def __init__(self,
n_filter=128,
n_confmaps=19,
n_pafmaps=38,
data_format="channels_first"):
super().__init__()
self.data_format = data_format
self.main_block = layers.LayerList([
Conv2d(n_filter=n_filter,
in_channels=n_filter,
act=tf.nn.relu,
data_format=self.data_format),
Conv2d(n_filter=n_filter,
in_channels=n_filter,
act=tf.nn.relu,
data_format=self.data_format),
Conv2d(n_filter=n_filter,
in_channels=n_filter,
act=tf.nn.relu,
data_format=self.data_format)
])
self.conf_block=layers.LayerList([
Conv2d(n_filter=512,in_channels=n_filter,filter_size=(1,1),strides=(1,1),act=tf.nn.relu,W_init=initializer,\
b_init=initializer,data_format=self.data_format),
Conv2d(n_filter=n_confmaps,in_channels=512,filter_size=(1,1),strides=(1,1),W_init=initializer,\
b_init=initializer,data_format=self.data_format)
])
self.paf_block=layers.LayerList([
Conv2d(n_filter=512,in_channels=n_filter,filter_size=(1,1),strides=(1,1),act=tf.nn.relu,W_init=initializer,\
b_init=initializer,data_format=self.data_format),
Conv2d(n_filter=n_pafmaps,in_channels=512,filter_size=(1,1),strides=(1,1),W_init=initializer,\
b_init=initializer,data_format=self.data_format)
])
def __init__(self,
n_filter=128,
in_channels=185,
n_confmaps=19,
n_pafmaps=38,
data_format="channels_first"):
super().__init__()
self.data_format = data_format
self.block_1 = self.Refinement_block(n_filter=n_filter,
in_channels=in_channels,
data_format=self.data_format)
self.block_2 = self.Refinement_block(n_filter=n_filter,
in_channels=n_filter,
data_format=self.data_format)
self.block_3 = self.Refinement_block(n_filter=n_filter,
in_channels=n_filter,
data_format=self.data_format)
self.block_4 = self.Refinement_block(n_filter=n_filter,
in_channels=n_filter,
data_format=self.data_format)
self.block_5 = self.Refinement_block(n_filter=n_filter,
in_channels=n_filter,
data_format=self.data_format)
self.conf_block=layers.LayerList([
Conv2d(n_filter=512,in_channels=n_filter,filter_size=(1,1),strides=(1,1),act=tf.nn.relu,W_init=initializer,b_init=initializer,\
data_format=self.data_format),
Conv2d(n_filter=n_confmaps,in_channels=512,filter_size=(1,1),strides=(1,1),W_init=initializer,b_init=initializer,\
data_format=self.data_format)
])
self.paf_block=layers.LayerList([
Conv2d(n_filter=512,in_channels=n_filter,filter_size=(1,1),strides=(1,1),act=tf.nn.relu,W_init=initializer,b_init=initializer,\
data_format=self.data_format),
Conv2d(n_filter=n_pafmaps,in_channels=512,filter_size=(1,1),strides=(1,1),W_init=initializer,b_init=initializer,\
data_format=self.data_format)
])
def nobn_dw_conv_block(n_filter,
in_channels,
filter_size=(3, 3),
strides=(1, 1),
W_init=initializer,
b_init=initializer,
data_format="channels_first"):
layer_list = []
layer_list.append(
DepthwiseConv2d(filter_size=filter_size,
strides=strides,
in_channels=in_channels,
act=tf.nn.relu,
W_init=initializer,
b_init=None,
data_format=data_format))
layer_list.append(
Conv2d(n_filter=n_filter,
filter_size=(1, 1),
strides=(1, 1),
in_channels=in_channels,
act=tf.nn.relu,
W_init=initializer,
b_init=None,
data_format=data_format))
return layers.LayerList(layer_list)
def __init__(self,in_channels=3,data_format="channels_first",pretrained=True):
super().__init__()
self.data_format=data_format
self.pretrained=pretrained
self.transpose=False
self.out_channels=512
if(self.data_format=="channel_last"):
self.main_block=tl.models.vgg19(pretrained=self.pretrained,end_with="conv4_2")
else:
if(self.pretrained):
print("only channels_last pretrained vgg19 available, adding transpose")
self.main_block=tl.models.vgg19(pretrained=self.pretrained,end_with="conv4_2")
self.transpose=True
else:
self.main_block=layers.LayerList([
self.conv_block(n_filter=64,in_channels=3,filter_size=(3,3),strides=(1,1),act=tf.nn.relu),
self.conv_block(n_filter=64,in_channels=64,filter_size=(3,3),strides=(1,1),act=tf.nn.relu),
MaxPool2d(filter_size=(2,2),strides=(2,2),data_format=self.data_format),
self.conv_block(n_filter=128,in_channels=64,filter_size=(3,3),strides=(1,1),act=tf.nn.relu),
self.conv_block(n_filter=128,in_channels=128,filter_size=(3,3),strides=(1,1),act=tf.nn.relu),
MaxPool2d(filter_size=(2,2),strides=(2,2),data_format=self.data_format),
self.conv_block(n_filter=256,in_channels=128,filter_size=(3,3),strides=(1,1),act=tf.nn.relu),
self.conv_block(n_filter=256,in_channels=256,filter_size=(3,3),strides=(1,1),act=tf.nn.relu),
self.conv_block(n_filter=256,in_channels=256,filter_size=(3,3),strides=(1,1),act=tf.nn.relu),
self.conv_block(n_filter=256,in_channels=256,filter_size=(3,3),strides=(1,1),act=tf.nn.relu),
MaxPool2d(filter_size=(2,2),strides=(2,2),data_format=self.data_format),
self.conv_block(n_filter=512,in_channels=256,filter_size=(3,3),strides=(1,1),act=tf.nn.relu),
self.conv_block(n_filter=512,in_channels=512,filter_size=(3,3),strides=(1,1),act=tf.nn.relu)
])
def __init__(self,
n_filter=128,
in_channels=512,
data_format="channels_first"):
super().__init__()
self.data_format = data_format
self.init_layer = Conv2d(n_filter=n_filter,
in_channels=in_channels,
filter_size=(1, 1),
act=tf.nn.relu,
data_format=self.data_format)
self.main_block = layers.LayerList([
conv_block(n_filter=n_filter,
in_channels=n_filter,
data_format=self.data_format),
conv_block(n_filter=n_filter,
in_channels=n_filter,
data_format=self.data_format),
conv_block(n_filter=n_filter,
in_channels=n_filter,
data_format=self.data_format),
])
self.end_layer = Conv2d(n_filter=n_filter,
in_channels=n_filter,
filter_size=(3, 3),
act=tf.nn.relu,
data_format=self.data_format)
def separable_block(n_filter=32,in_channels=3,filter_size=(3,3),strides=(1,1),dilation_rate=(1,1),act=tf.nn.relu,data_format="channels_first"):
layer_list=[]
layer_list.append(DepthwiseConv2d(filter_size=filter_size,strides=strides,in_channels=in_channels,
dilation_rate=dilation_rate,W_init=initial_w,b_init=None,data_format=data_format))
layer_list.append(BatchNorm2d(decay=0.99,act=act,num_features=in_channels,data_format=data_format,is_train=True))
layer_list.append(Conv2d(n_filter=n_filter,filter_size=(1,1),strides=(1,1),in_channels=in_channels,W_init=initial_w,b_init=None,data_format=data_format))
layer_list.append(BatchNorm2d(decay=0.99,act=act,num_features=n_filter,data_format=data_format,is_train=True))
return layers.LayerList(layer_list)
def __init__(self,n_filter,in_channels,data_format="channels_first"):
super().__init__()
self.data_format=data_format
self.init_layer=Conv2d(n_filter=n_filter,filter_size=(1,1),in_channels=in_channels,act=tf.nn.relu,data_format=self.data_format)
self.main_block=layers.LayerList([
conv_block(n_filter=n_filter,in_channels=n_filter,data_format=self.data_format),
conv_block(n_filter=n_filter,in_channels=n_filter,dilation_rate=(1,1),data_format=self.data_format)
])
def __init__(self,n_confmaps=19,n_pafmaps=38,in_channels=128,data_format="channels_first"):
super().__init__()
self.n_confmaps=n_confmaps
self.n_pafmaps=n_pafmaps
self.in_channels=in_channels
self.data_format=data_format
self.conf_block=layers.LayerList([
Conv2d(n_filter=128,in_channels=self.in_channels,filter_size=(3,3),strides=(1,1),padding="SAME",act=tf.nn.relu,W_init=initial_w,b_init=initial_b,data_format=self.data_format),
Conv2d(n_filter=128,in_channels=128,filter_size=(3,3),strides=(1,1),padding="SAME",act=tf.nn.relu,W_init=initial_w,b_init=initial_b,data_format=self.data_format),
Conv2d(n_filter=128,in_channels=128,filter_size=(3,3),strides=(1,1),padding="SAME",act=tf.nn.relu,W_init=initial_w,b_init=initial_b,data_format=self.data_format),
Conv2d(n_filter=512,in_channels=128,filter_size=(1,1),strides=(1,1),padding="SAME",act=tf.nn.relu,W_init=initial_w,b_init=initial_b,data_format=self.data_format),
Conv2d(n_filter=self.n_confmaps,in_channels=512,filter_size=(1,1),strides=(1,1),padding="SAME",act=tf.nn.relu,W_init=initial_w,b_init=initial_b,data_format=self.data_format)
])
self.paf_block=layers.LayerList([
Conv2d(n_filter=128,in_channels=self.in_channels,filter_size=(3,3),strides=(1,1),padding="SAME",act=tf.nn.relu,W_init=initial_w,b_init=initial_b,data_format=self.data_format),
Conv2d(n_filter=128,in_channels=128,filter_size=(3,3),strides=(1,1),padding="SAME",act=tf.nn.relu,W_init=initial_w,b_init=initial_b,data_format=self.data_format),
Conv2d(n_filter=128,in_channels=128,filter_size=(3,3),strides=(1,1),padding="SAME",act=tf.nn.relu,W_init=initial_w,b_init=initial_b,data_format=self.data_format),
Conv2d(n_filter=512,in_channels=128,filter_size=(1,1),strides=(1,1),padding="SAME",act=tf.nn.relu,W_init=initial_w,b_init=initial_b,data_format=self.data_format),
Conv2d(n_filter=self.n_pafmaps,in_channels=512,filter_size=(1,1),strides=(1,1),padding="SAME",act=tf.nn.relu,W_init=initial_w,b_init=initial_b,data_format=self.data_format)
])
def __init__(self, data_format="channels_first"):
super().__init__()
self.data_format = data_format
self.out_channels = 512
self.main_block = layers.LayerList([
conv_block(n_filter=32,
in_channels=3,
data_format=self.data_format,
strides=(2, 2)),
dw_conv_block(n_filter=64,
in_channels=32,
data_format=self.data_format),
dw_conv_block(n_filter=128,
in_channels=64,
data_format=self.data_format,
strides=(2, 2)),
dw_conv_block(n_filter=128,
in_channels=128,
data_format=self.data_format),
dw_conv_block(n_filter=256,
in_channels=128,
data_format=self.data_format,
strides=(2, 2)),
dw_conv_block(n_filter=256,
in_channels=256,
data_format=self.data_format),
dw_conv_block(n_filter=512,
in_channels=256,
data_format=self.data_format),
dw_conv_block(n_filter=512,
in_channels=512,
data_format=self.data_format,
dilation_rate=(2, 2)),
dw_conv_block(n_filter=512,
in_channels=512,
data_format=self.data_format),
dw_conv_block(n_filter=512,
in_channels=512,
data_format=self.data_format),
dw_conv_block(n_filter=512,
in_channels=512,
data_format=self.data_format),
dw_conv_block(n_filter=512,
in_channels=512,
data_format=self.data_format)
])
def conv_block(n_filter,
in_channels,
filter_size=(3, 3),
strides=(1, 1),
dilation_rate=(1, 1),
W_init=initializer,
b_init=initializer,
padding="SAME",
data_format="channels_first"):
layer_list = []
layer_list.append(Conv2d(n_filter=n_filter,filter_size=filter_size,strides=strides,in_channels=in_channels,\
dilation_rate=dilation_rate,padding=padding,W_init=initializer,b_init=initializer,data_format=data_format))
layer_list.append(
BatchNorm2d(decay=0.99,
act=tf.nn.relu,
num_features=n_filter,
data_format=data_format,
is_train=True))
return layers.LayerList(layer_list)
def __init__(self,
in_channels=3,
scale_size=8,
data_format="channels_first"):
super().__init__()
self.in_channels = in_channels
self.data_format = data_format
self.scale_size = scale_size
if (self.scale_size == 8):
strides = (1, 1)
else:
strides = (2, 2)
self.out_channels = 384
self.main_block = layers.LayerList([
self.conv_block(n_filter=32,
in_channels=3,
filter_size=(3, 3),
strides=(1, 1)),
self.conv_block(n_filter=64,
in_channels=32,
filter_size=(3, 3),
strides=(1, 1)),
MaxPool2d(filter_size=(2, 2),
strides=(2, 2),
padding="SAME",
data_format=self.data_format),
self.conv_block(n_filter=128,
in_channels=64,
filter_size=(3, 3),
strides=(1, 1)),
self.conv_block(n_filter=128,
in_channels=128,
filter_size=(3, 3),
strides=(1, 1)),
MaxPool2d(filter_size=(2, 2),
strides=(2, 2),
padding="SAME",
data_format=self.data_format),
self.conv_block(n_filter=200,
in_channels=128,
filter_size=(3, 3),
strides=(1, 1)),
self.conv_block(n_filter=200,
in_channels=200,
filter_size=(3, 3),
strides=strides),
self.conv_block(n_filter=200,
in_channels=200,
filter_size=(3, 3),
strides=(1, 1)),
MaxPool2d(filter_size=(2, 2),
strides=(2, 2),
padding="SAME",
data_format=self.data_format),
self.conv_block(n_filter=384,
in_channels=200,
filter_size=(3, 3),
strides=(1, 1)),
self.conv_block(n_filter=384,
in_channels=384,
filter_size=(3, 3),
strides=strides)
])
