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 yolo_body(inputs, num_anchors, num_classes):
""" Create YOLOv3 model CNN body in Keras.
y1, y2, y3 for detecting small, medium, and large objects.
Args:
inputs: Tensor model.inputs [1, 416, 416, 3].
num_anchors: anchors.
num_classes: number of classes.
Returns:
model: Keras model, output shape is:
[(1, 13, 13, 255), (1, 13, 13, 255), (1, 13, 13, 255)].
255 = 85 (80 classes, 1 logits, 4 box parameters) * 3 (anchor boxes).
3 elements corresponding to 3 object size (small, medium, large).
"""
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):
""" Last few layers for detecting objects with different sizes.
6 Conv2D_BN_Leaky layers followed by a Conv2D_linear layer.
www.cyberailab.com/home/a-closer-look-at-yolov3
"""
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 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."""
no_bias_kwargs = {'use_bias': False}
no_bias_kwargs.update(kwargs)
return compose(DarknetConv2D(*args, **no_bias_kwargs),
BatchNormalization(), LeakyReLU(alpha=0.1))