def mobilenetv2_yolo_body(inputs, num_anchors, num_classes):
#net, endpoint = inception_v2.inception_v2(inputs)
mobilenet = MobileNetV2(input_tensor=inputs, weights='imagenet')
# input: 416 x 416 x 3
# conv_pw_13_relu :13 x 13 x 1024
# conv_pw_11_relu :26 x 26 x 512
# conv_pw_5_relu : 52 x 52 x 256
f1 = mobilenet.get_layer('out_relu').output
# f1 :13 x 13 x 1024
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('block_13_expand_relu').output
# f2: 26 x 26 x 512
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('block_6_expand_relu').output
# f3 : 52 x 52 x 256
x = Concatenate()([x, f3])
x, y3 = make_last_layers(x, 128, num_anchors * (num_classes + 5))
return Model(inputs=inputs, outputs=[y1, y2, y3])
def yolo_body(inputs, num_anchors, num_classes):
#net, endpoint = inception_v2.inception_v2(inputs)
darknet = Model(inputs, darknet_ref_body(inputs))
# input: 416 x 416 x 3
# leaky_re_lu_7 :13 x 13 x 1024
# leaky_re_lu_5 :26 x 26 x 512
# leaky_re_lu_4 : 52 x 52 x 256
f1 = darknet.get_layer('leaky_re_lu_7').output
# f1 :13 x 13 x 1024
x, y1 = make_last_layers(f1, 256, num_anchors * (num_classes + 5))
x = compose(DarknetConv2D_BN_Leaky(128, (1, 1)), UpSampling2D(2))(x)
f2 = darknet.get_layer('leaky_re_lu_5').output
# f2: 26 x 26 x 512
x = Concatenate()([x, f2])
x, y2 = make_last_layers(x, 128, num_anchors * (num_classes + 5))
x = compose(DarknetConv2D_BN_Leaky(64, (1, 1)), UpSampling2D(2))(x)
f3 = darknet.get_layer('leaky_re_lu_4').output
# f3 : 52 x 52 x 256
x = Concatenate()([x, f3])
x, y3 = make_last_layers(x, 64, num_anchors * (num_classes + 5))
return Model(inputs=inputs, outputs=[y1, y2, y3])
def yolo_body(inputs, num_anchors, num_classes):
#net, endpoint = inception_v2.inception_v2(inputs)
squeezenet = squeezenet_body(input_tensor=inputs)
# input: 416 x 416 x 3
# contatenate_10 :12 x 12 x 640
# contatenate_6 :25 x 25 x 384
# contatenate_4 : 51 x 51 x 256
f1 = squeezenet.get_layer('concatenate_10').output
# f1 :13 x 13 x 1024
x, y1 = make_last_layers(f1, 512, num_anchors * (num_classes + 5))
x = compose(DarknetConv2D_BN_Leaky(256, (1, 1)), UpSampling2D(2))(x)
f2 = squeezenet.get_layer('concatenate_6').output
# f2: 26 x 26 x 512
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 = squeezenet.get_layer('concatenate_4').output
# f3 : 52 x 52 x 256
x = Concatenate()([x, f3])
x, y3 = make_last_layers(x, 128, num_anchors * (num_classes + 5))
return Model(inputs=inputs, outputs=[y1, y2, y3])
def darknet_ref_body(x): #tiny yolo with three output
'''Darknent body having 52 Convolution2D layers'''
x = DarknetConv2D_BN_Leaky(16, (3, 3))(x)
x = darknet_resblock_body(x, 32)
x = darknet_resblock_body(x, 64)
x = darknet_resblock_body(x, 128)
x = darknet_resblock_body(x, 256)
x = darknet_resblock_body(x, 512)
x = MaxPooling2D(pool_size=(2, 2), strides=(1, 1), padding='same')(x)
x = DarknetConv2D_BN_Leaky(1024, (3, 3))(x)
return x
def darknet_resblock_body(x, num_filters):
'''A series of resblocks starting with a downsampling Convolution2D'''
# Darknet uses left and top padding instead of 'same' mode
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same')(x)
x = DarknetConv2D_BN_Leaky(num_filters, (3, 3))(x)
return x