def tiny_yolo_body(inputs, num_anchors, num_classes):
'''Create Tiny YOLO_v3 model CNN body in keras.'''
x1 = compose(
DarknetConv2D_BN_Leaky(16, (3, 3)),
MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'),
DarknetConv2D_BN_Leaky(32, (3, 3)),
MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'),
DarknetConv2D_BN_Leaky(64, (3, 3)),
MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'),
DarknetConv2D_BN_Leaky(128, (3, 3)),
MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'),
DarknetConv2D_BN_Leaky(256, (3, 3)))(inputs)
x2 = compose(
MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'),
DarknetConv2D_BN_Leaky(512, (3, 3)),
MaxPooling2D(pool_size=(2, 2), strides=(1, 1), padding='same'),
DarknetConv2D_BN_Leaky(1024, (3, 3)),
DarknetConv2D_BN_Leaky(256, (1, 1)))(x1)
y1 = compose(DarknetConv2D_BN_Leaky(512, (3, 3)),
DarknetConv2D(num_anchors * (num_classes + 5), (1, 1)))(x2)
x2 = compose(DarknetConv2D_BN_Leaky(128, (1, 1)), UpSampling2D(2))(x2)
y2 = compose(Concatenate(), DarknetConv2D_BN_Leaky(256, (3, 3)),
DarknetConv2D(num_anchors * (num_classes + 5),
(1, 1)))([x2, x1])
return Model(inputs, [y1, y2])
def make_last_layers(x, num_filters, out_filters):
'''6 Conv2D_BN_Leaky layers followed by a Conv2D_linear layer'''
x = compose(DarknetConv2D_BN_Leaky(num_filters, (1, 1)),
DarknetConv2D_BN_Leaky(num_filters * 2, (3, 3)),
DarknetConv2D_BN_Leaky(num_filters, (1, 1)),
DarknetConv2D_BN_Leaky(num_filters * 2, (3, 3)),
DarknetConv2D_BN_Leaky(num_filters, (1, 1)))(x)
y = compose(DarknetConv2D_BN_Leaky(num_filters * 2, (3, 3)),
DarknetConv2D(out_filters, (1, 1)))(x)
return x, y
def yolo_body(inputs, num_anchors, num_classes):
"""Create YOLO_V3 model CNN body in Keras."""
darknet = Model(inputs, darknet_body(inputs))
x, y1 = make_last_layers(darknet.output, 512,
num_anchors * (num_classes + 5))
x = compose(DarknetConv2D_BN_Leaky(256, (1, 1)), UpSampling2D(2))(x)
x = Concatenate()([x, darknet.layers[152].output])
x, y2 = make_last_layers(x, 256, num_anchors * (num_classes + 5))
x = compose(DarknetConv2D_BN_Leaky(128, (1, 1)), UpSampling2D(2))(x)
x = Concatenate()([x, darknet.layers[92].output])
x, y3 = make_last_layers(x, 128, num_anchors * (num_classes + 5))
return Model(inputs, [y1, y2, y3])
def make_last_layers(x, num_filters, out_filters):
"""
6 Conv2D_BN_Leaky layers followed by a Conv2D_linear layer
:param x: 输入层
:param num_filters:
:param out_filters:
:return:
"""
x = compose(DarknetConv2D_BN_Leaky(num_filters, (1, 1)),
DarknetConv2D_BN_Leaky(num_filters * 2, (3, 3)),
DarknetConv2D_BN_Leaky(num_filters, (1, 1)),
DarknetConv2D_BN_Leaky(num_filters * 2, (3, 3)),
DarknetConv2D_BN_Leaky(num_filters, (1, 1)))(x)
y = compose(DarknetConv2D_BN_Leaky(num_filters * 2, (3, 3)),
DarknetConv2D(out_filters, (1, 1)))(x)
return x, y
def DarknetConv2D_BN_Leaky(*args, **kwargs):
"""
Darknet Convolution2D followed by BatchNormalization and LeakyReLU.
固件一个卷积快，conv2d+BN+Leaky
"""
no_bias_kwargs = {'use_bias': False}
no_bias_kwargs.update(kwargs)
return compose(DarknetConv2D(*args, **no_bias_kwargs),
BatchNormalization(), LeakyReLU(alpha=0.1))
def resblock_body(x, num_filters, num_blocks):
'''A series of resblocks starting with a downsampling Convolution2D'''
# Darknet uses left and top padding instead of 'same' mode
x = ZeroPadding2D(((1, 0), (1, 0)))(x)
x = DarknetConv2D_BN_Leaky(num_filters, (3, 3), strides=(2, 2))(x)
for i in range(num_blocks):
y = compose(DarknetConv2D_BN_Leaky(num_filters // 2, (1, 1)),
DarknetConv2D_BN_Leaky(num_filters, (3, 3)))(x)
x = Add()([x, y])
return x
def DarknetConv2D_BN_Leaky(*args, **kwargs):
"""Darknet Convolution2D followed by BatchNormalization and LeakyReLU."""
# yolo计算最小单元
no_bias_kwargs = {'use_bias': False}
no_bias_kwargs.update(kwargs)
# 最小单元组成
return compose(
DarknetConv2D(*args, **no_bias_kwargs),
BatchNormalization(),
LeakyReLU(alpha=0.1))
def mobile_body(inputs, num_anchors, num_classes):
mobilenet = MobileNet(input_tensor=inputs, weights='imagenet')
f1 = mobilenet.get_layer('conv_pw_13_relu').output
x, y1 = make_last_layers(f1, 512, num_anchors * (num_classes + 5))
x = compose(
DarknetConv2D_BN_Leaky(256, (1, 1)),
UpSampling2D(2))(x)
f2 = mobilenet.get_layer('conv_pw_11_relu').output
x = Concatenate()([x, f2])
x, y2 = make_last_layers(x, 256, num_anchors * (num_classes + 5))
x = compose(
DarknetConv2D_BN_Leaky(128, (1, 1)),
UpSampling2D(2))(x)
f3 = mobilenet.get_layer('conv_pw_5_relu').output
x = Concatenate()([x, f3])
x, y3 = make_last_layers(x, 128, num_anchors * (num_classes + 5))
return Model(input=inputs, outputs=[y1, y2, y3])
def yolo_body(inputs, num_anchors, num_classes):
"""
Create YOLO_V3 model CNN body in Keras.
:param inputs: 输入层
:param num_anchors: 一个 特征图的 anchors 数量，这里一个特征图有3个anchors
:param num_classes: 分类数量
:return: model 一个输入，三个输出
"""
darknet = Model(inputs, darknet_body(inputs))
x, y1 = make_last_layers(darknet.output, 512,
num_anchors * (num_classes + 5))
# rout -4
x = compose(DarknetConv2D_BN_Leaky(256, (1, 1)), UpSampling2D(2))(x)
# rout -1 61
x = Concatenate()([x, darknet.layers[152].output])
x, y2 = make_last_layers(x, 256, num_anchors * (num_classes + 5))
# rout -4
x = compose(DarknetConv2D_BN_Leaky(128, (1, 1)), UpSampling2D(2))(x)
# -1, 36
x = Concatenate()([x, darknet.layers[92].output])
x, y3 = make_last_layers(x, 128, num_anchors * (num_classes + 5))
return Model(inputs, [y1, y2, y3])
def resblock_body(x, num_filters, num_blocks):
"""
A series of resblocks starting with a downsampling Convolution2D
一个下采样快, 然后完成 shortcut
:param x: 输入层
:param num_filters: filters 数量
:param num_blocks: blocks 数量
:return:
"""
# Darknet uses left and top padding instead of 'same' mode
x = ZeroPadding2D(((1, 0), (1, 0)))(x)
# 卷积快， filter=32，kernel=3*3, padding = valid, strides = 2 下采样
x = DarknetConv2D_BN_Leaky(num_filters, (3, 3), strides=(2, 2))(x)
for i in range(num_blocks):
y = compose(DarknetConv2D_BN_Leaky(num_filters // 2, (1, 1)),
DarknetConv2D_BN_Leaky(num_filters, (3, 3)))(x)
# shortcut
x = Add()([x, y])
return x