def yolo3_ultralite_mobilenetv3small_body(inputs, num_anchors, num_classes, alpha=1.0):
'''Create YOLO_v3 Ultra-Lite MobileNetV3Small model CNN body in keras.'''
mobilenetv3small = MobileNetV3Small(input_tensor=inputs, weights='imagenet', include_top=False, alpha=alpha)
print('backbone layers number: {}'.format(len(mobilenetv3small.layers)))
# input: 416 x 416 x 3
# activation_31(layer 165, final feature map): 13 x 13 x (576*alpha)
# expanded_conv_10/Add(layer 162, end of block10): 13 x 13 x (96*alpha)
# activation_22(layer 117, middle in block8) : 26 x 26 x (288*alpha)
# expanded_conv_7/Add(layer 114, end of block7) : 26 x 26 x (48*alpha)
# activation_7(layer 38, middle in block3) : 52 x 52 x (96*alpha)
# expanded_conv_2/Add(layer 35, end of block2): 52 x 52 x (24*alpha)
# NOTE: activation layer name may different for TF1.x/2.x, so we
# use index to fetch layer
# f1 :13 x 13 x (576*alpha)
f1 = mobilenetv3small.layers[165].output
# f2: 26 x 26 x (288*alpha)
f2 = mobilenetv3small.layers[117].output
# f3 : 52 x 52 x (96*alpha)
f3 = mobilenetv3small.layers[38].output
f1_channel_num = int(576*alpha)
f2_channel_num = int(288*alpha)
f3_channel_num = int(96*alpha)
#f1_channel_num = 1024
#f2_channel_num = 512
#f3_channel_num = 256
y1, y2, y3 = yolo3_ultralite_predictions((f1, f2, f3), (f1_channel_num, f2_channel_num, f3_channel_num), num_anchors, num_classes)
return Model(inputs = inputs, outputs=[y1,y2,y3])
def yolo3_ultralite_peleenet_body(inputs, num_anchors, num_classes):
'''Create YOLO_v3 Ultra-Lite PeleeNet model CNN body in keras.'''
peleenet = PeleeNet(input_tensor=inputs,
weights='imagenet',
include_top=False)
print('backbone layers number: {}'.format(len(peleenet.layers)))
# input: 416 x 416 x 3
# re_lu_338(layer 365, final feature map): 13 x 13 x 704
# re_lu_307(layer 265, end of stride 16) : 26 x 26 x 512
# re_lu_266(layer 133, end of stride 8) : 52 x 52 x 256
# NOTE: activation layer name may different for TF1.x/2.x, so we
# use index to fetch layer
# f1: 13 x 13 x 704
f1 = peleenet.layers[365].output
# f2: 26 x 26 x 512
f2 = peleenet.layers[265].output
# f3: 52 x 52 x 256
f3 = peleenet.layers[133].output
f1_channel_num = 704
f2_channel_num = 512
f3_channel_num = 256
y1, y2, y3 = yolo3_ultralite_predictions(
(f1, f2, f3), (f1_channel_num, f2_channel_num, f3_channel_num),
num_anchors, num_classes)
return Model(inputs=inputs, outputs=[y1, y2, y3])
def yolo3_ultralite_mobilenetv2_body(inputs, num_anchors, num_classes, alpha=1.0):
'''Create YOLO_v3 Ultra-Lite MobileNetV2 model CNN body in keras.'''
mobilenetv2 = MobileNetV2(input_tensor=inputs, weights='imagenet', include_top=False, alpha=alpha)
print('backbone layers number: {}'.format(len(mobilenetv2.layers)))
# input: 416 x 416 x 3
# out_relu: 13 x 13 x 1280
# block_13_expand_relu: 26 x 26 x (576*alpha)
# block_6_expand_relu: 52 x 52 x (192*alpha)
# f1 :13 x 13 x 1280
f1 = mobilenetv2.get_layer('out_relu').output
# f2: 26 x 26 x (576*alpha)
f2 = mobilenetv2.get_layer('block_13_expand_relu').output
# f3 : 52 x 52 x (192*alpha)
f3 = mobilenetv2.get_layer('block_6_expand_relu').output
f1_channel_num = int(1280*alpha)
f2_channel_num = int(576*alpha)
f3_channel_num = int(192*alpha)
#f1_channel_num = 1024
#f2_channel_num = 512
#f3_channel_num = 256
y1, y2, y3 = yolo3_ultralite_predictions((f1, f2, f3), (f1_channel_num, f2_channel_num, f3_channel_num), num_anchors, num_classes)
return Model(inputs = inputs, outputs=[y1,y2,y3])
def yolo3_ultralite_ghostnet_body(inputs, num_anchors, num_classes):
'''Create YOLO_v3 Ultra-Lite GhostNet model CNN body in keras.'''
ghostnet = GhostNet(input_tensor=inputs,
weights='imagenet',
include_top=False)
print('backbone layers number: {}'.format(len(ghostnet.layers)))
# input: 416 x 416 x 3
# blocks_9_0_relu(layer 291, final feature map): 13 x 13 x 960
# blocks_8_3_add(layer 288, end of block8): 13 x 13 x 160
# blocks_7_0_ghost1_concat(layer 203, middle in block7) : 26 x 26 x 672
# blocks_6_4_add(layer 196, end of block6) : 26 x 26 x 112
# blocks_5_0_ghost1_concat(layer 101, middle in block5) : 52 x 52 x 240
# blocks_4_0_add(layer 94, end of block4): 52 x 52 x 40
# NOTE: activation layer name may different for TF1.x/2.x, so we
# use index to fetch layer
# f1: 13 x 13 x 960
f1 = ghostnet.layers[291].output
# f2: 26 x 26 x 672
f2 = ghostnet.layers[203].output
# f3: 52 x 52 x 240
f3 = ghostnet.layers[101].output
f1_channel_num = 960
f2_channel_num = 672
f3_channel_num = 240
y1, y2, y3 = yolo3_ultralite_predictions(
(f1, f2, f3), (f1_channel_num, f2_channel_num, f3_channel_num),
num_anchors, num_classes)
return Model(inputs=inputs, outputs=[y1, y2, y3])
