def yolo2_mobilenetv3large_body(inputs, num_anchors, num_classes, alpha=1.0):
"""Create YOLO_V2 MobileNetV3Large model CNN body in Keras."""
mobilenetv3large = MobileNetV3Large(input_tensor=inputs,
weights='imagenet',
include_top=False,
alpha=alpha)
print('backbone layers number: {}'.format(len(mobilenetv3large.layers)))
# input: 416 x 416 x 3
# mobilenetv3large.output(layer 194, final feature map): 13 x 13 x (960*alpha)
# expanded_conv_14/Add(layer 191, end of block14): 13 x 13 x (160*alpha)
# activation_29(layer 146, middle in block12) : 26 x 26 x (672*alpha)
# expanded_conv_11/Add(layer 143, end of block11) : 26 x 26 x (112*alpha)
# NOTE: activation layer name may different for TF1.x/2.x, so we
# use index to fetch layer
# f1: 13 x 13 x (960*alpha)
f1 = mobilenetv3large.output
# f2: 26 x 26 x (672*alpha)
f2 = mobilenetv3large.layers[146].output
f1_channel_num = int(960 * alpha)
f2_channel_num = int(672 * alpha)
y = yolo2_predictions((f1, f2), (f1_channel_num, f2_channel_num),
num_anchors, num_classes)
return Model(inputs, y)
def yolo2_xception_body(inputs, num_anchors, num_classes):
"""Create YOLO_V2 Xception model CNN body in Keras."""
xception = Xception(input_tensor=inputs,
weights='imagenet',
include_top=False)
print('backbone layers number: {}'.format(len(xception.layers)))
# input: 416 x 416 x 3
# xception.output: 13 x 13 x 2048
# block13_sepconv2_bn(middle in block13, layers[121]): 26 x 26 x 1024
# add_46(end of block12, layers[115]): 26 x 26 x 728
# f1: 13 x 13 x 2048
f1 = xception.output
# f2: 26 x 26 x 1024
f2 = xception.layers[121].output
f1_channel_num = 2048
f2_channel_num = 1024
#f1_channel_num = 1024
#f2_channel_num = 512
y = yolo2_predictions((f1, f2), (f1_channel_num, f2_channel_num),
num_anchors, num_classes)
return Model(inputs, y)
def yolo2_efficientnet_body(inputs, num_anchors, num_classes, level=0):
'''
Create YOLO_v2 EfficientNet model CNN body in keras.
# Arguments
level: EfficientNet level number.
by default we use basic EfficientNetB0 as backbone
'''
efficientnet, feature_map_info = get_efficientnet_backbone_info(inputs, level=level)
print('backbone layers number: {}'.format(len(efficientnet.layers)))
f1 = efficientnet.get_layer('top_activation').output
f1_channel_num = feature_map_info['f1_channel_num']
f2 = efficientnet.get_layer('block6a_expand_activation').output
f2_channel_num = feature_map_info['f2_channel_num']
y = yolo2_predictions((f1, f2), (f1_channel_num, f2_channel_num), num_anchors, num_classes)
return Model(inputs, y)
def yolo2_body(inputs, num_anchors, num_classes, weights_path=None):
"""Create YOLO_V2 model CNN body in Keras."""
darknet19 = Model(inputs, darknet19_body()(inputs))
if weights_path is not None:
darknet19.load_weights(weights_path, by_name=True)
print('Load weights {}.'.format(weights_path))
# input: 416 x 416 x 3
# darknet19.output : 13 x 13 x 1024
# conv13(layers[43]) : 26 x 26 x 512
print('backbone layers number: {}'.format(len(darknet19.layers)))
# f1: 13 x 13 x 1024
f1 = darknet19.output
# f2: 26 x 26 x 512
f2 = darknet19.layers[43].output
f1_channel_num = 1024
f2_channel_num = 512
y = yolo2_predictions((f1, f2), (f1_channel_num, f2_channel_num),
num_anchors, num_classes)
return Model(inputs, y)
def yolo2_mobilenet_body(inputs, num_anchors, num_classes, alpha=1.0):
"""Create YOLO_V2 MobileNet model CNN body in Keras."""
mobilenet = MobileNet(input_tensor=inputs,
weights='imagenet',
include_top=False,
alpha=alpha)
print('backbone layers number: {}'.format(len(mobilenet.layers)))
# input: 416 x 416 x 3
# mobilenet.output : 13 x 13 x (1024*alpha)
# conv_pw_11_relu(layers[73]) : 26 x 26 x (512*alpha)
# f1: 13 x 13 x (1024*alpha)
f1 = mobilenet.output
# f2: 26 x 26 x (512*alpha)
f2 = mobilenet.get_layer('conv_pw_11_relu').output
f1_channel_num = int(1024 * alpha)
f2_channel_num = int(512 * alpha)
y = yolo2_predictions((f1, f2), (f1_channel_num, f2_channel_num),
num_anchors, num_classes)
return Model(inputs, y)
def yolo2_mobilenetv2_body(inputs, num_anchors, num_classes, alpha=1.0):
"""Create YOLO_V2 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
# mobilenetv2.output : 13 x 13 x 1280
# block_13_expand_relu(layers[119]) : 26 x 26 x (576*alpha)
# f1: 13 x 13 x 1280
f1 = mobilenetv2.output
# f2: 26 x 26 x (576*alpha)
f2 = mobilenetv2.get_layer('block_13_expand_relu').output
f1_channel_num = 1280
f2_channel_num = int(576 * alpha)
y = yolo2_predictions((f1, f2), (f1_channel_num, f2_channel_num),
num_anchors, num_classes)
return Model(inputs, y)
def yolo2_mobilenetv3small_body(inputs, num_anchors, num_classes, alpha=1.0):
"""Create YOLO_V2 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
# mobilenetv3small.output(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)
# NOTE: activation layer name may different for TF1.x/2.x, so we
# use index to fetch layer
# f1: 13 x 13 x (960*alpha)
f1 = mobilenetv3small.output
# f2: 26 x 26 x (672*alpha)
f2 = mobilenetv3small.layers[117].output
f1_channel_num = int(576*alpha)
f2_channel_num = int(288*alpha)
y = yolo2_predictions((f1, f2), (f1_channel_num, f2_channel_num), num_anchors, num_classes)
return Model(inputs, y)