def darknet4det4(input_shape, output_channels):
inputs = Input(shape=(input_shape[0], input_shape[1], 3))
darknet = Model(inputs, darknet_body(inputs))
# downsample
subsample_x = compose(
DarknetConv2D_BN_Leaky(1024, (3, 3), strides=(1, 1)),
DarknetConv2D_BN_Leaky(512, (3, 3), strides=(1, 1)),
DarknetConv2D_BN_Leaky(512, (3, 3), strides=(2, 2), padding='SAME')
)(darknet.output)
_, y4 = make_last_layers(subsample_x, 512, output_channels, output_layer_name="output4")
x, y1 = make_last_layers(darknet.output, 512, output_channels, output_layer_name='output1')
# print(type(x))
# upsmaple
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, output_channels, output_layer_name='output2')
# upsample
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, output_channels, output_layer_name='output3')
# order in descending feature size
return Model(inputs, [y3, y2, y1, y4])
def make_last_layers(x, num_filters, out_filters, output_layer_name=None):
'''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), name=output_layer_name))(x)
return x, y
def DarknetConv2D_BN_Leaky(*args, **kwargs):
"""Darknet Convolution2D followed by BatchNormalization and LeakyReLU."""
no_bias_kwargs = {'use_bias': False}
no_bias_kwargs.update(kwargs)
return compose(
DarknetConv2D(*args, **no_bias_kwargs),
BatchNormalization(),
LeakyReLU(alpha=0.1))
def downsample(input_channels, times):
downconvs_ops = [
ResnetConv2D(
input_channels * pow(2, i + 1),
(3, 3),
strides=(2, 2),
) for i in range(times)
]
return compose(*downconvs_ops)
def darknet4det3(input_shape, output_channels):
"""Create YOLO_V3 model CNN body in Keras."""
inputs = Input(shape=(input_shape[0], input_shape[1], 3))
darknet = Model(inputs, darknet_body(inputs))
x, y1 = make_last_layers(darknet.output, 512, output_channels, output_layer_name='output1')
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, output_channels, output_layer_name='output2')
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, output_channels, output_layer_name='output3')
return Model(inputs, [y1, y2, y3])
def make_predict_head(y, num_filters, output_channels, name=None):
y = compose(
Conv2D_BN_Leaky(num_filters, kernel_size=(1, 1), strides=(1, 1)),
Conv2D_BN_Leaky(num_filters * 2, kernel_size=(1, 1), strides=(1, 1)),
# Conv2D_BN_Leaky(num_filters, kernel_size=(1, 1), strides=(1, 1)),
ResnetConv2D(output_channels,
kernel_size=(1, 1),
strides=(1, 1),
name=name))(y)
# print(y)
return y
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 bottleneck(x, num_channels):
shortcut = x
x = compose(
Conv2D_BN_Leaky(num_channels // 4, kernel_size=(1, 1), strides=(1, 1)),
Conv2D_BN_Leaky(num_channels // 4, kernel_size=(3, 3), strides=(1, 1)),
Conv2D_BN_Leaky(num_channels, kernel_size=(1, 1), strides=(1, 1)),
)(x)
x = Add()([x, shortcut])
x = LeakyReLU()(x)
return x
def make_last_layer(feature_maps, num_filters, output_channels):
"""
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), name=output_layer_name))(x)
:param feature_map:
:return:
"""
_y = []
out_c = sum(output_channels)
for idx, output in enumerate(feature_maps):
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)))(output)
y = compose(DarknetConv2D_BN_Leaky(num_filters * 2, (3, 3)),
DarknetConv2D(out_c, (1, 1),
name="output%d" % (idx + 1)))(x)
# _fp = compose(
# Conv2D(num_filters * 4, kernel_size=1, strides=1, padding='same'),
# Conv2D(num_filters, kernel_size=3, strides=1, padding='same'),
# # Conv2D(num_filters, kernel_size=1, strides=1, padding='same'),
# # Conv2D(num_filters * 2, kernel_size=3, strides=1, padding='same'),
# DarknetConv2D_BN_Leaky(out_c, (1, 1)),
# Conv2D(out_c, kernel_size=1, strides=1, padding='same', name="output%d" % (idx + 1)),
# )(output)
_y.append(y)
return _y
def upsample(input_channels, times):
return compose(
UpSampling2D(pow(2, times)),
ResnetConv2D(input_channels // pow(2, times), (3, 3), strides=(1, 1)))
