def __init__(self, name_scope, num_classes=7, is_train=True):
super(YOLOv3, self).__init__(name_scope)
self.is_train = is_train
self.num_classes = num_classes
# 提取图像特征的骨干代码
self.block = DarkNet53_conv_body(self.full_name(),
is_test=not self.is_train)
self.block_outputs = []
self.yolo_blocks = []
self.route_blocks_2 = []
for i in range(3):
# 添加从ci生成ri和ti的模块
yolo_block = self.add_sublayer(
"yolo_detecton_block_%d" % (i),
YoloDetectionBlock(self.full_name(),
channel=512 // (2**i),
is_test=not self.is_train))
self.yolo_blocks.append(yolo_block)
num_filters = 3 * (self.num_classes + 5)
# 添加从ti生成pi的模块，这是一个Conv2D操作，输出通道数为3 * (num_classes + 5)
block_out = self.add_sublayer(
"block_out_%d" % (i),
Conv2D(self.full_name(),
num_filters=num_filters,
filter_size=1,
stride=1,
padding=0,
act=None,
param_attr=ParamAttr(
initializer=fluid.initializer.Normal(0., 0.02)),
bias_attr=ParamAttr(
initializer=fluid.initializer.Constant(0.0),
regularizer=L2Decay(0.))))
self.block_outputs.append(block_out)
if i < 2:
# 对ri进行卷积
route = self.add_sublayer(
"route2_%d" % i,
ConvBNLayer(self.full_name(),
ch_out=256 // (2**i),
filter_size=1,
stride=1,
padding=0,
is_test=(not self.is_train)))
self.route_blocks_2.append(route)
# 将ri放大以便跟c_{i+1}保持同样的尺寸
self.upsample = Upsample(self.full_name())
def __init__(self, ch_in, is_train=True, use_random=False):
super(YOLOv3, self).__init__()
self.is_train = is_train
self.use_random = use_random
self.block = DarkNet53_conv_body(ch_in=ch_in, is_test=not self.is_train)
self.block_outputs = []
self.yolo_blocks = []
self.route_blocks_2 = []
ch_in_list = [1024, 768, 384]
for i in range(3):
yolo_block = self.add_sublayer(
"yolo_detecton_block_%d" % (i),
YoloDetectionBlock(
ch_in_list[i],
channel=512 // (2**i),
is_test=not self.is_train))
self.yolo_blocks.append(yolo_block)
num_filters = len(cfg.anchor_masks[i]) * (cfg.class_num + 5)
block_out = self.add_sublayer(
"block_out_%d" % (i),
Conv2D(
num_channels=1024 // (2**i),
num_filters=num_filters,
filter_size=1,
stride=1,
padding=0,
act=None,
param_attr=ParamAttr(
initializer=fluid.initializer.Normal(0., 0.02)),
bias_attr=ParamAttr(
initializer=fluid.initializer.Constant(0.0),
regularizer=L2Decay(0.))))
self.block_outputs.append(block_out)
if i < 2:
route = self.add_sublayer(
"route2_%d" % i,
ConvBNLayer(
ch_in=512 // (2**i),
ch_out=256 // (2**i),
filter_size=1,
stride=1,
padding=0,
is_test=(not self.is_train)))
self.route_blocks_2.append(route)
self.upsample = Upsample()
def __init__(self, ch_in, channel, is_test=True):
super(YoloDetectionBlock, self).__init__()
assert channel % 2 == 0, \
"channel {} cannot be divided by 2".format(channel)
self.conv0 = ConvBNLayer(
ch_in=ch_in,
ch_out=channel,
filter_size=1,
stride=1,
padding=0,
is_test=is_test)
self.conv1 = ConvBNLayer(
ch_in=channel,
ch_out=channel * 2,
filter_size=3,
stride=1,
padding=1,
is_test=is_test)
self.conv2 = ConvBNLayer(
ch_in=channel * 2,
ch_out=channel,
filter_size=1,
stride=1,
padding=0,
is_test=is_test)
self.conv3 = ConvBNLayer(
ch_in=channel,
ch_out=channel * 2,
filter_size=3,
stride=1,
padding=1,
is_test=is_test)
self.route = ConvBNLayer(
ch_in=channel * 2,
ch_out=channel,
filter_size=1,
stride=1,
padding=0,
is_test=is_test)
self.tip = ConvBNLayer(
ch_in=channel,
ch_out=channel * 2,
filter_size=3,
stride=1,
padding=1,
is_test=is_test)