def __init__(self,
name_scope,
group,
out_ch,
channels,
act="relu",
is_test=False,
pool=True,
use_cudnn=True):
super(ConvBNPool, self).__init__(name_scope)
self.group = group
self.pool = pool
filter_size = 3
conv_std_0 = (2.0 / (filter_size**2 * channels[0]))**0.5
conv_param_0 = fluid.ParamAttr(
initializer=fluid.initializer.Normal(0.0, conv_std_0))
conv_std_1 = (2.0 / (filter_size**2 * channels[1]))**0.5
conv_param_1 = fluid.ParamAttr(
initializer=fluid.initializer.Normal(0.0, conv_std_1))
self.conv_0_layer = Conv2D(
self.full_name(),
channels[0],
out_ch[0],
3,
padding=1,
param_attr=conv_param_0,
bias_attr=False,
act=None,
use_cudnn=use_cudnn)
self.bn_0_layer = BatchNorm(
self.full_name(), out_ch[0], act=act, is_test=is_test)
self.conv_1_layer = Conv2D(
self.full_name(),
num_channels=channels[1],
num_filters=out_ch[1],
filter_size=3,
padding=1,
param_attr=conv_param_1,
bias_attr=False,
act=None,
use_cudnn=use_cudnn)
self.bn_1_layer = BatchNorm(
self.full_name(), out_ch[1], act=act, is_test=is_test)
print( "pool", self.pool)
if self.pool:
self.pool_layer = Pool2D(
self.full_name(),
pool_size=2,
pool_type='max',
pool_stride=2,
use_cudnn=use_cudnn,
ceil_mode=True)
def __init__(self, name_scope, num_filter):
super(conv_block_4, self).__init__(name_scope)
self.conv1 = Conv2D(
self.full_name(),
num_filters=num_filter,
filter_size=3,
stride=1,
padding=1,
act='relu',
use_cudnn=use_cudnn,
param_attr=fluid.param_attr.ParamAttr(name="1_weights"),
bias_attr=False)
self.conv2 = Conv2D(
self.full_name(),
num_filters=num_filter,
filter_size=3,
stride=1,
padding=1,
act='relu',
use_cudnn=use_cudnn,
param_attr=fluid.param_attr.ParamAttr(name="2_weights"),
bias_attr=False)
self.conv3 = Conv2D(
self.full_name(),
num_filters=num_filter,
filter_size=3,
stride=1,
padding=1,
act='relu',
use_cudnn=use_cudnn,
param_attr=fluid.param_attr.ParamAttr(name="3_weights"),
bias_attr=False)
self.conv4 = Conv2D(
self.full_name(),
num_filters=num_filter,
filter_size=3,
stride=1,
padding=1,
act='relu',
use_cudnn=use_cudnn,
param_attr=fluid.param_attr.ParamAttr(name="4_weights"),
bias_attr=False)
self.pool1 = Pool2D(self.full_name(),
pool_size=2,
pool_type='max',
pool_stride=2,
use_cudnn=use_cudnn)
self.num_filter = num_filter
def __init__(self, num_classes=10, classifier_activation='softmax'):
super(LeNet, self).__init__()
self.num_classes = num_classes
self.features = Sequential(Conv2D(1, 6, 3, stride=1, padding=1),
Pool2D(2, 'max', 2),
Conv2D(6, 16, 5, stride=1, padding=0),
Pool2D(2, 'max', 2))
if num_classes > 0:
self.fc = Sequential(Linear(400, 120), Linear(120, 84),
Linear(84, 10, act=classifier_activation))
def __init__(self, in_size, reduction=4):
super(SeModule, self).__init__()
# self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.se = fluid.dygraph.Sequential(
Conv2D(in_size, in_size // reduction, filter_size=1, stride=1, padding=0),
BatchNorm(in_size // reduction,act='relu'),
Conv2D(in_size // reduction, in_size, filter_size=1, stride=1, padding=0),
BatchNorm(in_size),
hsigmoid()
)
def __init__(self, num_classes=10):
super(AlexNet, self).__init__()
# AlexNet与LeNet一样也会同时使用卷积和池化层提取图像特征
# 与LeNet不同的是激活函数换成了‘relu’
# 这里将conv1中的输入通道数设置成1，输入为（样本数m，1，28，28）
self.conv1 = Conv2D(num_channels=1,
num_filters=10,
filter_size=11,
stride=1,
padding=3,
act='relu')
# 输出为（m,10，24，24）
self.pool1 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
# 输出为（m,10,12,12）
self.conv2 = Conv2D(num_channels=10,
num_filters=100,
filter_size=5,
stride=1,
padding=2,
act='relu')
# （m,100,12,12）
self.pool2 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
# (m,100,6,6)
self.conv3 = Conv2D(num_channels=100,
num_filters=200,
filter_size=3,
stride=1,
padding=0,
act='relu')
# (m,200,4,4)
self.conv4 = Conv2D(num_channels=200,
num_filters=200,
filter_size=3,
stride=1,
padding=1,
act='relu')
# (m,200,4,4)
self.conv5 = Conv2D(num_channels=200,
num_filters=100,
filter_size=3,
stride=1,
padding=1,
act='relu')
# (m,100,4,4)
self.pool5 = Pool2D(pool_size=2, pool_stride=2,
pool_type='max') # 相当于无效
# (m,100,2,2)
self.fc1 = Linear(input_dim=400, output_dim=64, act='relu')
self.drop_ratio1 = 0.5
self.fc2 = Linear(input_dim=64, output_dim=64, act='relu')
self.drop_ratio2 = 0.5
self.fc3 = Linear(input_dim=64, output_dim=num_classes)
def __init__(self, num_classes=10):
super(GoogLeNet, self).__init__()
# GoogLeNet包含五个模块，每个模块后面紧跟一个池化层
# 第一个模块包含1个卷积层以及3x3最大池化
self.conv1 = Conv2D(num_channels=3,
num_filters=64,
filter_size=7,
padding=3,
act='relu')
self.pool1 = Pool2D(pool_size=3,
pool_stride=2,
pool_padding=1,
pool_type='max')
# 第二个模块包含2个卷积层以及3x3最大池化
self.conv2_1 = Conv2D(num_channels=64,
num_filters=64,
filter_size=1,
act='relu')
self.conv2_2 = Conv2D(num_channels=64,
num_filters=192,
filter_size=3,
padding=1,
act='relu')
self.pool2 = Pool2D(pool_size=3,
pool_stride=2,
pool_padding=1,
pool_type='max')
# 第三个模块包含2个Inception块以及3x3最大池化
self.block3_1 = Inception(192, 64, (96, 128), (16, 32), 32)
self.block3_2 = Inception(256, 128, (128, 192), (32, 96), 64)
self.pool3 = Pool2D(pool_size=3,
pool_stride=2,
pool_padding=1,
pool_type='max')
# 第四个模块包含5个Inception块以及3x3最大池化
self.block4_1 = Inception(480, 192, (96, 208), (16, 48), 64)
self.block4_2 = Inception(512, 160, (112, 224), (24, 64), 64)
self.block4_3 = Inception(512, 128, (128, 256), (24, 64), 64)
self.block4_4 = Inception(512, 112, (144, 288), (32, 64), 64)
self.block4_5 = Inception(528, 256, (160, 320), (32, 128), 128)
self.pool4 = Pool2D(pool_size=3,
pool_stride=2,
pool_padding=1,
pool_type='max')
# 第五个模块包含2个Inception块
self.block5_1 = Inception(832, 256, (160, 320), (32, 128), 128)
self.block5_2 = Inception(832, 384, (192, 384), (48, 128), 128)
# 全局平均池化，尺寸用的是global_pooling，pool_stride不起作用
self.pool5 = Pool2D(pool_stride=1,
global_pooling=True,
pool_type='avg')
self.fc = Linear(input_dim=1024, output_dim=num_classes, act='softmax')
def __init__(self):
super(MNIST, self).__init__()
# 定义一个卷积层，使用relu激活函数
self.conv1 = Conv2D(num_channels=1, num_filters=20, filter_size=5, stride=1, padding=2, act='relu')
# 定义一个池化层，池化核为2，步长为2，使用最大池化方式
self.pool1 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
# 定义一个卷积层，使用relu激活函数
self.conv2 = Conv2D(num_channels=20, num_filters=20, filter_size=5, stride=1, padding=2, act='relu')
# 定义一个池化层，池化核为2，步长为2，使用最大池化方式
self.pool2 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
# 定义一个全连接层，输出节点数为10
self.fc = Linear(input_dim=980, output_dim=10, act='softmax')
def __init__(self, num_class=10):
super(LeNet, self).__init__()
# 创建卷积和池化层块，每个卷积层sigmoid激活函数，后面加一个2x2的池化
self.conv1 = Conv2D(num_channels=1, num_filters=6, filter_size=5, act='sigmoid')
self.pool1 = Pool2D(pool_size=2, pool_type='max', pool_stride=2, pool_padding=0)
self.conv2 = Conv2D(num_channels=6, num_filters=16, filter_size=5, act='sigmoid')
self.pool2 = Pool2D(pool_size=2, pool_type='max', pool_stride=2, pool_padding=0)
# 创建第3个卷积层，此卷积层不含有池化层
self.conv3 = Conv2D(num_channels=16, num_filters=120, filter_size=5, act='sigmoid')
# 创建全连接层，卷积层的输出数据格式是[N,C,H,W]，在输入全连接层的时候，会自动将数据拉平
# 也就是对每个样本，自动将其转化为长度为K的向量，K=C×H×W ，一个mini-batch的数据维度变成了N×K的二维向量
self.fc1 = Linear(input_dim=120, output_dim=64, act='sigmoid')
self.fc2 = Linear(input_dim=64, output_dim=num_classes, act='softmax')
def __init__(self,
num_channels,
num_filters,
filter_size,
stride=1,
padding=0,
norm_layer='instance',
use_bias=True,
scale_factor=1,
stddev=0.02):
super(SeparableConv2D, self).__init__()
if use_bias == False:
con_bias_attr = False
else:
con_bias_attr = fluid.ParamAttr(
initializer=fluid.initializer.Constant(0.0))
self.conv_sep = Conv2D(
num_channels=num_channels,
num_filters=num_channels * scale_factor,
filter_size=filter_size,
stride=stride,
padding=padding,
use_cudnn=use_cudnn,
groups=num_channels,
param_attr=fluid.ParamAttr(
initializer=fluid.initializer.NormalInitializer(loc=0.0,
scale=stddev)),
bias_attr=con_bias_attr)
self.norm = InstanceNorm(
num_channels=num_filters,
param_attr=fluid.ParamAttr(
initializer=fluid.initializer.Constant(1.0)),
bias_attr=fluid.ParamAttr(
initializer=fluid.initializer.Constant(0.0)),
)
self.conv_out = Conv2D(
num_channels=num_channels * scale_factor,
num_filters=num_filters,
filter_size=1,
stride=1,
use_cudnn=use_cudnn,
param_attr=fluid.ParamAttr(
initializer=fluid.initializer.NormalInitializer(loc=0.0,
scale=stddev)),
bias_attr=con_bias_attr)
def __init__ (self, input_channel, output_nc, config, norm_layer=InstanceNorm, dropout_rate=0, n_blocks=9, padding_type='reflect'):
super(SubMobileResnetGenerator, self).__init__()
if type(norm_layer) == functools.partial:
use_bias = norm_layer.func == InstanceNorm
else:
use_bias = norm_layer == InstanceNorm
self.model = fluid.dygraph.LayerList([Pad2D(paddings=[3, 3, 3, 3], mode="reflect"),
Conv2D(input_channel, config['channels'][0], filter_size=7, padding=0, use_cudnn=use_cudnn, bias_attr=use_bias),
norm_layer(config['channels'][0]),
ReLU()])
n_downsampling = 2
for i in range(n_downsampling):
mult = 2 ** i
in_c = config['channels'][i]
out_c = config['channels'][i + 1]
self.model.extend([Conv2D(in_c * mult, out_c * mult * 2, filter_size=3, stride=2, padding=1, use_cudnn=use_cudnn, bias_attr=use_bias),
norm_layer(out_c * mult * 2),
ReLU()])
mult = 2 ** n_downsampling
in_c = config['channels'][2]
for i in range(n_blocks):
if len(config['channels']) == 6:
offset = 0
else:
offset = i // 3
out_c = config['channels'][offset + 3]
self.model.extend([MobileResnetBlock(in_c * mult, out_c * mult, padding_type=padding_type, norm_layer=norm_layer, dropout_rate=dropout_rate, use_bias=use_bias)])
if len(config['channels']) == 6:
offset = 4
else:
offset = 6
for i in range(n_downsampling):
out_c = config['channels'][offset + i]
mult = 2 ** (n_downsampling - i)
output_size = (i + 1) * 128
self.model.extend([Conv2DTranspose(in_c * mult, int(out_c * mult / 2), filter_size=3, output_size=output_size, stride=2, padding=1, use_cudnn=use_cudnn, bias_attr=use_bias),
# self.model.extend([Conv2DTranspose(in_c * mult, int(out_c * mult / 2), filter_size=3, stride=2, padding=1, use_cudnn=use_cudnn, bias_attr=use_bias),
# Pad2D(paddings=[0, 1, 0, 1], mode='constant', pad_value=0.0),
norm_layer(int(out_c * mult / 2)),
ReLU()])
in_c = out_c
self.model.extend([Pad2D(paddings=[3, 3, 3, 3], mode="reflect")])
self.model.extend([Conv2D(in_c, output_nc, filter_size=7, padding=0)])
def __init__(self,name_scope):
super(MNIST,self).__init__(name_scope)
name_scope = self.full_name()
# 定义卷积层，输出特征通道num_filters设置为20，卷积核的大小filter_size为5，卷积步长stride=1，padding=2
# 激活函数使用relu
self.conv1 = Conv2D(num_channels=1,num_filters=20, filter_size=5, stride=1, padding=2, act='relu')
# 定义池化层，池化核pool_size=2，池化步长为2，选择最大池化方式
self.pool1 = Pool2D( pool_size=2, pool_stride=2, pool_type='max')
# 定义卷积层，输出特征通道num_filters设置为20，卷积核的大小filter_size为5，卷积步长stride=1，padding=2
self.conv2 = Conv2D(num_channels=20, num_filters=20, filter_size=5, stride=1, padding=2, act='relu')
# 定义池化层，池化核pool_size=2，池化步长为2，选择最大池化方式
self.pool2 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
# self.linear = Linear(20*7*7, 1, act=None)
self.linear = Linear(20*7*7, 10, act='softmax')
def __init__(self):
super(M_net, self).__init__()
self.scale1 = Pool2D(pool_size=2, pool_type='avg', pool_stride=2, pool_padding=0)
self.scale2 = Pool2D(pool_size=2, pool_type='avg', pool_stride=2, pool_padding=0)
self.scale3 = Pool2D(pool_size=2, pool_type='avg', pool_stride=2, pool_padding=0)
self.block1_conv1 = Conv_Block(3, 32, 3, 1)
self.block1_conv2 = Conv_Block(32, 32, 3, 1)
self.block1_pool1 = Pool2D(pool_size=2, pool_type='max', pool_stride=2, pool_padding=0)
self.block2_input1 = Conv_Block(3, 64, 3, 1)
self.block2_conv1 = Conv_Block(96, 64, 3, 1)
self.block2_conv2 = Conv_Block(64, 64, 3, 1)
self.block2_pool1 = Pool2D(pool_size=2, pool_type='max', pool_stride=2, pool_padding=0)
self.block3_input1 = Conv_Block(3, 128, 3, 1)
self.block3_conv1 = Conv_Block(192, 128, 3, 1)
self.block3_conv2 = Conv_Block(128, 128, 3, 1)
self.block3_pool1 = Pool2D(pool_size=2, pool_type='max', pool_stride=2, pool_padding=0)
self.block4_input1 = Conv_Block(3, 256, 3, 1)
self.block4_conv1 = Conv_Block(384, 256, 3, 1)
self.block4_conv2 = Conv_Block(256, 256, 3, 1)
self.block4_pool1 = Pool2D(pool_size=2, pool_type='max', pool_stride=2, pool_padding=0)
self.block5_conv1 = Conv_Block(256, 512, 3, 1)
self.block5_conv2 = Conv_Block(512, 512, 3, 1)
self.block6_dconv = Conv2DTranspose(512, 256, 2, stride=2)
self.block6_conv1 = Conv_Block(512, 256, 3, 1)
self.block6_conv2 = Conv_Block(256, 256, 3, 1)
self.block7_dconv = Conv2DTranspose(256, 128, 2, stride=2)
self.block7_conv1 = Conv_Block(256, 128, 3, 1)
self.block7_conv2 = Conv_Block(128, 128, 3, 1)
self.block8_dconv = Conv2DTranspose(128, 64, 2, stride=2)
self.block8_conv1 = Conv_Block(128, 64, 3, 1)
self.block8_conv2 = Conv_Block(64, 64, 3, 1)
self.block9_dconv = Conv2DTranspose(64, 32, 2, stride=2)
self.block9_conv1 = Conv_Block(64, 32, 3, 1)
self.block9_conv2 = Conv_Block(32, 32, 3, 1)
self.side63 = Conv2D(256, 2, 1, act='sigmoid')
self.side73 = Conv2D(128, 2, 1, act='sigmoid')
self.side83 = Conv2D(64, 2, 1, act='sigmoid')
self.side93 = Conv2D(32, 2, 1, act='sigmoid')
def __init__(self, num_classes=1000):
super(AlexNet, self).__init__()
# AlexNet与LeNet一样使用卷积层与池化层提取图像特征
# 不同的是AlexNet激活函数换成了relu
self.conv1 = Conv2D(num_channels=3,
num_filters=96,
filter_size=11,
stride=4,
padding=5,
act='relu')
# 对于每一个卷积层，激活操作是包含在卷积层中的
self.pool1 = Pool2D(pool_size=2, pool_type='max', pool_stride=2)
self.conv2 = Conv2D(num_channels=96,
num_filters=256,
filter_size=5,
stride=1,
padding=2,
act='relu')
self.pool2 = Pool2D(pool_size=2, pool_type='max', pool_stride=2)
self.conv3 = Conv2D(num_channels=256,
num_filters=384,
filter_size=3,
stride=1,
padding=1,
act='relu')
self.conv4 = Conv2D(num_channels=384,
num_filters=384,
filter_size=3,
stride=1,
padding=1,
act='relu')
self.conv5 = Conv2D(num_channels=384,
num_filters=256,
filter_size=3,
stride=1,
padding=1,
act='relu')
self.pool5 = Pool2D(pool_size=2, pool_type='max', pool_stride=2)
self.fc1 = Linear(input_dim=12544, output_dim=4096, act='relu')
self.drop_ratio1 = 0.5
# AlexNet的一个改进就是引入了dropout
# 在全连接之后使用dropout抑制过拟合
self.fc2 = Linear(input_dim=4096, output_dim=4096, act='relu')
self.drop_ratio2 = 0.5
self.fc3 = Linear(input_dim=4096,
output_dim=num_classes,
act='softmax')
def architecture_init(self):
# shared layers
ch_in = self.channels
shared_sub_layers = [
Conv2D(num_channels=3,
num_filters=ch_in,
filter_size=3,
padding=1,
param_attr=weight_initializer,
bias_attr=bias_initializer,
stride=1,
act=None)
]
for i in range(self.repeat_num):
ch_out = min(ch_in * 2, self.max_conv_dim)
sub_layer = ResBlock(ch_in,
ch_out,
normalize=False,
downsample=True,
sn=self.sn,
act=None)
ch_in = ch_out
shared_sub_layers.append(sub_layer)
shared_sub_layers.append(Leaky_Relu(alpha=0.2))
shared_sub_layers.append(
Conv2D(num_channels=self.max_conv_dim,
num_filters=self.max_conv_dim,
filter_size=4,
padding=0,
param_attr=weight_initializer,
bias_attr=bias_initializer,
stride=1,
act=None))
shared_sub_layers.append(Leaky_Relu(alpha=0.2))
shared_layers = Sequential(*shared_sub_layers)
# unshared layers
unshared_sub_layers = []
for _ in range(self.num_domains):
sub_layer = Linear(self.max_conv_dim,
self.style_dim,
param_attr=weight_initializer,
bias_attr=bias_initializer,
act=None)
unshared_sub_layers.append(sub_layer)
unshared_layers = Sequential(*unshared_sub_layers)
return shared_layers, unshared_layers
def __init__(self,
num_channels,
num_filters,
filter_size,
stride=1,
groups=1,
act=None):
super(ConvBNLayer, self).__init__()
self._conv = Conv2D(
num_channels=num_channels,
num_filters=num_filters,
filter_size=filter_size,
stride=stride,
padding=(filter_size - 1) // 2,
groups=None,
act=None,
param_attr=fluid.param_attr.ParamAttr(),
bias_attr=False)
self._batch_norm = BatchNorm(
num_filters,
act=act,
param_attr=fluid.param_attr.ParamAttr(),
bias_attr=fluid.param_attr.ParamAttr())
def __init__(self,
ch_in,
ch_out,
filter_size=3,
stride=1,
groups=1,
padding=0,
act="leaky",
is_test=True):
super(ConvBNLayer, self).__init__()
self.conv = Conv2D(num_channels=ch_in,
num_filters=ch_out,
filter_size=filter_size,
stride=stride,
padding=padding,
groups=groups,
param_attr=ParamAttr(
initializer=fluid.initializer.Normal(0., 0.02)),
bias_attr=False,
act=None)
self.batch_norm = BatchNorm(
num_channels=ch_out,
is_test=is_test,
param_attr=ParamAttr(initializer=fluid.initializer.Normal(
0., 0.02),
regularizer=L2Decay(0.)),
bias_attr=ParamAttr(initializer=fluid.initializer.Constant(0.0),
regularizer=L2Decay(0.)))
self.act = act
def __init__(self,
num_channels,
num_filters,
filter_size,
padding=0,
stride=1,
groups=None,
act=None,
name=None):
super(ConvLayer, self).__init__()
param_attr, bias_attr = initial_type(name=name,
input_channels=num_channels,
use_bias=True,
filter_size=filter_size)
self.num_filters = num_filters
self._conv = Conv2D(num_channels=num_channels,
num_filters=num_filters,
filter_size=filter_size,
padding=padding,
stride=stride,
groups=groups,
act=act,
param_attr=param_attr,
bias_attr=bias_attr)
def __init__(self,
num_channels,
num_filters,
filter_size,
stride=1,
groups=1,
act=None):
"""
num_channels, 卷积层的输入通道数
num_filters, 卷积层的输出通道数
stride, 卷积层的步幅
groups, 分组卷积的组数，默认groups=1不使用分组卷积
act, 激活函数类型，默认act=None不使用激活函数
"""
super(ConvBNLayer, self).__init__()
# 创建卷积层
self.conv = Conv2D(num_channels=num_channels,
num_filters=num_filters,
filter_size=filter_size,
stride=stride,
padding=(filter_size - 1) // 2,
groups=groups,
act=None,
bias_attr=False)
# 创建BatchNorm层
self.batch_norm = BatchNorm(num_channels=num_filters, act=act)
def __init__(self,
num_channels,
num_filters,
filter_size,
stride=1,
groups=1,
act="relu",
name=None):
super(ConvBNLayer, self).__init__()
self._conv = Conv2D(num_channels=num_channels,
num_filters=num_filters,
filter_size=filter_size,
stride=stride,
padding=(filter_size - 1) // 2,
groups=groups,
param_attr=ParamAttr(
initializer=Normal(scale=0.001),
name=name + "_weights"),
bias_attr=False)
bn_name = name + '_bn'
self._batch_norm = BatchNorm(
num_filters,
weight_attr=ParamAttr(name=bn_name + '_scale',
initializer=fluid.initializer.Constant(1.0)),
bias_attr=ParamAttr(bn_name + '_offset',
initializer=fluid.initializer.Constant(0.0)))
self.act = act
def __init__(self,
backbone,
num_classes,
in_channels,
channels=None,
pretrained_model=None,
ignore_index=255,
**kwargs):
super(FCN, self).__init__()
self.num_classes = num_classes
self.ignore_index = ignore_index
self.EPS = 1e-5
if channels is None:
channels = in_channels
self.backbone = manager.BACKBONES[backbone](**kwargs)
self.conv_last_2 = ConvBNLayer(num_channels=in_channels,
num_filters=channels,
filter_size=1,
stride=1,
name='conv-2')
self.conv_last_1 = Conv2D(num_channels=channels,
num_filters=self.num_classes,
filter_size=1,
stride=1,
padding=0,
param_attr=ParamAttr(
initializer=Normal(scale=0.001),
name='conv-1_weights'))
self.init_weight(pretrained_model)
def __init__(self,
num_channels,
num_filters,
filter_size,
conv_stride=1,
conv_padding=0,
conv_dilation=1,
conv_groups=1,
act=None,
use_cudnn=False,
param_attr=None,
bias_attr=None):
super(SimpleImgConv, self).__init__()
self._conv2d = Conv2D(num_channels=num_channels,
num_filters=num_filters,
filter_size=filter_size,
stride=conv_stride,
padding=conv_padding,
dilation=conv_dilation,
groups=conv_groups,
param_attr=None,
bias_attr=None,
act=act,
use_cudnn=use_cudnn)
def __init__(self,
in_channels,
num_filters,
filter_size,
stride=1,
padding=0,
groups=1,
act='relu',
name=None):
super(ConvBNLayer, self).__init__()
self.conv = Conv2D(num_channels=in_channels,
num_filters=num_filters,
filter_size=filter_size,
stride=stride,
padding=padding,
groups=groups,
act=None,
param_attr=ParamAttr(name=name + ".conv.weight"),
bias_attr=False)
self.bn = BatchNorm(num_filters,
act=act,
epsilon=0.001,
param_attr=ParamAttr(name=name + ".bn.weight"),
bias_attr=ParamAttr(name=name + ".bn.bias"),
moving_mean_name=name + '.bn.running_mean',
moving_variance_name=name + '.bn.running_var')
def __init__(self,
num_channels,
num_filters,
filter_size,
stride=1,
groups=1,
act=None,
name=None):
super(ConvBNLayer, self).__init__()
self._conv = Conv2D(num_channels=num_channels,
num_filters=num_filters,
filter_size=filter_size,
stride=stride,
padding=(filter_size - 1) // 2,
groups=None,
act=None,
param_attr=fluid.param_attr.ParamAttr(name=name +
"_weights"),
bias_attr=False)
if name == "conv1":
bn_name = "bn_" + name
else:
bn_name = "bn" + name[3:]
self._batch_norm = BatchNorm(
num_filters,
act=act,
param_attr=ParamAttr(name=bn_name +
"_scale"), #fluid.param_attr.ParamAttr(),
bias_attr=ParamAttr(bn_name +
"_offset"), #fluid.param_attr.ParamAttr())
moving_mean_name=bn_name + "_mean",
moving_variance_name=bn_name + "_variance")
def __init__(self,
dict_dim,
emb_dim=128,
hid_dim=128,
fc_hid_dim=96,
class_dim=2,
channels=1,
win_size=(3, 128)):
super(CNN, self).__init__()
self.dict_dim = dict_dim
self.emb_dim = emb_dim
self.hid_dim = hid_dim
self.fc_hid_dim = fc_hid_dim
self.class_dim = class_dim
self.channels = channels
self.win_size = win_size
self.embedding = Embedding(size=[self.dict_dim + 1, self.emb_dim],
dtype='float64',
is_sparse=False,
padding_idx=0)
self._conv2d = Conv2D(num_channels=self.channels,
num_filters=self.hid_dim,
filter_size=win_size,
padding=[1, 0],
use_cudnn=True,
act=None,
dtype="float64")
self._fc_1 = Linear(input_dim=self.hid_dim,
output_dim=self.fc_hid_dim,
dtype="float64")
self._fc_2 = Linear(input_dim=self.fc_hid_dim,
output_dim=self.class_dim,
act="softmax",
dtype="float64")
def __init__(self,
height,
width,
with_r,
with_boundary,
in_channels,
first_one=False,
out_channels=256,
kernel_size=1,
stride=1,
padding=0):
super(CoordConvTh, self).__init__()
self.out_channels = out_channels
self.kernel_size = kernel_size
self.stride = stride
self.padding = padding
self.addcoords = AddCoordsTh(height, width, with_r, with_boundary)
in_channels += 2
if with_r:
in_channels += 1
if with_boundary and not first_one:
in_channels += 2
self.conv = Conv2D(num_channels=in_channels,
num_filters=self.out_channels,
filter_size=self.kernel_size,
stride=self.stride,
padding=self.padding)
def __init__(self,
img_size=256,
img_ch=3,
style_dim=64,
max_conv_dim=512,
sn=False,
w_hpf=0):
super(Generator, self).__init__()
self.img_size = img_size
self.img_ch = img_ch
self.style_dim = style_dim
self.max_conv_dim = max_conv_dim
self.sn = sn
self.channels = 2**14 // img_size # if 256 -> 64
self.w_hpf = w_hpf
self.repeat_num = int(np.log2(img_size)) - 4 # if 256 -> 4
if self.w_hpf == 1:
self.repeat_num += 1
self.from_rgb = Conv2D(num_channels=self.img_ch,
num_filters=self.channels,
filter_size=3,
padding=1,
param_attr=weight_initializer,
bias_attr=bias_initializer,
stride=1,
act=None)
self.encode, self.decode, self.to_rgb = self.architecture_init()
def __init__(self,
input_channels,
output_channels,
filter_size,
stride=1,
padding=0,
act=None,
name=None):
super(ConvBNLayer, self).__init__()
self._conv = Conv2D(num_channels=input_channels,
num_filters=output_channels,
filter_size=filter_size,
stride=stride,
padding=padding,
param_attr=ParamAttr(name=name + "/weights"),
bias_attr=False)
self._bn = BatchNorm(
num_channels=output_channels,
act=act,
epsilon=1e-3,
momentum=0.99,
param_attr=ParamAttr(name=name + "/BatchNorm/gamma"),
bias_attr=ParamAttr(name=name + "/BatchNorm/beta"),
moving_mean_name=name + "/BatchNorm/moving_mean",
moving_variance_name=name + "/BatchNorm/moving_variance")
def __init__(self, inc, outc, size, padding=1):
super(Conv_Block, self).__init__()
self.c1 = Conv2D(num_channels=inc,
num_filters=outc,
filter_size=size,
padding=padding)
self.bn = BatchNorm(num_channels=outc, act='relu', in_place=True)
def __init__(self,
num_channels,
filter_size,
num_filters,
stride,
padding,
channels=None,
num_groups=1,
use_cudnn=True):
super(ConvBNLayer, self).__init__()
tmp_param = ParamAttr(name=self.full_name() + "_weights")
self._conv = Conv2D(num_channels=num_channels,
num_filters=num_filters,
filter_size=filter_size,
stride=stride,
padding=padding,
groups=num_groups,
act=None,
use_cudnn=use_cudnn,
param_attr=tmp_param,
bias_attr=False)
self._batch_norm = BatchNorm(
num_filters,
param_attr=ParamAttr(name=self.full_name() + "_bn" + "_scale"),
bias_attr=ParamAttr(name=self.full_name() + "_bn" + "_offset"),
moving_mean_name=self.full_name() + "_bn" + '_mean',
moving_variance_name=self.full_name() + "_bn" + '_variance')
def __init__(self,
num_channels,
num_filters=64,
filter_size=7,
stride=1,
stddev=0.02,
padding=0,
norm=True,
norm_layer=InstanceNorm,
relu=True,
relufactor=0.0,
use_bias=False):
super(conv2d, self).__init__()
if use_bias == False:
con_bias_attr = False
else:
con_bias_attr = fluid.ParamAttr(
initializer=fluid.initializer.Constant(0.0))
self.conv = Conv2D(num_channels=num_channels,
num_filters=int(num_filters),
filter_size=int(filter_size),
stride=stride,
padding=padding,
use_cudnn=use_cudnn,
param_attr=fluid.ParamAttr(
initializer=fluid.initializer.NormalInitializer(
loc=0.0, scale=stddev)),
bias_attr=con_bias_attr)
if norm_layer == InstanceNorm:
self.bn = InstanceNorm(
num_channels=num_filters,
param_attr=fluid.ParamAttr(
initializer=fluid.initializer.Constant(1.0),
trainable=False),
bias_attr=fluid.ParamAttr(
initializer=fluid.initializer.Constant(0.0),
trainable=False),
)
elif norm_layer == BatchNorm:
self.bn = BatchNorm(
num_channels=num_filters,
param_attr=fluid.ParamAttr(initializer=fluid.initializer.
NormalInitializer(1.0, 0.02)),
bias_attr=fluid.ParamAttr(
initializer=fluid.initializer.Constant(0.0)),
)
else:
raise NotImplementedError
self.relufactor = relufactor
self.use_bias = use_bias
self.norm = norm
if relu:
if relufactor == 0.0:
self.lrelu = ReLU()
else:
self.lrelu = Leaky_ReLU(self.relufactor)
self.relu = relu