def __build_nework(self, input_data):
"""
It is better look at this function with the Yolo_v3_Structure diagram made by Levio
One link is here: https://github.com/wizyoung/YOLOv3_TensorFlow
"""
# by YZ, these are the three feature extractions from darknet53, with difference dimension reductions (by 8, 16, 32)
route_1, route_2, input_data = backbone.darknet53(input_data, self.trainable)
# input_data is -1*13*13*1024
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv52')
input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, 'conv53')
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv54')
input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, 'conv55')
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv56')
conv_lobj_branch = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, name='conv_lobj_branch')
conv_lbbox = common.convolutional(conv_lobj_branch, (1, 1, 1024, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_lbbox', activate=False, bn=False)
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv57')
# upsampling input data (1/32) to match route_2 (1/16), -1*26*16*512
input_data = common.upsample(input_data, name='upsample0', method=self.upsample_method)
with tf.variable_scope('route_1'):
# route_2 is -1*26*26*256, so input_data is -1*26*26*768
input_data = tf.concat([input_data, route_2], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 768, 256), self.trainable, 'conv58')
input_data = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, 'conv59')
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv60')
input_data = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, 'conv61')
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv62')
conv_mobj_branch = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, name='conv_mobj_branch' )
conv_mbbox = common.convolutional(conv_mobj_branch, (1, 1, 512, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_mbbox', activate=False, bn=False)
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv63')
input_data = common.upsample(input_data, name='upsample1', method=self.upsample_method)
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 384, 128), self.trainable, 'conv64')
input_data = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, 'conv65')
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv66')
input_data = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, 'conv67')
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv68')
conv_sobj_branch = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, name='conv_sobj_branch')
conv_sbbox = common.convolutional(conv_sobj_branch, (1, 1, 256, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_sbbox', activate=False, bn=False)
# dimensions are: -1*13*13*255, -1*26*26*255, -1*52*52*255
return conv_lbbox, conv_mbbox, conv_sbbox
def __build_nework(self, input_layer, training):
route_1, route_2, conv = backbone.darknet53(input_layer, training)
conv = common.convolutional(conv, (1, 1, 1024, 512), training)
conv = common.convolutional(conv, (3, 3, 512, 1024), training)
conv = common.convolutional(conv, (1, 1, 1024, 512), training)
conv = common.convolutional(conv, (3, 3, 512, 1024), training)
conv = common.convolutional(conv, (1, 1, 1024, 512), training)
conv_lobj_branch = common.convolutional(conv, (3, 3, 512, 1024),
training)
conv_lbbox = common.convolutional(conv_lobj_branch,
(1, 1, 1024, 3 * (80 + 5)),
training,
activate=False,
bn=False)
conv = common.convolutional(conv, (1, 1, 512, 256), training)
conv = common.upsample(conv)
conv = tf.concat([conv, route_2], axis=-1)
conv = common.convolutional(conv, (1, 1, 768, 256), training)
conv = common.convolutional(conv, (3, 3, 256, 512), training)
conv = common.convolutional(conv, (1, 1, 512, 256), training)
conv = common.convolutional(conv, (3, 3, 256, 512), training)
conv = common.convolutional(conv, (1, 1, 512, 256), training)
conv_mobj_branch = common.convolutional(conv, (3, 3, 256, 512),
training)
conv_mbbox = common.convolutional(conv_mobj_branch,
(1, 1, 512, 3 * (80 + 5)),
training,
activate=False,
bn=False)
conv = common.convolutional(conv, (1, 1, 256, 128), training)
conv = common.upsample(conv)
conv = tf.concat([conv, route_1], axis=-1)
conv = common.convolutional(conv, (1, 1, 384, 128), training)
conv = common.convolutional(conv, (3, 3, 128, 256), training)
conv = common.convolutional(conv, (1, 1, 256, 128), training)
conv = common.convolutional(conv, (3, 3, 128, 256), training)
conv = common.convolutional(conv, (1, 1, 256, 128), training)
conv_sobj_branch = common.convolutional(conv, (3, 3, 128, 256),
training)
conv_sbbox = common.convolutional(conv_sobj_branch,
(1, 1, 256, 3 * (80 + 5)),
training,
activate=False,
bn=False)
return conv_lbbox, conv_mbbox, conv_sbbox
def YOLOv3(for_annother_use=False):
input_layer = tf.keras.layers.Input(shape=[416,416,3])
route_1, route_2, conv = backbone.darknet53(input_layer)
conv = common.convolutional(conv, (1, 1, 1024, 512))
sconv1 = conv = common.convolutional(conv, (3, 3, 512, 1024))
conv = common.convolutional(conv, (1, 1, 1024, 512))
sconv2 = conv = common.convolutional(conv, (3, 3, 512, 1024))
conv = common.convolutional(conv, (1, 1, 1024, 512))
sconv3 = conv_lobj_branch = common.convolutional(conv, (3, 3, 512, 1024))
conv_lbbox = common.convolutional(conv_lobj_branch, (1, 1, 1024, 3 * (NUM_CLASS + 5)), activate=False, bn=False)
conv = common.convolutional(conv, (1, 1, 512, 256))
conv = common.upsample(conv)
conv = tf.concat([conv, route_2], axis=-1)
conv = common.convolutional(conv, (1, 1, 768, 256))
mconv1 = conv = common.convolutional(conv, (3, 3, 256, 512))
conv = common.convolutional(conv, (1, 1, 512, 256))
mconv2 = conv = common.convolutional(conv, (3, 3, 256, 512))
conv = common.convolutional(conv, (1, 1, 512, 256))
mconv3 = conv_mobj_branch = common.convolutional(conv, (3, 3, 256, 512))
conv_mbbox = common.convolutional(conv_mobj_branch, (1, 1, 512, 3 * (NUM_CLASS + 5)), activate=False, bn=False)
conv = common.convolutional(conv, (1, 1, 256, 128))
conv = common.upsample(conv)
conv = tf.concat([conv, route_1], axis=-1)
conv = common.convolutional(conv, (1, 1, 384, 128))
lconv1 = conv = common.convolutional(conv, (3, 3, 128, 256))
conv = common.convolutional(conv, (1, 1, 256, 128))
lconv2 = conv = common.convolutional(conv, (3, 3, 128, 256))
conv = common.convolutional(conv, (1, 1, 256, 128))
lconv3 = conv_sobj_branch = common.convolutional(conv, (3, 3, 128, 256))
conv_sbbox = common.convolutional(conv_sobj_branch, (1, 1, 256, 3 * (NUM_CLASS + 5)), activate=False, bn=False)
if for_annother_use:
convs_sbbox = tf.concat([lconv1, lconv2, lconv3], axis=-1, name="lfeature")
convs_mbbox = tf.concat([mconv1, mconv2, mconv3], axis=-1, name="mfeature")
convs_lbbox = tf.concat([sconv1, sconv2, sconv3], axis=-1, name="sfeature")
yolo = Model(input_layer,[conv_sbbox, conv_mbbox, conv_lbbox, convs_sbbox,convs_mbbox,convs_lbbox])
# 52,26,13 52,26,13
yolo.load_weights(filepath=tf.keras.utils.get_file('yolo3.h5',''))
yolo.trainable = False
else:
# classic YOLOV3 model trained for coco datasets
yolo = Model(input_layer, [conv_sbbox, conv_mbbox, conv_lbbox])
yolo.load_weights(filepath=tf.keras.utils.get_file('yolo3.h5',''))
yolo.trainable =False
return yolo
def __build_nework(self, input_data):
route_1, route_2, input_data = backbone.darknet53(input_data, self.trainable)
# input_data is -1*13*13*1024
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv52')
input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, 'conv53')
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv54')
input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, 'conv55')
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv56')
conv_lobj_branch = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, name='conv_lobj_branch')
conv_lbbox = common.convolutional(conv_lobj_branch, (1, 1, 1024, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_lbbox', activate=False, bn=False)
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv57')
# upsampling input data (1/32) to match route_2 (1/16), -1*26*16*512
input_data = common.upsample(input_data, name='upsample0', method=self.upsample_method)
with tf.variable_scope('route_1'):
# route_2 is -1*26*26*256, so input_data is -1*26*26*768
input_data = tf.concat([input_data, route_2], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 768, 256), self.trainable, 'conv58')
input_data = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, 'conv59')
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv60')
input_data = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, 'conv61')
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv62')
conv_mobj_branch = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, name='conv_mobj_branch' )
conv_mbbox = common.convolutional(conv_mobj_branch, (1, 1, 512, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_mbbox', activate=False, bn=False)
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv63')
input_data = common.upsample(input_data, name='upsample1', method=self.upsample_method)
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 384, 128), self.trainable, 'conv64')
input_data = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, 'conv65')
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv66')
input_data = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, 'conv67')
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv68')
conv_sobj_branch = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, name='conv_sobj_branch')
conv_sbbox = common.convolutional(conv_sobj_branch, (1, 1, 256, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_sbbox', activate=False, bn=False)
# dimensions are: -1*13*13*255, -1*26*26*255, -1*52*52*255
return conv_lbbox, conv_mbbox, conv_sbbox
def YOLOv3(input_layer):
route_1, route_2, conv = backbone.darknet53(input_layer)
original_conv = conv
conv = common.convolutional(conv, (1, 1, 1024, 512))
conv = common.convolutional(conv, (3, 3, 512, 1024))
conv = common.convolutional(conv, (1, 1, 1024, 512))
conv = common.convolutional(conv, (3, 3, 512, 1024))
conv = common.convolutional(conv, (1, 1, 1024, 512))
conv_lobj_branch = common.convolutional(conv, (3, 3, 512, 1024))
conv_lbbox = common.convolutional(conv_lobj_branch,
(1, 1, 1024, 3 * (NUM_CLASS + 5)),
activate=False,
bn=False)
conv = common.convolutional(conv, (1, 1, 512, 256))
conv = common.upsample(conv)
conv = tf.concat([conv, route_2], axis=-1)
conv = common.convolutional(conv, (1, 1, 768, 256))
conv = common.convolutional(conv, (3, 3, 256, 512))
conv = common.convolutional(conv, (1, 1, 512, 256))
conv = common.convolutional(conv, (3, 3, 256, 512))
conv = common.convolutional(conv, (1, 1, 512, 256))
conv_mobj_branch = common.convolutional(conv, (3, 3, 256, 512))
conv_mbbox = common.convolutional(conv_mobj_branch,
(1, 1, 512, 3 * (NUM_CLASS + 5)),
activate=False,
bn=False)
conv = common.convolutional(conv, (1, 1, 256, 128))
conv = common.upsample(conv)
conv = tf.concat([conv, route_1], axis=-1)
conv = common.convolutional(conv, (1, 1, 384, 128))
conv = common.convolutional(conv, (3, 3, 128, 256))
conv = common.convolutional(conv, (1, 1, 256, 128))
conv = common.convolutional(conv, (3, 3, 128, 256))
conv = common.convolutional(conv, (1, 1, 256, 128))
conv_sobj_branch = common.convolutional(conv, (3, 3, 128, 256))
conv_sbbox = common.convolutional(conv_sobj_branch,
(1, 1, 256, 3 * (NUM_CLASS + 5)),
activate=False,
bn=False)
return [conv_sbbox, conv_mbbox,
conv_lbbox], (route_1, route_2, original_conv)
def YOLOv3(input_layer):
"""
build the whole network of YOLOv3
:param input_layer: [batch, 416, 416, 3]
:return: 3 scale predictions [[b, 52, 52, anchors*(5+classes)], [b, 26, 26, anchors*(5+classes)], [b, 13, 13, anchors*(5+classes)]]
"""
route_1, route_2, conv = backbone.darknet53(
input_layer
) # call darknet to get the basic network, [52,52,256], [26,26,512], [13,13,1024]
"""large scale output [batch, 13, 13, 3*(5+c)]"""
conv = common.convolutional(conv, (1, 1, 1024, 512), conv_trainable=False)
conv = common.convolutional(conv, (3, 3, 512, 1024), conv_trainable=False)
conv = common.convolutional(conv, (1, 1, 1024, 512), conv_trainable=False)
conv = common.convolutional(conv, (3, 3, 512, 1024))
conv = common.convolutional(conv, (1, 1, 1024, 512))
conv_lobj_branch = common.convolutional(conv, (3, 3, 512, 1024))
conv_lbbox = common.convolutional(conv_lobj_branch,
(1, 1, 1024, 3 * (NUM_CLASS + 5)),
activate=False,
bn=False)
"""the medium scale output, [batch, 26, 26, 3*(NUM_CLASS+5)]"""
conv = common.convolutional(conv, (1, 1, 512, 256), conv_trainable=False)
conv = common.upsample(conv)
conv = tf.concat([conv, route_2], axis=-1) # concat in channel dimension
conv = common.convolutional(conv, (1, 1, 768, 256), conv_trainable=False)
conv = common.convolutional(conv, (3, 3, 256, 512), conv_trainable=False)
conv = common.convolutional(conv, (1, 1, 512, 256), conv_trainable=False)
conv = common.convolutional(conv, (3, 3, 256, 512))
conv = common.convolutional(conv, (1, 1, 512, 256))
conv_mobj_branch = common.convolutional(conv, (3, 3, 256, 512))
conv_mbbox = common.convolutional(conv_mobj_branch,
(1, 1, 512, 3 * (NUM_CLASS + 5)),
activate=False,
bn=False)
"""the small scale output, [batch, 52, 52, 3*(NUM_CLASS+5)]"""
conv = common.convolutional(conv, (1, 1, 256, 128), conv_trainable=False)
conv = common.upsample(conv)
conv = tf.concat([conv, route_1], axis=-1) # concat in channel dimension
conv = common.convolutional(conv, (1, 1, 384, 128), conv_trainable=False)
conv = common.convolutional(conv, (3, 3, 128, 256), conv_trainable=False)
conv = common.convolutional(conv, (1, 1, 256, 128), conv_trainable=False)
conv = common.convolutional(conv, (3, 3, 128, 256))
conv = common.convolutional(conv, (1, 1, 256, 128))
conv_sobj_branch = common.convolutional(conv, (3, 3, 128, 256))
conv_sbbox = common.convolutional(conv_sobj_branch,
(1, 1, 256, 3 * (NUM_CLASS + 5)),
activate=False,
bn=False)
return [conv_sbbox, conv_mbbox, conv_lbbox]
def __build_nework(self, input_data):
route_1, route_2, input_data = backbone.darknet53(input_data)
input_data = common.convolutional(input_data, (1, 1, 1024, 512))
input_data = common.convolutional(input_data, (3, 3, 512, 1024))
input_data = common.convolutional(input_data, (1, 1, 1024, 512))
input_data = common.convolutional(input_data, (3, 3, 512, 1024))
input_data = common.convolutional(input_data, (1, 1, 1024, 512))
conv_lobj_branch = common.convolutional(input_data, (3, 3, 512, 1024))
conv_lbbox = common.convolutional(conv_lobj_branch,
(1, 1, 1024, 3 * (80 + 5)),
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 512, 256))
input_data = common.upsample(input_data)
input_data = tf.concat([input_data, route_2], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 768, 256))
input_data = common.convolutional(input_data, (3, 3, 256, 512))
input_data = common.convolutional(input_data, (1, 1, 512, 256))
input_data = common.convolutional(input_data, (3, 3, 256, 512))
input_data = common.convolutional(input_data, (1, 1, 512, 256))
conv_mobj_branch = common.convolutional(input_data, (3, 3, 256, 512))
conv_mbbox = common.convolutional(conv_mobj_branch,
(1, 1, 512, 3 * (80 + 5)),
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 256, 128))
input_data = common.upsample(input_data)
input_data = tf.concat([input_data, route_1], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 384, 128))
input_data = common.convolutional(input_data, (3, 3, 128, 256))
input_data = common.convolutional(input_data, (1, 1, 256, 128))
input_data = common.convolutional(input_data, (3, 3, 128, 256))
input_data = common.convolutional(input_data, (1, 1, 256, 128))
conv_sobj_branch = common.convolutional(input_data, (3, 3, 128, 256))
conv_sbbox = common.convolutional(conv_sobj_branch,
(1, 1, 256, 3 * (80 + 5)),
activate=False,
bn=False)
return conv_lbbox, conv_mbbox, conv_sbbox
def __build_nework(self, input_data):
route_1, route_2, input_data = backbone.darknet53(input_data, self.trainable)
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv52')
input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, 'conv53')
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv54')
input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, 'conv55')
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv56')
conv_lobj_branch = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, name='conv_lobj_branch')
conv_lbbox = common.convolutional(conv_lobj_branch, (1, 1, 1024, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_lbbox', activate=False, bn=False)
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv57')
input_data = common.upsample(input_data, name='upsample0', method=self.upsample_method)
with tf.variable_scope('route_1'):
input_data = tf.concat([input_data, route_2], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 768, 256), self.trainable, 'conv58')
input_data = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, 'conv59')
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv60')
input_data = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, 'conv61')
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv62')
conv_mobj_branch = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, name='conv_mobj_branch' )
conv_mbbox = common.convolutional(conv_mobj_branch, (1, 1, 512, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_mbbox', activate=False, bn=False)
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv63')
input_data = common.upsample(input_data, name='upsample1', method=self.upsample_method)
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 384, 128), self.trainable, 'conv64')
input_data = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, 'conv65')
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv66')
input_data = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, 'conv67')
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv68')
conv_sobj_branch = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, name='conv_sobj_branch')
conv_sbbox = common.convolutional(conv_sobj_branch, (1, 1, 256, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_sbbox', activate=False, bn=False)
return conv_lbbox, conv_mbbox, conv_sbbox
def structure_network(self, input_data):
# 调取 darknet53 网络，获取 3 个尺度的返回值
route_1, route_2, input_data = backbone.darknet53(input_data, self.training_flag)
# conv set 操作 conv: 1 x 1 -> 3 x 3 -> 1 x 1 -> 3 x 3 -> 1 x 1
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.training_flag, 'conv52')
input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.training_flag, 'conv53')
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.training_flag, 'conv54')
input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.training_flag, 'conv55')
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.training_flag, 'conv56')
# scale one 小尺度的 feature maps: conv set -> conv 3 x 3 -> 1 x 1
conv_lobj_branch = common.convolutional(input_data, (3, 3, 512, 1024),
self.training_flag, name='conv_lobj_branch')
# 3 * (self.num_class + 5) 表示为: 每个尺度有 3 个 anchors，每个 anchor 有 5 + num_class 个值
# 5 = 4 + 1, 4个 坐标值，1 个置信度，num_class 表示分类的数量
conv_lbbox = common.convolutional(conv_lobj_branch, (1, 1, 1024, 3 * (self.num_class + 5)),
training_flag=self.training_flag, name='conv_lbbox',
activate=False, bn=False)
# 进入另一个分支点: conv set -> 1 x 1 -> up_sampling -> concatenate
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.training_flag, 'conv57')
input_data = common.up_sample(input_data, name='up_sample0', method=self.up_sample_method)
with tf.variable_scope('route_1'):
input_data = tf.concat([input_data, route_2], axis=-1)
# conv set 操作 conv: 1 x 1 -> 3 x 3 -> 1 x 1 -> 3 x 3 -> 1 x 1
input_data = common.convolutional(input_data, (1, 1, 768, 256), self.training_flag, 'conv58')
input_data = common.convolutional(input_data, (3, 3, 256, 512), self.training_flag, 'conv59')
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.training_flag, 'conv60')
input_data = common.convolutional(input_data, (3, 3, 256, 512), self.training_flag, 'conv61')
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.training_flag, 'conv62')
# scale two 中尺度的 feature maps: conv set -> conv 3 x 3 -> 1 x 1
conv_mobj_branch = common.convolutional(input_data, (3, 3, 256, 512),
self.training_flag, name='conv_mobj_branch')
conv_mbbox = common.convolutional(conv_mobj_branch, (1, 1, 512, 3 * (self.num_class + 5)),
training_flag=self.training_flag, name='conv_mbbox',
activate=False, bn=False)
# 进入另一个分支点: conv set -> 1 x 1 -> up_sampling -> concatenate
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.training_flag, 'conv63')
input_data = common.up_sample(input_data, name='up_sample1', method=self.up_sample_method)
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)
# conv set 操作 conv: 1 x 1 -> 3 x 3 -> 1 x 1 -> 3 x 3 -> 1 x 1
input_data = common.convolutional(input_data, (1, 1, 384, 128), self.training_flag, 'conv64')
input_data = common.convolutional(input_data, (3, 3, 128, 256), self.training_flag, 'conv65')
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.training_flag, 'conv66')
input_data = common.convolutional(input_data, (3, 3, 128, 256), self.training_flag, 'conv67')
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.training_flag, 'conv68')
# scale three 大尺度的 feature maps: conv set -> conv 3 x 3 -> 1 x 1
conv_sobj_branch = common.convolutional(input_data, (3, 3, 128, 256),
self.training_flag, name='conv_sobj_branch')
conv_sbbox = common.convolutional(conv_sobj_branch, (1, 1, 256, 3 * (self.num_class + 5)),
training_flag=self.training_flag, name='conv_sbbox',
activate=False, bn=False)
# 将 3 个尺度 小、中、大 的 feature maps 类似于 13 x 13 大小的那种 feature maps
return conv_lbbox, conv_mbbox, conv_sbbox
pass
def __build_nework(self, input_data):
print('__build_nework self.net_type=', self.net_type)
assert self.net_type in [
'darknet53', 'mobilenetv2', 'mobilenetv3', 'mobilenetv3_small'
]
if self.net_type == 'darknet53':
route_1, route_2, input_data = backbone.darknet53(
input_data, self.trainable)
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv52')
input_data = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable, 'conv53')
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv54')
input_data = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable, 'conv55')
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv56')
conv_lobj_branch = common.convolutional(input_data,
(3, 3, 512, 1024),
self.trainable,
name='conv_lobj_branch')
conv_lbbox = common.convolutional(
conv_lobj_branch, (1, 1, 1024, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_lbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv57')
input_data = common.upsample(input_data,
name='upsample0',
method=self.upsample_method)
with tf.variable_scope('route_1'):
input_data = tf.concat([input_data, route_2], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 768, 256),
self.trainable, 'conv58')
input_data = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable, 'conv59')
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv60')
input_data = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable, 'conv61')
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv62')
conv_mobj_branch = common.convolutional(input_data,
(3, 3, 256, 512),
self.trainable,
name='conv_mobj_branch')
conv_mbbox = common.convolutional(
conv_mobj_branch, (1, 1, 512, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_mbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv63')
input_data = common.upsample(input_data,
name='upsample1',
method=self.upsample_method)
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 384, 128),
self.trainable, 'conv64')
input_data = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable, 'conv65')
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv66')
input_data = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable, 'conv67')
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv68')
conv_sobj_branch = common.convolutional(input_data,
(3, 3, 128, 256),
self.trainable,
name='conv_sobj_branch')
conv_sbbox = common.convolutional(
conv_sobj_branch, (1, 1, 256, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_sbbox',
activate=False,
bn=False)
return conv_lbbox, conv_mbbox, conv_sbbox
elif self.net_type == 'mobilenetv2':
route_1, route_2, input_data = backbone.mobilenetv2(
input_data, self.trainable)
input_data = common.convolutional(input_data, (1, 1, 320, 160),
self.trainable, 'conv18')
input_data = common.convolutional(input_data, (3, 3, 160, 320),
self.trainable, 'conv19')
input_data = common.convolutional(input_data, (1, 1, 320, 160),
self.trainable, 'conv20')
conv_lobj_branch = common.convolutional(input_data,
(3, 3, 160, 320),
self.trainable,
name='conv_lobj_branch')
conv_lbbox = common.convolutional(
conv_lobj_branch, (1, 1, 320, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_lbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 160, 80),
self.trainable, 'conv21')
input_data = common.upsample(input_data,
name='upsample0',
method=self.upsample_method)
with tf.variable_scope('route_1'):
input_data = tf.concat([input_data, route_2], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 176, 80),
self.trainable, 'conv22')
input_data = common.convolutional(input_data, (3, 3, 80, 160),
self.trainable, 'conv23')
input_data = common.convolutional(input_data, (1, 1, 160, 80),
self.trainable, 'conv24')
conv_mobj_branch = common.convolutional(input_data,
(3, 3, 80, 160),
self.trainable,
name='conv_mobj_branch')
conv_mbbox = common.convolutional(
conv_mobj_branch, (1, 1, 160, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_mbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 80, 40),
self.trainable, 'conv25')
input_data = common.upsample(input_data,
name='upsample1',
method=self.upsample_method)
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 72, 40),
self.trainable, 'conv26')
input_data = common.convolutional(input_data, (3, 3, 40, 80),
self.trainable, 'conv27')
input_data = common.convolutional(input_data, (1, 1, 80, 40),
self.trainable, 'conv28')
conv_sobj_branch = common.convolutional(input_data, (3, 3, 40, 80),
self.trainable,
name='conv_sobj_branch')
conv_sbbox = common.convolutional(
conv_sobj_branch, (1, 1, 80, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_sbbox',
activate=False,
bn=False)
return conv_lbbox, conv_mbbox, conv_sbbox
elif self.net_type == 'mobilenetv3':
route_1, route_2, input_data = backbone.mobilenetv3(
input_data, self.trainable)
input_data = common.convolutional(input_data, (1, 1, 160, 80),
self.trainable, 'conv8')
input_data = common.convolutional(input_data, (3, 3, 80, 160),
self.trainable, 'conv9')
input_data = common.convolutional(input_data, (1, 1, 160, 80),
self.trainable, 'conv10')
conv_lobj_branch = common.convolutional(input_data,
(3, 3, 80, 160),
self.trainable,
name='conv_lobj_branch')
conv_lbbox = common.convolutional(
conv_lobj_branch, (1, 1, 160, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_lbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 80, 40),
self.trainable, 'conv11')
input_data = common.upsample(input_data,
name='upsample0',
method=self.upsample_method)
with tf.variable_scope('route_1'):
input_data = tf.concat([input_data, route_2], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 152, 40),
self.trainable, 'conv12')
input_data = common.convolutional(input_data, (3, 3, 40, 80),
self.trainable, 'conv13')
input_data = common.convolutional(input_data, (1, 1, 80, 40),
self.trainable, 'conv14')
conv_mobj_branch = common.convolutional(input_data, (3, 3, 40, 80),
self.trainable,
name='conv_mobj_branch')
conv_mbbox = common.convolutional(
conv_mobj_branch, (1, 1, 80, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_mbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 40, 20),
self.trainable, 'conv15')
input_data = common.upsample(input_data,
name='upsample1',
method=self.upsample_method)
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 60, 20),
self.trainable, 'conv16')
input_data = common.convolutional(input_data, (3, 3, 20, 40),
self.trainable, 'conv17')
input_data = common.convolutional(input_data, (1, 1, 40, 20),
self.trainable, 'conv18')
conv_sobj_branch = common.convolutional(input_data, (3, 3, 20, 40),
self.trainable,
name='conv_sobj_branch')
conv_sbbox = common.convolutional(
conv_sobj_branch, (1, 1, 40, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_sbbox',
activate=False,
bn=False)
return conv_lbbox, conv_mbbox, conv_sbbox
elif self.net_type == 'mobilenetv3_small':
route_1, route_2, input_data = backbone.mobilenetv3_small(
input_data, self.trainable)
input_data = common.convolutional(input_data, (1, 1, 96, 80),
self.trainable, 'conv7')
input_data = common.convolutional(input_data, (3, 3, 80, 160),
self.trainable, 'conv8')
input_data = common.convolutional(input_data, (1, 1, 160, 80),
self.trainable, 'conv9')
conv_lobj_branch = common.convolutional(input_data,
(3, 3, 80, 160),
self.trainable,
name='conv_lobj_branch')
conv_lbbox = common.convolutional(
conv_lobj_branch, (1, 1, 160, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_lbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 80, 40),
self.trainable, 'conv10')
input_data = common.upsample(input_data,
name='upsample0',
method=self.upsample_method)
with tf.variable_scope('route_1'):
input_data = tf.concat([input_data, route_2], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 88, 40),
self.trainable, 'conv11')
input_data = common.convolutional(input_data, (3, 3, 40, 80),
self.trainable, 'conv12')
input_data = common.convolutional(input_data, (1, 1, 80, 40),
self.trainable, 'conv13')
conv_mobj_branch = common.convolutional(input_data, (3, 3, 40, 80),
self.trainable,
name='conv_mobj_branch')
conv_mbbox = common.convolutional(
conv_mobj_branch, (1, 1, 80, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_mbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 40, 20),
self.trainable, 'conv14')
input_data = common.upsample(input_data,
name='upsample1',
method=self.upsample_method)
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 44, 20),
self.trainable, 'conv15')
input_data = common.convolutional(input_data, (3, 3, 20, 40),
self.trainable, 'conv16')
input_data = common.convolutional(input_data, (1, 1, 40, 20),
self.trainable, 'conv17')
conv_sobj_branch = common.convolutional(input_data, (3, 3, 20, 40),
self.trainable,
name='conv_sobj_branch')
conv_sbbox = common.convolutional(
conv_sobj_branch, (1, 1, 40, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_sbbox',
activate=False,
bn=False)
return conv_lbbox, conv_mbbox, conv_sbbox
else:
print('self.net_type=%s error' % self.net_type)
def __build_network(self, input_data):
'''
:param self:
:param input_data:
:return:
'''
# 输入层进入 Darknet-53 网络后，得到了三个分支
route_1, route_2, input_data = backbone.darknet53(input_data, self.trainable) # 输出的尺度为52,26,13
# route_1.shape=(?,52,52,256)，一个特征点代表8*8的图像 检测小目标，最小检测8*8的图像
# route_2.shape=(?,26,26,512)，一个特征点代表16*16的图像，检测中目标，最小检测16*16的图像
# route_3.shape=(?,13,13,1024)， 一个特征点代表32*32像素的图像范围，可以用来检测大目标，最小检测32*32的图像。
# ?具体大小与该批次输入的图片数量有关
# ====predict one=======#
# Convolutional Set 模块，1X1-->3X3-->1X1-->3X3-->1X1
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv52')
input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, 'conv53')
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv54')
input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, 'conv55')
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv56')
# conv_lbbox 用于预测大尺寸物体，shape = [None, 13, 13, 255],255=3*(80+5)
conv_lobj_branch = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, name='conv_lobj_branch')
conv_lbbox = common.convolutional(conv_lobj_branch, (1, 1, 1024, 3 * (self.num_class + 5)),
trainable=self.trainable, name='conv_lbbox', activate=False, bn=False)
# 上采样
# 这里的 upsample 使用的是最近邻插值方法，这样的好处在于上采样过程不需要学习，从而减少了网络参数
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv57')
input_data = common.upsample(input_data, name='upsample0', method=self.upsample_method)
# 连接
with tf.variable_scope('route_1'):
input_data = tf.concat([input_data, route_2], axis=-1)#input_data.shape(?,26,26,768),768=256(input_data)+512(route_2),第4维的拼接
# ====predict two=======#
# Convolutional Set 模块，1X1-->3X3-->1X1-->3X3-->1X1
input_data = common.convolutional(input_data, (1, 1, 768, 256), self.trainable, 'conv58')
input_data = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, 'conv59')
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv60')
input_data = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, 'conv61')
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv62')
# conv_mbbox 用于预测中等尺寸物体，shape = [None, 26, 26, 255]
conv_mobj_branch = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, name='conv_mobj_branch')
conv_mbbox = common.convolutional(conv_mobj_branch, (1, 1, 512, 3 * (self.num_class + 5)),
trainable=self.trainable, name='conv_mbbox', activate=False, bn=False)
input_data = common.convolutional(input_data, (1, 1,256, 128), self.trainable, 'conv63')
input_data = common.upsample(input_data, name='upsample1', method=self.upsample_method)
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)#input_data.shape(?,52,52,384),384=128(input_data)+256(route_1),第4维的拼接
# ====predict three=======#
# Convolutional Set 模块，1X1-->3X3-->1X1-->3X3-->1X1
input_data = common.convolutional(input_data, (1, 1, 384, 128), self.trainable, 'conv64')
input_data = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, 'conv65')
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv66')
input_data = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, 'conv67')
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv68')
# conv_sbbox 用于预测小尺寸物体，shape = [None, 52, 52, 255]
conv_sobj_branch = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, name='conv_sobj_branch')
conv_sbbox = common.convolutional(conv_sobj_branch, (1, 1, 256, 3 * (self.num_class + 5)),
trainable=self.trainable, name='conv_sbbox', activate=False, bn=False)
return conv_lbbox, conv_mbbox, conv_sbbox
def __build_nework(self, input_data):
route_1, route_2, input_data = backbone.darknet53(
input_data, self.trainable)
conv_lobj_branch = common.EP(input_data,
189,
462,
name='EP5',
stride=1)
conv_lbbox = common.convolutional(
conv_lobj_branch, (1, 1, 462, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_lbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 189, 105),
self.trainable, 'conv5')
input_data = common.upsample(input_data,
name='upsample0',
method=self.upsample_method)
input_data = tf.concat([input_data, route_2], axis=-1)
input_data = common.PEP(input_data,
430,
325,
113,
name='PEP17',
stride=1)
input_data = common.PEP(input_data,
325,
207,
99,
name='PEP18',
stride=1)
input_data = common.convolutional(input_data, (1, 1, 207, 98),
self.trainable, 'conv6')
conv_mobj_branch = common.EP(input_data, 98, 183, name='EP6', stride=1)
conv_mbbox = common.convolutional(
conv_mobj_branch, (1, 1, 183, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_mbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 98, 47),
self.trainable, 'conv7')
input_data = common.upsample(input_data,
name='upsample1',
method=self.upsample_method)
input_data = tf.concat([input_data, route_1], axis=-1)
input_data = common.PEP(input_data,
197,
122,
58,
name='PEP19',
stride=1)
input_data = common.PEP(input_data,
122,
87,
52,
name='PEP20',
stride=1)
conv_sobj_branch = common.PEP(input_data,
87,
93,
47,
name='PEP21',
stride=1)
conv_sbbox = common.convolutional(conv_sobj_branch,
(1, 1, 93, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_sbbox',
activate=False,
bn=False)
return conv_lbbox, conv_mbbox, conv_sbbox
def __build_nework(self, input_data):
#backbone.darknet53函数返回3个输出值，分贝时4倍、8倍、以及16倍下采样的输出
route_1, route_2, route_3, input_data = backbone.darknet53(input_data, self.trainable)
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv52')
input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, 'conv53')
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv54')
input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, 'conv55')
input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv56')
#conv56 得到输出13*13*512
conv_lobj_branch = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, name='conv_lobj_branch')
conv_lbbox = common.convolutional(conv_lobj_branch, (1, 1, 1024, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_lbbox', activate=False, bn=False)
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv57')
input_data = common.upsample(input_data, name='upsample0', method=self.upsample_method)
#上采样以后得到26*26*256
with tf.variable_scope('route_1'):
input_data = tf.concat([input_data, route_3], axis=-1)
#将上采样得到的输出与16倍的下采样输出26*26*512进行concat操作，得到26*26*（256+512）=26*26*768
input_data = common.convolutional(input_data, (1, 1, 768, 256), self.trainable, 'conv58')
input_data = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, 'conv59')
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv60')
input_data = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, 'conv61')
input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv62')
#得到输出26*26*256
conv_mobj_branch = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, name='conv_mobj_branch' )
conv_mbbox = common.convolutional(conv_mobj_branch, (1, 1, 512, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_mbbox', activate=False, bn=False)
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv63')
input_data = common.upsample(input_data, name='upsample1', method=self.upsample_method)
#上采样输出为52*52*128
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_2], axis=-1)
#8倍下采样输出52*52*256，concat以后为52*52*384
input_data = common.convolutional(input_data, (1, 1, 384, 128), self.trainable, 'conv64')
input_data = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, 'conv65')
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv66')
input_data = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, 'conv67')
input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv68')
#得到输出52*52*128
conv_sobj_branch = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, name='conv_sobj_branch')
conv_sbbox = common.convolutional(conv_sobj_branch, (1, 1, 256, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_sbbox', activate=False, bn=False)
input_data = common.convolutional(input_data, (1, 1, 128, 64), self.trainable, 'conv63')
input_data = common.upsample(input_data, name='upsample1', method=self.upsample_method)
#上采样以后得到输出104*104*64
with tf.variable_scope('route_3'):
input_data = tf.concat([input_data, route_1], axis=-1)
#4倍下采样输出104*104*128，concat以后为104*104*128
input_data = common.convolutional(input_data, (1, 1, 192, 64), self.trainable, 'conv64')
input_data = common.convolutional(input_data, (3, 3, 64, 128), self.trainable, 'conv65')
input_data = common.convolutional(input_data, (1, 1, 128, 64), self.trainable, 'conv66')
input_data = common.convolutional(input_data, (3, 3, 64, 128), self.trainable, 'conv67')
input_data = common.convolutional(input_data, (1, 1, 128, 64), self.trainable, 'conv68')
#得到输出104*104*64
conv_sobj_branch_1 = common.convolutional(input_data, (3, 3, 64, 128), self.trainable, name='conv_sobj_branch')
conv_sbbox_1 = common.convolutional(conv_sobj_branch_1, (1, 1, 128, 3*(self.num_class + 5)),
trainable=self.trainable, name='conv_sbbox', activate=False, bn=False)
return conv_lbbox, conv_mbbox, conv_sbbox, conv_sbbox_1
def build_backbone(self):
return backbone.darknet53(self.trainable, self.darknet_gn,
self.precision)
def __build_nework(self, input_data):
# route1 2 3 input data 分别为用于后面concat的值 即 128残差后用于最大特征图concat的 route1 以此类推
route_1, route_2, input_data = backbone.darknet53(
input_data, self.trainable)
# 经过全部残差的 output 先经过五次DBL操作
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv52')
input_data = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable, 'conv53')
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv54')
input_data = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable, 'conv55')
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv56')
conv_lobj_branch = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable,
name='conv_lobj_branch')
conv_lbbox = common.convolutional(
conv_lobj_branch, (1, 1, 1024, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_lbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv57')
input_data = common.upsample(input_data,
name='upsample0',
method=self.upsample_method)
with tf.variable_scope('route_1'):
input_data = tf.concat([input_data, route_2], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 768, 256),
self.trainable, 'conv58')
input_data = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable, 'conv59')
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv60')
input_data = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable, 'conv61')
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv62')
conv_mobj_branch = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable,
name='conv_mobj_branch')
conv_mbbox = common.convolutional(
conv_mobj_branch, (1, 1, 512, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_mbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv63')
input_data = common.upsample(input_data,
name='upsample1',
method=self.upsample_method)
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 384, 128),
self.trainable, 'conv64')
input_data = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable, 'conv65')
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv66')
input_data = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable, 'conv67')
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv68')
conv_sobj_branch = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable,
name='conv_sobj_branch')
conv_sbbox = common.convolutional(
conv_sobj_branch, (1, 1, 256, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_sbbox',
activate=False,
bn=False)
# 返回三种大小的检测框 13*13*255 26*26 52*52
return conv_lbbox, conv_mbbox, conv_sbbox
def __build_nework(self, input_data):
"""经过Darknet-53后，分出三个分支y1,y2,y3"""
route_1, route_2, input_data = backbone.darknet53(
input_data, self.trainable)
#(Conv + BN + leaky_relu)×5
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv52')
input_data = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable, 'conv53')
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv54')
input_data = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable, 'conv55')
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv56')
conv_lobj_branch = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable,
name='conv_lobj_branch')
#y1的输出[None,13,13,3*(80+5)=255],用于检测大物体
conv_lbbox = common.convolutional(
conv_lobj_branch, (1, 1, 1024, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_lbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv57')
input_data = common.upsample(input_data,
name='upsample0',
method=self.upsample_method)
#第一个concat操作
with tf.variable_scope('route_1'):
input_data = tf.concat([input_data, route_2], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 768, 256),
self.trainable, 'conv58')
input_data = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable, 'conv59')
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv60')
input_data = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable, 'conv61')
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv62')
conv_mobj_branch = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable,
name='conv_mobj_branch')
#y2的输出[None,26,26,3*(80+5)=255],用于检测中等物体
conv_mbbox = common.convolutional(
conv_mobj_branch, (1, 1, 512, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_mbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv63')
input_data = common.upsample(input_data,
name='upsample1',
method=self.upsample_method)
# input_data = common.upsample(input_data, name='upsample2', method=self.upsample_method)
# route_1 = common.upsample(route_1, name = 'upsample3',method=self.upsample_method)
#第二个concat操作
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 384, 128),
self.trainable, 'conv64')
input_data = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable, 'conv65')
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv66')
input_data = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable, 'conv67')
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv68')
conv_sobj_branch = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable,
name='conv_sobj_branch')
#y3的输出[None,52,52,3*(80+5)=255],用于检测小物体
conv_sbbox = common.convolutional(
conv_sobj_branch, (1, 1, 256, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_sbbox',
activate=False,
bn=False)
return conv_lbbox, conv_mbbox, conv_sbbox
def __build_nework(self, input_data):
"""
基于输入的数据构建YOLO v3模型
:param input_data:
:return:
"""
# 1. 构建darknet53网络结构，得到输出值(第一个分支、第二个分支以及最后输出数据)
route_1, route_2, input_data = backbone.darknet53(
input_data, self.trainable) # 骨干网络(Encoder网络)
# 2. 对最终输出数据连续5次卷积操作([3,3,1024] -> [1,1,512] -> [3,3,1024] -> [1,1,512]-> [3,3,1024] -> [1,1,512])
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv52')
input_data = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable, 'conv53')
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv54')
input_data = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable, 'conv55')
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv56')
# 3. 最后一个分支对应的预测值输出
conv_lobj_branch = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable,
name='conv_lobj_branch')
conv_lbbox = common.convolutional(conv_lobj_branch,
(1, 1, 1024, self.anchor_per_scale *
(self.num_class + 5)),
trainable=self.trainable,
name='conv_lbbox',
activate=False,
bn=False)
# 4. 将最后一个分支进行卷积转换+上采样
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv57')
input_data = common.upsample(input_data,
name='upsample0',
method=self.upsample_method)
# 5. 将最后一个分支的数据和第二个分支的数据合并
with tf.variable_scope('route_1'):
input_data = tf.concat([input_data, route_2], axis=-1)
# 6. 对第二个分支数据连续5次卷积操作
input_data = common.convolutional(input_data, (1, 1, 768, 256),
self.trainable, 'conv58')
input_data = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable, 'conv59')
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv60')
input_data = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable, 'conv61')
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv62')
# 7. 第二个分支对应的预测值输出
conv_mobj_branch = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable,
name='conv_mobj_branch')
conv_mbbox = common.convolutional(
conv_mobj_branch, (1, 1, 512, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_mbbox',
activate=False,
bn=False)
# 8. 将第二个分支的数据进行卷积转换 + 上采样
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv63')
input_data = common.upsample(input_data,
name='upsample1',
method=self.upsample_method)
# 9. 将第二个分支的数据和第三个分支的数据合并
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)
# 10. 对第三个分支的数据连续5次卷积操作
input_data = common.convolutional(input_data, (1, 1, 384, 128),
self.trainable, 'conv64')
input_data = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable, 'conv65')
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv66')
input_data = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable, 'conv67')
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv68')
# 11. 第三个分支对应的预测值输出
conv_sobj_branch = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable,
name='conv_sobj_branch')
conv_sbbox = common.convolutional(
conv_sobj_branch, (1, 1, 256, 3 * (self.num_class + 5)),
trainable=self.trainable,
name='conv_sbbox',
activate=False,
bn=False)
# 12. 返回三个分支的数据输出，也就是大目标、中等目标、小目标的检测
return conv_lbbox, conv_mbbox, conv_sbbox
def __build_nework(self, input_data):
input_data = backbone.darknet53(input_data, self.trainable)
# input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv52')
# input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, 'conv53')
# input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv54')
# input_data = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, 'conv55')
# input_data = common.convolutional(input_data, (1, 1, 1024, 512), self.trainable, 'conv56')
#
# conv_lobj_branch = common.convolutional(input_data, (3, 3, 512, 1024), self.trainable, name='conv_lobj_branch')
# conv_l = common.convolutional(input_data, (1, 1, 1024, self.num_class),
# trainable=self.trainable, name='conv_l', activate=False, bn=False)
conv_l = tf.layers.flatten(input_data)
conv_l = tf.reshape(conv_l, (-1, 8 * 8 * 128))
conv_l = tf.layers.dense(
conv_l,
units=1024,
activation=tf.nn.leaky_relu,
kernel_regularizer=tf.contrib.layers.l2_regularizer(0.1))
conv_l = tf.layers.dropout(conv_l, rate=0.4)
conv_l = tf.layers.dense(
conv_l,
units=512,
activation=tf.nn.leaky_relu,
kernel_regularizer=tf.contrib.layers.l2_regularizer(0.1))
conv_l = tf.layers.dropout(conv_l, rate=0.4)
conv_l = tf.layers.dense(conv_l,
units=self.num_class,
name='conv_l',
activation=tf.nn.softmax)
# input_data = common.convolutional(input_data, (1, 1, 1024, 256), self.trainable, 'conv57')
# input_data = common.upsample(input_data, name='upsample0', method=self.upsample_method)
#
# with tf.variable_scope('route_1'):
# input_data = tf.concat([input_data, route_2], axis=-1)
# input_data = common.convolutional(input_data, (1, 1, 768, 256), self.trainable, 'conv58')
# input_data = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, 'conv59')
# input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv60')
# input_data = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, 'conv61')
# input_data = common.convolutional(input_data, (1, 1, 512, 256), self.trainable, 'conv62')
#
# conv_mobj_branch = common.convolutional(input_data, (3, 3, 256, 512), self.trainable, name='conv_mobj_branch')
# conv_m = common.convolutional(input_data, (1, 1, 768, self.num_class),
# trainable=self.trainable, name='conv_m', activate=False, bn=False)
# conv_m = tf.layers.flatten(input_data)
# conv_m = tf.reshape(conv_m, (-1, 26 * 26 * 768))
# conv_m = tf.layers.dense(conv_m, units=self.num_class, name='conv_m', activation=tf.nn.relu)
#
# input_data = common.convolutional(input_data, (1, 1, 768, 128), self.trainable, 'conv63')
# input_data = common.upsample(input_data, name='upsample1', method=self.upsample_method)
#
# with tf.variable_scope('route_2'):
# input_data = tf.concat([input_data, route_1], axis=-1)
# input_data = common.convolutional(input_data, (1, 1, 384, 128), self.trainable, 'conv64')
# input_data = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, 'conv65')
# input_data = common.convolutional(input_data, (1, 1, 256, 128), self.trainable, 'conv66')
# input_data = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, 'conv67')
# input_data = common.convolutional(input_data, (1, 1, 384, 128), self.trainable, 'conv68')
#
# conv_sobj_branch = common.convolutional(input_data, (3, 3, 128, 256), self.trainable, name='conv_sobj_branch')
# conv_s = common.convolutional(input_data, (1, 1, 384, self.num_class),
# trainable=self.trainable, name='conv_s', activate=False, bn=False)
# conv_s = tf.layers.flatten(input_data)
# conv_s = tf.reshape(conv_s, (-1, 52 * 52 * 384))
# conv_s = tf.layers.dense(conv_s, units=self.num_class, name='conv_s', activation=tf.nn.relu)
return conv_l
def YOLOv3(input_layer):
if BACK_BONE == 'resnet18':
route_1, route_2, conv = backbone.resnet(input_layer, 18)
if BACK_BONE == 'resnet34':
route_1, route_2, conv = backbone.resnet(input_layer, 34)
if BACK_BONE == 'resnet50':
route_1, route_2, conv = backbone.resnet(input_layer, 50)
if BACK_BONE == 'resnet101':
route_1, route_2, conv = backbone.resnet(input_layer, 101)
if BACK_BONE == 'resnet152':
route_1, route_2, conv = backbone.resnet(input_layer, 152)
if BACK_BONE == 'darknet53':
route_1, route_2, conv = backbone.darknet53(input_layer)
conv = common.convolutional(conv, (1, 1, 1024, 512))
conv = common.convolutional(conv, (3, 3, 512, 1024))
conv = common.convolutional(conv, (1, 1, 1024, 512))
conv = common.convolutional(conv, (3, 3, 512, 1024))
conv = common.convolutional(conv, (1, 1, 1024, 512))
conv_lobj_branch = common.convolutional(conv, (3, 3, 512, 1024))
conv_lbbox = common.convolutional(conv_lobj_branch,
(1, 1, 1024, 3 * (NUM_CLASS + 5)),
activate=False,
bn=False)
conv = common.convolutional(conv, (1, 1, 512, 256))
conv = common.upsample(conv)
conv = tf.concat([conv, route_2], axis=-1)
conv = common.convolutional(conv, (1, 1, 768, 256))
conv = common.convolutional(conv, (3, 3, 256, 512))
conv = common.convolutional(conv, (1, 1, 512, 256))
conv = common.convolutional(conv, (3, 3, 256, 512))
conv = common.convolutional(conv, (1, 1, 512, 256))
conv_mobj_branch = common.convolutional(conv, (3, 3, 256, 512))
conv_mbbox = common.convolutional(conv_mobj_branch,
(1, 1, 512, 3 * (NUM_CLASS + 5)),
activate=False,
bn=False)
conv = common.convolutional(conv, (1, 1, 256, 128))
conv = common.upsample(conv)
conv = tf.concat([conv, route_1], axis=-1)
conv = common.convolutional(conv, (1, 1, 384, 128))
conv = common.convolutional(conv, (3, 3, 128, 256))
conv = common.convolutional(conv, (1, 1, 256, 128))
conv = common.convolutional(conv, (3, 3, 128, 256))
conv = common.convolutional(conv, (1, 1, 256, 128))
conv_sobj_branch = common.convolutional(conv, (3, 3, 128, 256))
conv_sbbox = common.convolutional(conv_sobj_branch,
(1, 1, 256, 3 * (NUM_CLASS + 5)),
activate=False,
bn=False)
return [conv_sbbox, conv_mbbox, conv_lbbox]
def __build_network(self, input_data):
route_1, route_2, input_data = backbone.darknet53(
input_data, self.trainable)
# DBL * 5
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv52')
input_data = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable, 'conv53')
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv54')
input_data = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable, 'conv55')
input_data = common.convolutional(input_data, (1, 1, 1024, 512),
self.trainable, 'conv56')
# Large, Route 3 in .images/yolo-arch1.png
conv_lobj_branch = common.convolutional(input_data, (3, 3, 512, 1024),
self.trainable,
name='conv_lobj_branch')
conv_lbbox = common.convolutional(
conv_lobj_branch, (1, 1, 1024, 3 * (self.num_classes + 5)),
trainable=self.trainable,
name='conv_lbbox',
activate=False,
bn=False)
# the last dimension of conv_lbbox is 3*(20+5), i.e anchor_per_scale * (num_classes + 5)
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv57')
input_data = common.upsample(input_data,
name='upsample0',
method=self.upsample_method) #resize
with tf.variable_scope('route_1'):
input_data = tf.concat([input_data, route_2], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 768, 256),
self.trainable, 'conv58')
input_data = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable, 'conv59')
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv60')
input_data = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable, 'conv61')
input_data = common.convolutional(input_data, (1, 1, 512, 256),
self.trainable, 'conv62')
conv_mobj_branch = common.convolutional(input_data, (3, 3, 256, 512),
self.trainable,
name='conv_mobj_branch')
conv_mbbox = common.convolutional(
conv_mobj_branch, (1, 1, 512, 3 * (self.num_classes + 5)),
trainable=self.trainable,
name='conv_mbbox',
activate=False,
bn=False)
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv63')
input_data = common.upsample(input_data,
name='upsample1',
method=self.upsample_method)
with tf.variable_scope('route_2'):
input_data = tf.concat([input_data, route_1], axis=-1)
input_data = common.convolutional(input_data, (1, 1, 384, 128),
self.trainable, 'conv64')
input_data = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable, 'conv65')
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv66')
input_data = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable, 'conv67')
input_data = common.convolutional(input_data, (1, 1, 256, 128),
self.trainable, 'conv68')
conv_sobj_branch = common.convolutional(input_data, (3, 3, 128, 256),
self.trainable,
name='conv_sobj_branch')
conv_sbbox = common.convolutional(
conv_sobj_branch, (1, 1, 256, 3 * (self.num_classes + 5)),
trainable=self.trainable,
name='conv_sbbox',
activate=False,
bn=False)
return conv_lbbox, conv_mbbox, conv_sbbox
