def __init__(self, inp, oup, k, s, p, dw=False, linear=False, data_format="NCHW"):
super().__init__()
self.linear = linear
if dw:
self.conv = nn.Conv2D(
inp, oup, k, s, p, groups=inp, bias_attr=False, data_format=data_format)
else:
self.conv = nn.Conv2D(inp, oup, k, s, p, bias_attr=False, data_format=data_format)
self.bn = nn.BatchNorm2D(oup, data_format=data_format)
if not linear:
self.prelu = nn.PReLU(oup, data_format=data_format)
def __init__(self, extract_embedding: bool = True):
super(CNN6, self).__init__()
self.bn0 = nn.BatchNorm2D(64)
self.conv_block1 = ConvBlock5x5(in_channels=1, out_channels=64)
self.conv_block2 = ConvBlock5x5(in_channels=64, out_channels=128)
self.conv_block3 = ConvBlock5x5(in_channels=128, out_channels=256)
self.conv_block4 = ConvBlock5x5(in_channels=256, out_channels=512)
self.fc1 = nn.Linear(512, self.emb_size)
self.fc_audioset = nn.Linear(self.emb_size, 527)
self.extract_embedding = extract_embedding
def _make_layer(self, planes, blocks, stride):
downsample = None
if stride != [1, 1] or self.inplanes != planes:
downsample = nn.Sequential(conv1x1(self.inplanes, planes, stride),
nn.BatchNorm2D(planes))
layers = []
layers.append(AsterBlock(self.inplanes, planes, stride, downsample))
self.inplanes = planes
for _ in range(1, blocks):
layers.append(AsterBlock(self.inplanes, planes))
return nn.Sequential(*layers)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2D(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride),
nn.BatchNorm2D(planes * block.expansion),)
layers = [block(self.inplanes, planes, stride, downsample, use_se=self.use_se)]
self.inplanes = planes
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, use_se=self.use_se))
return nn.Sequential(*layers)
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.bn1 = nn.BatchNorm2D(inplanes)
self.conv1 = nn.Conv2D(inplanes,
planes,
kernel_size=1,
bias_attr=False)
self.bn2 = nn.BatchNorm2D(planes)
self.conv2 = nn.Conv2D(planes, (planes * 1),
kernel_size=3,
stride=stride,
padding=1,
bias_attr=False)
self.bn3 = nn.BatchNorm2D((planes * 1))
self.conv3 = nn.Conv2D((planes * 1),
planes * Bottleneck.outchannel_ratio,
kernel_size=1,
bias_attr=False)
self.bn4 = nn.BatchNorm2D(planes * Bottleneck.outchannel_ratio)
self.relu = nn.ReLU()
self.downsample = downsample
self.stride = stride
def __init__(self, npoint, radius, nsample, in_channel, mlp, group_all):
super(PointNetSetAbstraction, self).__init__()
self.npoint = npoint
self.radius = radius
self.nsample = nsample
self.mlp_convs = []
self.mlp_bns = []
last_channel = in_channel
for out_channel in mlp:
self.mlp_convs.append(nn.Conv2D(last_channel, out_channel, 1))
self.mlp_bns.append(nn.BatchNorm2D(out_channel))
last_channel = out_channel
self.group_all = group_all
def __init__(self, in_chan, out_chan):
super(AttentionRefinementModule, self).__init__()
self.conv = layers.ConvBNReLU(in_chan,
out_chan,
kernel_size=3,
stride=1,
padding=1)
self.conv_atten = nn.Conv2D(out_chan,
out_chan,
kernel_size=1,
bias_attr=None)
self.bn_atten = nn.BatchNorm2D(out_chan)
self.sigmoid_atten = nn.Sigmoid()
def BatchNorm2d(num_features, eps=1e-05, momentum=0.9, affine=True):
if not affine:
weight_attr = False
bias_attr = False
else:
weight_attr = None
bias_attr = None
batchnorm = nn.BatchNorm2D(num_features,
momentum,
eps,
weight_attr=weight_attr,
bias_attr=bias_attr)
return batchnorm
def _block(self, in_channels, out_channels, kernel_size, stride, padding):
return nn.Sequential(
nn.Conv2DTranspose(
in_channels, out_channels, kernel_size, stride, padding, bias_attr=False,
weight_attr=paddle.ParamAttr(initializer=conv_initializer() )
),
nn.BatchNorm2D(
out_channels,
weight_attr=paddle.ParamAttr(initializer=bn_initializer() ) ,
momentum=0.8
),
nn.ReLU(),
)
def __init__(self, inp, oup, reduction=32):
super(CoordAttention, self).__init__()
self.pool_h = nn.AdaptiveAvgPool2D((None, 1))
self.pool_w = nn.AdaptiveAvgPool2D((1, None))
mip = max(8, inp // reduction)
self.conv1 = nn.Conv2D(inp, mip, kernel_size=1, stride=1, padding=0)
self.bn1 = nn.BatchNorm2D(mip)
self.act = H_Swish()
self.conv_h = nn.Conv2D(mip, oup, kernel_size=1, stride=1, padding=0)
self.conv_w = nn.Conv2D(mip, oup, kernel_size=1, stride=1, padding=0)
def __init__(self, num_classes):
super(ResidualAttentionModel_56, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2D(3,
64,
kernel_size=7,
stride=2,
padding=3,
bias_attr=False), nn.BatchNorm2D(64), nn.ReLU())
self.mpool1 = nn.MaxPool2D(kernel_size=3, stride=2, padding=1)
self.residual_block1 = ResidualBlock(64, 256)
self.attention_module1 = AttentionModule_stage1(256, 256)
self.residual_block2 = ResidualBlock(256, 512, 2)
self.attention_module2 = AttentionModule_stage2(512, 512)
self.residual_block3 = ResidualBlock(512, 1024, 2)
self.attention_module3 = AttentionModule_stage3(1024, 1024)
self.residual_block4 = ResidualBlock(1024, 2048, 2)
self.residual_block5 = ResidualBlock(2048, 2048)
self.residual_block6 = ResidualBlock(2048, 2048)
self.mpool2 = nn.Sequential(nn.BatchNorm2D(2048), nn.ReLU(),
nn.AvgPool2D(kernel_size=7, stride=1))
self.fc = nn.Linear(2048, num_classes)
def __init__(self, c_in, c_out, is_downsample=False):
super(BasicBlock, self).__init__()
self.is_downsample = is_downsample
if is_downsample:
self.conv1 = nn.Conv2D(c_in, c_out, 3, stride=2, padding=1, bias_attr=False)
else:
self.conv1 = nn.Conv2D(c_in, c_out, 3, stride=1, padding=1, bias_attr=False)
self.bn1 = nn.BatchNorm2D(c_out)
self.relu = nn.ReLU()
self.conv2 = nn.Conv2D(c_out, c_out, 3, stride=1, padding=1, bias_attr=False)
self.bn2 = nn.BatchNorm2D(c_out)
if is_downsample:
self.downsample = nn.Sequential(
nn.Conv2D(c_in, c_out, 1, stride=2, bias_attr=False),
nn.BatchNorm2D(c_out)
)
elif c_in != c_out:
self.downsample = nn.Sequential(
nn.Conv2D(c_in, c_out, 1, stride=1, bias_attr=False),
nn.BatchNorm2D(c_out)
)
self.is_downsample = True
def __init__(self, in_channel_left, in_channel_right):
super(MFR, self).__init__()
self.conv0 = nn.Conv2D(in_channel_left, 256, 3, 1, 1)
self.bn0 = nn.BatchNorm2D(256)
self.conv1 = nn.Conv2D(in_channel_right, 256, 1)
self.bn1 = nn.BatchNorm2D(256)
self.conv2 = nn.Conv2D(256, 256, kernel_size=3, stride=1, padding=1)
self.bn2 = nn.BatchNorm2D(256)
self.conv13 = nn.Conv2D(256,
256,
kernel_size=(1, 3),
stride=1,
padding=(0, 1))
self.bn13 = nn.BatchNorm2D(256)
self.conv31 = nn.Conv2D(256,
256,
kernel_size=(3, 1),
stride=1,
padding=(1, 0))
self.bn31 = nn.BatchNorm2D(256)
def __init__(self, in_channels, out_channels, kernel_size, residual):
super(DlaRoot, self).__init__()
self.conv = nn.Conv2D(
in_channels,
out_channels,
1,
stride=1,
bias_attr=False,
padding=(kernel_size - 1) // 2,
)
self.bn = nn.BatchNorm2D(out_channels)
self.relu = nn.ReLU()
self.residual = residual
def __init__(self, in_dim, out_dim, kernel_size=4, stride=2, padding=1, use_dropout=False):
super(Upsample, self).__init__()
sequence = [
nn.ReLU(), # ReLU
nn.Conv2DTranspose(in_dim, out_dim, kernel_size, stride, padding, bias_attr=False), # Conv2DTranspose
nn.BatchNorm2D(out_dim) # nn.BatchNorm2D
]
if use_dropout:
sequence.append(nn.Dropout(p=0.5))
self.layers = nn.Sequential(*sequence)
def __init__(self, in_channel):
super(SR, self).__init__()
self.conv1 = nn.Conv2D(in_channel,
192,
kernel_size=3,
stride=1,
padding=1)
self.bn1 = nn.BatchNorm2D(192)
self.conv2 = nn.Conv2D(192,
192 * 2,
kernel_size=3,
stride=1,
padding=1)
def __init__(self,
in_features,
out_features,
groups=1,
kernel_size=3,
padding=1):
super(SameBlock2d, self).__init__()
self.conv = nn.Conv2D(in_channels=in_features,
out_channels=out_features,
kernel_size=kernel_size,
padding=padding,
groups=groups)
self.norm = nn.BatchNorm2D(out_features)
def __init__(self):
super(Generator, self).__init__()
self.conv_1 = nn.Conv2DTranspose(
100,512,4,1,0,
bias_attr=False,weight_attr=paddle.ParamAttr(name="g_dconv_weight_1_",initializer=conv_initializer)
)
self.bn_1 = nn.BatchNorm2D(
512,
weight_attr=paddle.ParamAttr(name="g_1_bn_weight_",initializer=bn_initializer),momentum=0.8
)
self.conv_2 = nn.Conv2DTranspose(
512,256,4,2,1,
bias_attr=False,weight_attr=paddle.ParamAttr(name="g_dconv_weight_2_",initializer=conv_initializer)
)
self.bn_2 = nn.BatchNorm2D(
256,
weight_attr=paddle.ParamAttr(name="g_2_bn_weight_",initializer=bn_initializer),momentum=0.8
)
self.conv_3 = nn.Conv2DTranspose(
256,128,4,2,1,
bias_attr=False,weight_attr=paddle.ParamAttr(name="g_dconv_weight_3_",initializer=conv_initializer)
)
self.bn_3 = nn.BatchNorm2D(
128,
weight_attr=paddle.ParamAttr(name="g_3_bn_weight_",initializer=bn_initializer),momentum=0.8
)
self.conv_4 = nn.Conv2DTranspose(
128,64,4,2,1,
bias_attr=False,weight_attr=paddle.ParamAttr(name="g_dconv_weight_4_",initializer=conv_initializer)
)
self.bn_4 = nn.BatchNorm2D(
64,
weight_attr=paddle.ParamAttr(name="g_4_bn_weight_",initializer=bn_initializer),momentum=0.8
)
self.conv_5 = nn.Conv2DTranspose(
64,3,4,2,1,
bias_attr=False,weight_attr=paddle.ParamAttr(name="g_dconv_weight_5_",initializer=conv_initializer)
)
self.tanh = paddle.nn.Tanh()
def __init__(self, in_dim, out_dim, kernel_size=4, stride=2, padding=1):
super(ConvBlock, self).__init__()
self.layers = nn.Sequential(
nn.Conv2D(in_dim,
out_dim,
kernel_size,
stride,
padding,
bias_attr=False), # Conv2D
nn.BatchNorm2D(out_dim), # BatchNorm2D
nn.LeakyReLU(0.2) # LeakyReLU, leaky=0.2
)
def __init__(self, inplanes, planes, stride=1):
super().__init__()
# all conv layers have stride 1. an avgpool is performed after the second convolution when stride > 1
self.conv1 = nn.Conv2D(inplanes, planes, 1, bias_attr=False)
self.bn1 = nn.BatchNorm2D(planes)
self.conv2 = nn.Conv2D(planes, planes, 3, padding=1, bias_attr=False)
self.bn2 = nn.BatchNorm2D(planes)
self.avgpool = nn.AvgPool2D(stride) if stride > 1 else Identity()
self.conv3 = nn.Conv2D(planes,
planes * self.expansion,
1,
bias_attr=False)
self.bn3 = nn.BatchNorm2D(planes * self.expansion)
self.relu = nn.ReLU()
self.downsample = None
self.stride = stride
if stride > 1 or inplanes != planes * Bottleneck.expansion:
# downsampling layer is prepended with an avgpool, and the subsequent convolution has stride 1
# self.downsample = nn.Sequential(OrderedDict([
# ("-1", nn.AvgPool2D(stride)),
# ("0", nn.Conv2D(inplanes, planes * self.expansion, 1, stride=1, bias_attr=False)),
# ("1", nn.BatchNorm2D(planes * self.expansion))
# ]))
self.downsample = nn.Sequential(
("-1", nn.AvgPool2D(stride)),
("0",
nn.Conv2D(inplanes,
planes * self.expansion,
1,
stride=1,
bias_attr=False)),
("1", nn.BatchNorm2D(planes * self.expansion)))
def __init__(self, channel):
super(SRMLayer, self).__init__()
self.cfc = self.create_parameter(
shape=[channel, 2],
default_initializer=nn.initializer.Assign(
paddle.zeros([channel, 2])))
self.bn = nn.BatchNorm2D(channel)
self.activation = nn.Sigmoid()
setattr(self.cfc, 'srm_param', True)
setattr(self.bn.weight, 'srm_param', True)
setattr(self.bn.bias, 'srm_param', True)
def __init__(self,
in_features,
out_features,
kernel_size=3,
padding=1,
groups=1):
super(DownBlock2d, self).__init__()
self.conv = nn.Conv2D(in_channels=in_features,
out_channels=out_features,
kernel_size=kernel_size,
padding=padding,
groups=groups)
self.norm = nn.BatchNorm2D(out_features)
self.pool = nn.AvgPool2D(kernel_size=(2, 2))
def conv3x3_block(in_channels, out_channels, stride=1):
n = 3 * 3 * out_channels
w = math.sqrt(2. / n)
conv_layer = nn.Conv2D(
in_channels,
out_channels,
kernel_size=3,
stride=stride,
padding=1,
weight_attr=nn.initializer.Normal(
mean=0.0, std=w),
bias_attr=nn.initializer.Constant(0))
block = nn.Sequential(conv_layer, nn.BatchNorm2D(out_channels), nn.ReLU())
return block
def __init__(
self, in_channels, out_channels, kernel_size, stride, padding, groups=1
):
super(ConvBN, self).__init__()
self.conv = nn.Conv2D(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=stride,
padding=padding,
groups=groups,
bias_attr=False,
)
self.bn = nn.BatchNorm2D(num_features=out_channels)
def __init__(self, num_modules=1, end_relu=False, num_landmarks=98, fname_pretrained=None):
super(FAN, self).__init__()
self.num_modules = num_modules
self.end_relu = end_relu
# Base part
self.conv1 = CoordConvTh(256, 256, True, False,
in_channels=3, out_channels=64,
kernel_size=7, stride=2, padding=3)
self.bn1 = nn.BatchNorm2D(64)
self.conv2 = ConvBlock(64, 128)
self.conv3 = ConvBlock(128, 128)
self.conv4 = ConvBlock(128, 256)
# Stacking part
self.add_sublayer('m0', HourGlass(1, 4, 256, first_one=True))
self.add_sublayer('top_m_0', ConvBlock(256, 256))
self.add_sublayer('conv_last0', nn.Conv2D(256, 256, 1, 1, 0))
self.add_sublayer('bn_end0', nn.BatchNorm2D(256))
self.add_sublayer('l0', nn.Conv2D(256, num_landmarks+1, 1, 1, 0))
if fname_pretrained is not None:
self.load_pretrained_weights(fname_pretrained)
def __init__(self,
inplanes,
planes,
stride=1,
downsample=None,
groups=1,
base_width=64,
dilation=1):
super(IBasicBlock, self).__init__()
if groups != 1 or base_width != 64:
raise ValueError(
'BasicBlock only supports groups=1 and base_width=64')
if dilation > 1:
raise NotImplementedError(
"Dilation > 1 not supported in BasicBlock")
self.bn1 = nn.BatchNorm2D(inplanes, epsilon=1e-05, momentum=0.1)
self.conv1 = conv3x3(inplanes, planes)
self.bn2 = nn.BatchNorm2D(planes, epsilon=1e-05, momentum=0.1)
self.prelu = nn.PReLU(planes)
self.conv2 = conv3x3(planes, planes, stride)
self.bn3 = nn.BatchNorm2D(planes, epsilon=1e-05, momentum=0.1)
self.downsample = downsample
self.stride = stride
def __init__(self,
cin,
cout,
kernel_size,
stride,
padding,
output_padding=0,
*args,
**kwargs):
super().__init__(*args, **kwargs)
self.conv_block = nn.Sequential(
nn.Conv2DTranspose(cin, cout, kernel_size, stride, padding,
output_padding), nn.BatchNorm2D(cout))
self.act = nn.ReLU()
def __init__(self, in_channels, channels, se_ratio=12):
super(SE, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2D(1)
self.fc = nn.Sequential(
nn.Conv2D(in_channels,
channels // se_ratio,
kernel_size=1,
padding=0),
nn.BatchNorm2D(channels // se_ratio),
nn.ReLU(),
nn.Conv2D(channels // se_ratio, channels, kernel_size=1,
padding=0),
nn.Sigmoid(),
)
def make_layers(cfg, batch_norm=False):
layers = []
in_channels = 3
for v in cfg:
if v == 'M':
layers += [nn.MaxPool2D(kernel_size=2, stride=2)]
else:
conv2d = nn.Conv2D(in_channels, v, kernel_size=3, padding=1)
if batch_norm:
layers += [conv2d, nn.BatchNorm2D(v), nn.ReLU()]
else:
layers += [conv2d, nn.ReLU()]
in_channels = v
return nn.Sequential(*layers)
def __init__(self, ):
super(Discriminator, self).__init__()
self.dis = nn.Sequential(
# input [B, 1, 32, 32] -> [B, 64, 16, 16]
nn.Conv2D(1, 64, 4, 2, 1, bias_attr=False),
nn.LeakyReLU(0.2),
# state size. [B, 64, 16, 16] -> [B, 128, 8, 8]
nn.Conv2D(64, 64 * 2, 4, 2, 1, bias_attr=False),
nn.BatchNorm2D(64 * 2),
nn.LeakyReLU(0.2),
# state size. [B, 128, 8, 8] -> [B, 256, 4, 4]
nn.Conv2D(64 * 2, 64 * 4, 4, 2, 1, bias_attr=False),
nn.BatchNorm2D(64 * 4),
nn.LeakyReLU(0.2),
# state size. [B, 256, 4, 4] -> [B, 1, 1, 1]
nn.Conv2D(64 * 4, 1, 4, 1, 0, bias_attr=False),
# 这里为需要改变的地方
# nn.Sigmoid()
nn.LeakyReLU())
