层：全连接层，神经元数量为self.MS_OUTPUT_SIZE，使用softmax作为激活函数，
CTC层：使用CTC的loss作为损失函数，实现连接性时序多输出
'''
input_data = Input(name='the_input',
shape=(self.AUDIO_LENGTH, self.AUDIO_FEATURE_LENGTH,
1))
layer_h = Conv2D(32, (3, 3),
use_bias=False,
activation='relu',
padding='same',
kernel_initializer='he_normal')(input_data) # 卷积层
#layer_h = Dropout(0.05)(layer_h)
layer_h = Conv2D(32, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h) # 卷积层
layer_h = MaxPooling2D(pool_size=2, strides=None,
padding="valid")(layer_h) # 池化层
#layer_h = Dropout(0.05)(layer_h) # 随机中断部分神经网络连接，防止过拟合
layer_h = Conv2D(64, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h) # 卷积层
#layer_h = Dropout(0.1)(layer_h)
layer_h = Conv2D(64, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h) # 卷积层
layer_h = MaxPooling2D(pool_size=2, strides=None,
padding="valid")(layer_h) # 池化层
#layer_h = Dropout(0.1)(layer_h)
layer_h = Conv2D(128, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h) # 卷积层
#layer_h = Dropout(0.15)(layer_h)
layer_h = Conv2D(128, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h) # 卷积层
layer_h = MaxPooling2D(pool_size=2, strides=None,
padding="valid")(layer_h) # 池化层
#layer_h = Dropout(0.15)(layer_h)
layer_h = Conv2D(128, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h) # 卷积层
#layer_h = Dropout(0.2)(layer_h)
layer_h = Conv2D(128, (3, 3),
use_bias=True,
activation='relu',
padding='same',
kernel_initializer='he_normal')(layer_h) # 卷积层
layer_h = MaxPooling2D(pool_size=1, strides=None,
padding="valid")(layer_h) # 池化层
#layer_h = Dropout(0.2)(layer_h)
#layer_h = Conv2D(128, (3,3), use_bias=True, activation='relu', padding='same', kernel_initializer='he_normal')(layer_h) # 卷积层
#layer_h = Dropout(0.2)(layer_h)
#layer_h = Conv2D(128, (3,3), use_bias=True, activation='relu', padding='same', kernel_initializer='he_normal')(layer_h) # 卷积层
#layer_h = MaxPooling2D(pool_size=1, strides=None, padding="valid")(layer_h) # 池化层
#test=Model(inputs = input_data, outputs = layer_h)
#test.summary()
layer_h = Reshape((200, 3200))(layer_h) #Reshape层
#layer_h16 = Dropout(0.3)(layer_h16) # 随机中断部分神经网络连接，防止过拟合
layer_h = Dense(128,
activation="relu",
use_bias=True,
kernel_initializer='he_normal')(layer_h) # 全连接层
inner = layer_h
#layer_h5 = LSTM(256, activation='relu', use_bias=True, return_sequences=True)(layer_h4) # LSTM层
rnn_size = 128
gru_1 = GRU(rnn_size,
return_sequences=True,
kernel_initializer='he_normal',
name='gru1')(inner)
gru_1b = GRU(rnn_size,
return_sequences=True,
go_backwards=True,
kernel_initializer='he_normal',
name='gru1_b')(inner)
gru1_merged = add([gru_1, gru_1b])
gru_2 = GRU(rnn_size,
return_sequences=True,
kernel_initializer='he_normal',
name='gru2')(gru1_merged)
gru_2b = GRU(rnn_size,
return_sequences=True,
go_backwards=True,
kernel_initializer='he_normal',
name='gru2_b')(gru1_merged)
gru2 = concatenate([gru_2, gru_2b])
layer_h = gru2
#layer_h20 = Dropout(0.4)(gru2)
layer_h = Dense(128,
activation="relu",
use_bias=True,
kernel_initializer='he_normal')(layer_h) # 全连接层
#layer_h17 = Dropout(0.3)(layer_h17)
layer_h = Dense(self.MS_OUTPUT_SIZE,
use_bias=True,
kernel_initializer='he_normal')(layer_h) # 全连接层
y_pred = Activation('softmax', name='Activation0')(layer_h)
model_data = Model(inputs=input_data, outputs=y_pred)
#model_data.summary()
labels = Input(name='the_labels',
shape=[self.label_max_string_length],
dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
# Keras doesn't currently support loss funcs with extra parameters
# so CTC loss is implemented in a lambda layer
#layer_out = Lambda(ctc_lambda_func,output_shape=(self.MS_OUTPUT_SIZE, ), name='ctc')([y_pred, labels, input_length, label_length])#(layer_h6) # CTC
loss_out = Lambda(self.ctc_lambda_func, output_shape=(1, ),
name='ctc')(
[y_pred, labels, input_length, label_length])
model = Model(inputs=[input_data, labels, input_length, label_length],
outputs=loss_out)
model.summary()
# clipnorm seems to speeds up convergence
#sgd = SGD(lr=0.0001, decay=1e-6, momentum=0.9, nesterov=True, clipnorm=5)
#opt = Adadelta(lr = 0.01, rho = 0.95, epsilon = 1e-06)
opt = Adam(lr=0.001,
beta_1=0.9,
beta_2=0.999,
decay=0.0,
epsilon=10e-8)
#model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=sgd)
model.compile(loss={
'ctc': lambda y_true, y_pred: y_pred
},
optimizer=opt)
# captures output of softmax so we can decode the output during visualization
test_func = K.function([input_data], [y_pred])
#print('[*提示] 创建模型成功，模型编译成功')
print('[*Info] Create Model Successful, Compiles Model Successful. ')
return model, model_data
def build_UNet2D_4L(inp_shape, k_size=3):
merge_axis = -1 # Feature maps are concatenated along last axis (for tf backend)
data = Input(shape=inp_shape)
conv1 = Convolution2D(filters=32,
kernel_size=k_size,
padding='same',
activation='relu')(data)
conv1 = Convolution2D(filters=32,
kernel_size=k_size,
padding='same',
activation='relu')(conv1)
pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
conv2 = Convolution2D(filters=64,
kernel_size=k_size,
padding='same',
activation='relu')(pool1)
conv2 = Convolution2D(filters=64,
kernel_size=k_size,
padding='same',
activation='relu')(conv2)
pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
conv3 = Convolution2D(filters=64,
kernel_size=k_size,
padding='same',
activation='relu')(pool2)
conv3 = Convolution2D(filters=64,
kernel_size=k_size,
padding='same',
activation='relu')(conv3)
pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
conv4 = Convolution2D(filters=128,
kernel_size=k_size,
padding='same',
activation='relu')(pool3)
conv4 = Convolution2D(filters=128,
kernel_size=k_size,
padding='same',
activation='relu')(conv4)
pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)
conv5 = Convolution2D(filters=256,
kernel_size=k_size,
padding='same',
activation='relu')(pool4)
up1 = UpSampling2D(size=(2, 2))(conv5)
conv6 = Convolution2D(filters=256,
kernel_size=k_size,
padding='same',
activation='relu')(up1)
conv6 = Convolution2D(filters=256,
kernel_size=k_size,
padding='same',
activation='relu')(conv6)
merged1 = concatenate([conv4, conv6], axis=merge_axis)
conv6 = Convolution2D(filters=256,
kernel_size=k_size,
padding='same',
activation='relu')(merged1)
up2 = UpSampling2D(size=(2, 2))(conv6)
conv7 = Convolution2D(filters=256,
kernel_size=k_size,
padding='same',
activation='relu')(up2)
conv7 = Convolution2D(filters=256,
kernel_size=k_size,
padding='same',
activation='relu')(conv7)
merged2 = concatenate([conv3, conv7], axis=merge_axis)
conv7 = Convolution2D(filters=256,
kernel_size=k_size,
padding='same',
activation='relu')(merged2)
up3 = UpSampling2D(size=(2, 2))(conv7)
conv8 = Convolution2D(filters=128,
kernel_size=k_size,
padding='same',
activation='relu')(up3)
conv8 = Convolution2D(filters=128,
kernel_size=k_size,
padding='same',
activation='relu')(conv8)
merged3 = concatenate([conv2, conv8], axis=merge_axis)
conv8 = Convolution2D(filters=128,
kernel_size=k_size,
padding='same',
activation='relu')(merged3)
up4 = UpSampling2D(size=(2, 2))(conv8)
conv9 = Convolution2D(filters=64,
kernel_size=k_size,
padding='same',
activation='relu')(up4)
conv9 = Convolution2D(filters=64,
kernel_size=k_size,
padding='same',
activation='relu')(conv9)
merged4 = concatenate([conv1, conv9], axis=merge_axis)
conv9 = Convolution2D(filters=64,
kernel_size=k_size,
padding='same',
activation='relu')(merged4)
conv10 = Convolution2D(filters=1,
kernel_size=k_size,
padding='same',
activation='sigmoid')(conv9)
output = conv10
model = Model(data, output)
return model
def make_yolov3_model():
input_image = Input(shape=(None, None, 3))
# Layer 0 => 4
x = _conv_block(input_image, [{'filter': 32, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 0},
{'filter': 64, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 1},
{'filter': 32, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 2},
{'filter': 64, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 3}])
# Layer 5 => 8
x = _conv_block(x, [{'filter': 128, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 5},
{'filter': 64, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 6},
{'filter': 128, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 7}])
# Layer 9 => 11
x = _conv_block(x, [{'filter': 64, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 9},
{'filter': 128, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 10}])
# Layer 12 => 15
x = _conv_block(x, [{'filter': 256, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 12},
{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 13},
{'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 14}])
# Layer 16 => 36
for i in range(7):
x = _conv_block(x, [{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 16+i*3},
{'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 17+i*3}])
skip_36 = x
# Layer 37 => 40
x = _conv_block(x, [{'filter': 512, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 37},
{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 38},
{'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 39}])
# Layer 41 => 61
for i in range(7):
x = _conv_block(x, [{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 41+i*3},
{'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 42+i*3}])
skip_61 = x
# Layer 62 => 65
x = _conv_block(x, [{'filter': 1024, 'kernel': 3, 'stride': 2, 'bnorm': True, 'leaky': True, 'layer_idx': 62},
{'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 63},
{'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 64}])
# Layer 66 => 74
for i in range(3):
x = _conv_block(x, [{'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 66+i*3},
{'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 67+i*3}])
# Layer 75 => 79
x = _conv_block(x, [{'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 75},
{'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 76},
{'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 77},
{'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 78},
{'filter': 512, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 79}], skip=False)
# Layer 80 => 82
yolo_82 = _conv_block(x, [{'filter': 1024, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 80},
{'filter': 255, 'kernel': 1, 'stride': 1, 'bnorm': False, 'leaky': False, 'layer_idx': 81}], skip=False)
# Layer 83 => 86
x = _conv_block(x, [{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 84}], skip=False)
x = UpSampling2D(2)(x)
x = concatenate([x, skip_61])
# Layer 87 => 91
x = _conv_block(x, [{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 87},
{'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 88},
{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 89},
{'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 90},
{'filter': 256, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 91}], skip=False)
# Layer 92 => 94
yolo_94 = _conv_block(x, [{'filter': 512, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 92},
{'filter': 255, 'kernel': 1, 'stride': 1, 'bnorm': False, 'leaky': False, 'layer_idx': 93}], skip=False)
# Layer 95 => 98
x = _conv_block(x, [{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 96}], skip=False)
x = UpSampling2D(2)(x)
x = concatenate([x, skip_36])
# Layer 99 => 106
yolo_106 = _conv_block(x, [{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 99},
{'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 100},
{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 101},
{'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 102},
{'filter': 128, 'kernel': 1, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 103},
{'filter': 256, 'kernel': 3, 'stride': 1, 'bnorm': True, 'leaky': True, 'layer_idx': 104},
{'filter': 255, 'kernel': 1, 'stride': 1, 'bnorm': False, 'leaky': False, 'layer_idx': 105}], skip=False)
model = Model(input_image, [yolo_82, yolo_94, yolo_106])
return model
def architecture(config):
input_image = Input(shape=(IMAGE_H, IMAGE_W, 3))
true_boxes = Input(shape=(1, 1, 1, TRUE_BOX_BUFFER, 4))
# Layer 1
x = Conv2D(32, (3, 3),
strides=(1, 1),
padding='same',
name='conv_1',
use_bias=False)(input_image)
x = BatchNormalization(name='norm_1')(x)
x = LeakyReLU(alpha=0.1)(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
# Layer 2
x = Conv2D(64, (3, 3),
strides=(1, 1),
padding='same',
name='conv_2',
use_bias=False)(x)
x = BatchNormalization(name='norm_2')(x)
x = LeakyReLU(alpha=0.1)(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
# Layer 3
x = Conv2D(128, (3, 3),
strides=(1, 1),
padding='same',
name='conv_3',
use_bias=False)(x)
x = BatchNormalization(name='norm_3')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 4
x = Conv2D(64, (1, 1),
strides=(1, 1),
padding='same',
name='conv_4',
use_bias=False)(x)
x = BatchNormalization(name='norm_4')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 5
x = Conv2D(128, (3, 3),
strides=(1, 1),
padding='same',
name='conv_5',
use_bias=False)(x)
x = BatchNormalization(name='norm_5')(x)
x = LeakyReLU(alpha=0.1)(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
# Layer 6
x = Conv2D(256, (3, 3),
strides=(1, 1),
padding='same',
name='conv_6',
use_bias=False)(x)
x = BatchNormalization(name='norm_6')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 7
x = Conv2D(128, (1, 1),
strides=(1, 1),
padding='same',
name='conv_7',
use_bias=False)(x)
x = BatchNormalization(name='norm_7')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 8
x = Conv2D(256, (3, 3),
strides=(1, 1),
padding='same',
name='conv_8',
use_bias=False)(x)
x = BatchNormalization(name='norm_8')(x)
x = LeakyReLU(alpha=0.1)(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
# Layer 9
x = Conv2D(512, (3, 3),
strides=(1, 1),
padding='same',
name='conv_9',
use_bias=False)(x)
x = BatchNormalization(name='norm_9')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 10
x = Conv2D(256, (1, 1),
strides=(1, 1),
padding='same',
name='conv_10',
use_bias=False)(x)
x = BatchNormalization(name='norm_10')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 11
x = Conv2D(512, (3, 3),
strides=(1, 1),
padding='same',
name='conv_11',
use_bias=False)(x)
x = BatchNormalization(name='norm_11')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 12
x = Conv2D(256, (1, 1),
strides=(1, 1),
padding='same',
name='conv_12',
use_bias=False)(x)
x = BatchNormalization(name='norm_12')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 13
x = Conv2D(512, (3, 3),
strides=(1, 1),
padding='same',
name='conv_13',
use_bias=False)(x)
x = BatchNormalization(name='norm_13')(x)
x = LeakyReLU(alpha=0.1)(x)
skip_connection = x
x = MaxPooling2D(pool_size=(2, 2))(x)
# Layer 14
x = Conv2D(1024, (3, 3),
strides=(1, 1),
padding='same',
name='conv_14',
use_bias=False)(x)
x = BatchNormalization(name='norm_14')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 15
x = Conv2D(512, (1, 1),
strides=(1, 1),
padding='same',
name='conv_15',
use_bias=False)(x)
x = BatchNormalization(name='norm_15')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 16
x = Conv2D(1024, (3, 3),
strides=(1, 1),
padding='same',
name='conv_16',
use_bias=False)(x)
x = BatchNormalization(name='norm_16')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 17
x = Conv2D(512, (1, 1),
strides=(1, 1),
padding='same',
name='conv_17',
use_bias=False)(x)
x = BatchNormalization(name='norm_17')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 18
x = Conv2D(1024, (3, 3),
strides=(1, 1),
padding='same',
name='conv_18',
use_bias=False)(x)
x = BatchNormalization(name='norm_18')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 19
x = Conv2D(1024, (3, 3),
strides=(1, 1),
padding='same',
name='conv_19',
use_bias=False)(x)
x = BatchNormalization(name='norm_19')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 20
x = Conv2D(1024, (3, 3),
strides=(1, 1),
padding='same',
name='conv_20',
use_bias=False)(x)
x = BatchNormalization(name='norm_20')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 21
skip_connection = Conv2D(64, (1, 1),
strides=(1, 1),
padding='same',
name='conv_21',
use_bias=False)(skip_connection)
skip_connection = BatchNormalization(name='norm_21')(skip_connection)
skip_connection = LeakyReLU(alpha=0.1)(skip_connection)
skip_connection = Lambda(space_to_depth_x2)(skip_connection)
x = concatenate([skip_connection, x])
# Layer 22
x = Conv2D(1024, (3, 3),
strides=(1, 1),
padding='same',
name='conv_22',
use_bias=False)(x)
x = BatchNormalization(name='norm_22')(x)
x = LeakyReLU(alpha=0.1)(x)
# Layer 23
x = Conv2D(BOX * (4 + 1 + CLASS), (1, 1),
strides=(1, 1),
padding='same',
name='conv_23')(x)
output = Reshape((GRID_H, GRID_W, BOX, 4 + 1 + CLASS))(x)
# small hack to allow true_boxes to be registered when Keras build the model
# for more information: https://github.com/fchollet/keras/issues/2790
output = Lambda(lambda args: args[0])([output, true_boxes])
model = Model([input_image, true_boxes], output)