def yolo3_spp_xception_body(inputs, num_anchors, num_classes):
"""Create YOLO_V3 SPP Xception model CNN body in Keras."""
xception = Xception(input_tensor=inputs,
weights='imagenet',
include_top=False)
# input: 416 x 416 x 3
# block14_sepconv2_act: 13 x 13 x 2048
# block13_sepconv2_bn(middle in block13): 26 x 26 x 1024
# add_46(end of block12): 26 x 26 x 728
# block4_sepconv2_bn(middle in block4) : 52 x 52 x 728
# add_37(end of block3) : 52 x 52 x 256
f1 = xception.get_layer('block14_sepconv2_act').output
# f1 :13 x 13 x 2048
x, y1 = make_spp_last_layers(f1, 1024, num_anchors * (num_classes + 5))
x = compose(DarknetConv2D_BN_Leaky(512, (1, 1)), UpSampling2D(2))(x)
f2 = xception.get_layer('block13_sepconv2_bn').output
# f2: 26 x 26 x 1024
x = Concatenate()([x, f2])
x, y2 = make_last_layers(x, 512, num_anchors * (num_classes + 5))
x = compose(DarknetConv2D_BN_Leaky(256, (1, 1)), UpSampling2D(2))(x)
f3 = xception.get_layer('block4_sepconv2_bn').output
# f3 : 52 x 52 x 728
x = Concatenate()([x, f3])
x, y3 = make_last_layers(x, 256, num_anchors * (num_classes + 5))
return Model(inputs=inputs, outputs=[y1, y2, y3])
def yolo3_spp_xception_body(inputs, num_anchors, num_classes):
"""Create YOLO_V3 SPP Xception model CNN body in Keras."""
xception = Xception(input_tensor=inputs,
weights='imagenet',
include_top=False)
# input: 416 x 416 x 3
# block14_sepconv2_act: 13 x 13 x 2048
# block13_sepconv2_bn(middle in block13): 26 x 26 x 1024
# add_46(end of block12): 26 x 26 x 728
# block4_sepconv2_bn(middle in block4) : 52 x 52 x 728
# add_37(end of block3) : 52 x 52 x 256
# f1: 13 x 13 x 2048
f1 = xception.get_layer('block14_sepconv2_act').output
# f2: 26 x 26 x 1024
f2 = xception.get_layer('block13_sepconv2_bn').output
# f3: 52 x 52 x 728
f3 = xception.get_layer('block4_sepconv2_bn').output
#f1_channel_num = 2048
#f2_channel_num = 1024
#f3_channel_num = 728
f1_channel_num = 1024
f2_channel_num = 512
f3_channel_num = 256
#feature map 1 head & output (13x13 for 416 input)
x, y1 = make_spp_last_layers(f1, f1_channel_num // 2,
num_anchors * (num_classes + 5))
#upsample fpn merge for feature map 1 & 2
x = compose(DarknetConv2D_BN_Leaky(f2_channel_num // 2, (1, 1)),
UpSampling2D(2))(x)
x = Concatenate()([x, f2])
#feature map 2 head & output (26x26 for 416 input)
x, y2 = make_last_layers(x, f2_channel_num // 2,
num_anchors * (num_classes + 5))
#upsample fpn merge for feature map 2 & 3
x = compose(DarknetConv2D_BN_Leaky(f3_channel_num // 2, (1, 1)),
UpSampling2D(2))(x)
x = Concatenate()([x, f3])
#feature map 3 head & output (52x52 for 416 input)
x, y3 = make_last_layers(x, f3_channel_num // 2,
num_anchors * (num_classes + 5))
return Model(inputs=inputs, outputs=[y1, y2, y3])
def yolo3_spp_body(inputs, num_anchors, num_classes, weights_path=None):
"""Create YOLO_V3 SPP model CNN body in Keras."""
darknet = Model(inputs, darknet53_body(inputs))
if weights_path is not None:
darknet.load_weights(weights_path, by_name=True)
print('Load weights {}.'.format(weights_path))
#x, y1 = make_last_layers(darknet.output, 512, num_anchors*(num_classes+5))
x, y1 = make_spp_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 yolo3_spp_body(inputs, num_anchors, num_classes, weights_path=None):
"""Create YOLO_V3 SPP model CNN body in Keras."""
darknet = Model(inputs, darknet53_body(inputs))
if weights_path is not None:
darknet.load_weights(weights_path, by_name=True)
print('Load weights {}.'.format(weights_path))
# f1: 13 x 13 x 1024
f1 = darknet.output
# f2: 26 x 26 x 512
f2 = darknet.layers[152].output
# f3: 52 x 52 x 256
f3 = darknet.layers[92].output
f1_channel_num = 1024
f2_channel_num = 512
f3_channel_num = 256
# feature map 1 head & output (19x19 for 608 input)
x, y1 = make_spp_last_layers(f1, f1_channel_num // 2,
num_anchors * (num_classes + 5))
# upsample fpn merge for feature map 1 & 2
x = compose(DarknetConv2D_BN_Leaky(f2_channel_num // 2, (1, 1)),
UpSampling2D(2))(x)
x = Concatenate()([x, f2])
# feature map 2 head & output (38x38 for 608 input)
x, y2 = make_last_layers(x, f2_channel_num // 2,
num_anchors * (num_classes + 5))
# upsample fpn merge for feature map 2 & 3
x = compose(DarknetConv2D_BN_Leaky(f3_channel_num // 2, (1, 1)),
UpSampling2D(2))(x)
x = Concatenate()([x, f3])
# feature map 3 head & output (76x76 for 608 input)
x, y3 = make_last_layers(x, f3_channel_num // 2,
num_anchors * (num_classes + 5))
return Model(inputs, [y1, y2, y3])