def __init__(self):
super(ASPP, self).__init__()
in_planes = 2048
dilations = [1, 6, 12, 18]
# all aspp module output feature maps with channel 256
self.aspp1 = _ASPPModule(in_planes, planes=256, kernel_size=1, padding=0, dilation=dilations[0])
self.aspp2 = _ASPPModule(in_planes, planes=256, kernel_size=3, padding=dilations[1], dilation=dilations[1])
self.aspp3 = _ASPPModule(in_planes, planes=256, kernel_size=3, padding=dilations[2], dilation=dilations[2])
self.aspp4 = _ASPPModule(in_planes, planes=256, kernel_size=3, padding=dilations[3], dilation=dilations[3])
# perform global average pooling on the last feature map of the backbone
# batchsize must be greater than 1, otherwise exception will be thrown in calculating BatchNorm
self.global_avg_pool = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)),
nn.Conv2d(in_planes, 256, 1, stride=1, bias=False),
nn.BatchNorm2d(256),
nn.ReLU())
self.p1 = nn.AdaptiveAvgPool2d(1)
self.p2 = nn.Conv2d(in_planes, 256, 1, stride=1, bias=False)
self.p3 = nn.BatchNorm2d(256)
self.conv1 = nn.Conv2d(1280, 256, 1, bias=False)
self.bn1 = nn.BatchNorm2d(256)
self.relu = nn.ReLU()
self.dropout = nn.Dropout(0.5)
self._init_weight()
def __init__(self):
super().__init__()
self.conv2d_1 = nn.Conv2d(1,6,5,padding=2)
self.avgpool2d = nn.AvgPool2d(2,stride=2)
self.conv2d_2 = nn.Conv2d(6,16,5)
self.flatten = nn.Flatten()
self.sig = nn.Sigmoid()
self.linear_1 = nn.Linear(16*5*5, 120)
self.linear_2 = nn.Linear(120, 84)
self.linear_3 = nn.Linear(84, 10)
def __init__(self, block, layers, num_classes=10):
super(ResNet, self).__init__()
self.inplanes = 64
self.initdata = nn.Conv2d(1,
64,
kernel_size=7,
stride=1,
padding=3,
bias=False)
self.bn0 = nn.BatchNorm2d(64)
self.relu0 = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self.make_layers(block, 64, layers[0])
self.layer2 = self.make_layers(block, 128, layers[1], stride=1)
self.layer3 = self.make_layers(block, 256, layers[2], stride=1)
self.layer4 = self.make_layers(block, 512, layers[3], stride=2)
self.avg = nn.AvgPool2d(7, stride=1)
self.full = nn.Linear(512 * block.expansion, num_classes)
self.sigmoid = nn.Sigmoid()
for m in self.modules():
if isinstance(
m,
nn.Conv2d): # isinstance() 函数来判断一个对象是否是一个已知的类型，类似 type()。
init.kaiming_normal_(m.weight,
mode='fan_out',
nonlinearity='relu')
elif isinstance(m, nn.BatchNorm2d):
init.constant_(m.weight, 1)
init.constant_(m.bias, 0)
def __init__(self, num_classes):
super(Decoder, self).__init__()
low_level_in_planes = 256
self.conv1 = nn.Conv2d(low_level_in_planes, 48, 1, bias=False)
self.bn1 = nn.BatchNorm2d(48)
self.relu = nn.ReLU()
self.last_conv = nn.Sequential(
nn.Conv2d(304, 256, kernel_size=3, stride=1, padding=1,
bias=False), nn.BatchNorm2d(256), nn.ReLU(),
nn.Dropout(0.5),
nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1,
bias=False), nn.BatchNorm2d(256), nn.ReLU(),
nn.Dropout(0.1),
nn.Conv2d(256, num_classes, kernel_size=1, stride=1))
self._init_weight()
def conv1x1(in_planes, out_planes, stride=1):
"""1x1 convolution"""
return nn.Conv2d(in_planes,
out_planes,
kernel_size=1,
stride=stride,
bias=False)
def conv3x3(in_planes, out_planes, stride=1):
"""3x3 convolution with padding"""
return nn.Conv2d(in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
def __init__(self):
super().__init__()
self.relu = nn.ReLU()
self.avgpool2d = nn.AvgPool2d(2, stride=2)
#输入部分
self.conv2d_1 = nn.Conv2d(1, 6, kernel_size=5, padding=2)
self.batchnorm2d = nn.BatchNorm2d(6)
#中间残差块
self.conv2d_2 = nn.Conv2d(6, 6, kernel_size=3, padding=1)
#输出部分
self.conv2d_3 = nn.Conv2d(6, 6, 5)
self.flatten = nn.Flatten()
self.sig = nn.Sigmoid()
self.linear_1 = nn.Linear(6 * 5 * 5, 64)
self.linear_2 = nn.Linear(64, 10)
def __init__(self, inplane, plane, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplane, plane, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(plane)
self.conv2 = nn.Conv2d(plane,
plane,
kernel_size=3,
padding=1,
stride=stride,
bias=False)
self.bn2 = nn.BatchNorm2d(plane)
self.conv3 = nn.Conv2d(plane,
self.expansion * plane,
kernel_size=1,
bias=False)
self.bn3 = nn.BatchNorm2d(self.expansion * plane)
self.downsample = downsample
self.stride = stride
self.relu3 = nn.ReLU(inplace=True)
def __init__(self, rnn_size, embedding_size, input_size, output_size,
grids_width, grids_height, dropout_par, device):
super(VPTLSTM, self).__init__()
######参数初始化##########
self.device = device
self.rnn_size = rnn_size # hidden size默认128
self.embedding_size = embedding_size # 空间坐标嵌入尺寸64，每个状态用64维向量表示
self.input_size = input_size # 输入尺寸6,特征向量长度
self.output_size = output_size # 输出尺寸5
self.grids_width = grids_width
self.grids_height = grids_height
self.dropout_par = dropout_par
############网络层初始化###############
# 输入embeded_input,hidden_states
self.cell = nn.LSTMCell(2 * self.embedding_size, self.rnn_size)
# 输入Embed层，将长度为input_size的vec映射到embedding_size
self.input_embedding_layer = nn.Linear(self.input_size,
self.embedding_size)
# 输入[vehicle_num,grids_height,grids_width,rnn_size] [26,39,5,128]
# 输出[vehicle_num,grids_height-12,grids_width-4,rnn_size*4] [26,27,1,32]
self.social_tensor_conv1 = nn.Conv2d(in_channels=self.rnn_size,
out_channels=self.rnn_size // 2,
kernel_size=(5, 3),
stride=(2, 1))
self.social_tensor_conv2 = nn.Conv2d(in_channels=self.rnn_size // 2,
out_channels=self.rnn_size // 4,
kernel_size=(5, 3),
stride=1)
self.social_tensor_embed = nn.Linear(
(self.grids_height - 15) * (self.grids_width - 4) *
self.rnn_size // 4, self.embedding_size)
# 输出Embed层，将长度为64的hidden_state映射到5
self.output_layer = nn.Linear(self.rnn_size, self.output_size)
self.relu = nn.ReLU()
self.dropout = nn.Dropout(self.dropout_par)
def __init__(self, in_channels, key_channels, out_channels, scale=1, dropout=0.1, bn_type=None):
super(SpatialOCR_Module, self).__init__()
self.object_context_block = ObjectAttentionBlock(in_channels, key_channels, scale, bn_type)
_in_channels = 2 * in_channels
self.conv_bn_dropout = nn.Sequential(
nn.Conv2d(_in_channels, out_channels, kernel_size=1, padding=0, bias=False),
nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True),
nn.Dropout2d(dropout)
)
def __init__(self,
in_planes,
planes,
stride=1,
downsample=None,
dilation=1):
super(Bottleneck, self).__init__()
self.conv1 = conv1x1(in_planes, planes)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes,
planes,
kernel_size=3,
stride=stride,
dilation=dilation,
padding=dilation,
bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def __init__(self, inp_dim, out_dim):
"""
residual block
:param inp_dim: input dimension
:param out_dim: output dimension
"""
super(Residual, self).__init__()
# the channel must be at least 1
out_dim_half = max(1, int(out_dim / 2))
self.conv1 = nn.Conv2d(inp_dim, out_dim_half, 1, 1, bias=False)
self.bn1 = nn.BatchNorm2d(out_dim_half)
self.relu = nn.ReLU()
self.conv2 = nn.Conv2d(out_dim_half, out_dim_half, 3, 1, 1, bias=False)
self.bn2 = nn.BatchNorm2d(out_dim_half)
self.conv3 = nn.Conv2d(out_dim_half, out_dim, 1, 1, bias=False)
self.bn3 = nn.BatchNorm2d(out_dim)
self.skip_layer = nn.Conv2d(inp_dim, out_dim, 1, 1, bias=False)
self.skip_layer_bn = nn.BatchNorm2d(out_dim)
def __init__(self, in_planes, planes, kernel_size, padding, dilation):
"""
One single ASPP module
:param in_planes: input channels
:param planes: output channels
:param kernel_size: kernel size in conv
:param padding: padding
:param dilation: dilation
"""
super(_ASPPModule, self).__init__()
self.atrous_conv = nn.Conv2d(in_planes, planes, kernel_size=kernel_size,
stride=1, padding=padding, dilation=dilation, bias=False)
self.bn = nn.BatchNorm2d(planes)
self.relu = nn.ReLU()
self._init_weight()
def make_layers(self, block, planes, num_blocks, stride=1):
downsample = None
layers = []
if stride != 1 or self.inplanes != block.expansion * planes:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes,
block.expansion * planes,
kernel_size=1,
stride=stride,
bias=False),
nn.BatchNorm2d(block.expansion * planes))
layers.append(
block(self.inplanes, planes, stride=stride, downsample=downsample))
self.inplanes = planes * block.expansion
for i in range(1, num_blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def __init__(self) -> None:
super(MaskBranch, self).__init__()
self.conv1 = Residual(256, 256)
self.conv2 = Residual(256, 256)
self.up16to8 = nn.UpsamplingBilinear2d(scale_factor=2)
self.conv3 = Residual(256, 128)
self.up8to4 = nn.UpsamplingBilinear2d(scale_factor=2)
self.conv4 = Residual(128, 64)
self.up4to2 = nn.UpsamplingBilinear2d(scale_factor=2)
self.conv5 = Residual(64, 64)
self.up2to1 = nn.UpsamplingBilinear2d(scale_factor=2)
self.conv6 = Residual(64, 1)
self.conv11 = nn.Conv2d(1, 1, kernel_size=1, stride=1)
def _make_multi_grid_layer(self,
block,
planes,
blocks,
stride=1,
dilation=1):
"""
Multi-grid unit
:param block: Bottleneck
:param planes:
:param blocks:
:param stride:
:param dilation:
:return:
"""
downsample = None
if stride != 1 or self.in_planes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.in_planes,
planes * block.expansion,
kernel_size=1,
stride=stride,
bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = list()
layers.append(
block(self.in_planes,
planes,
stride,
dilation=blocks[0] * dilation,
downsample=downsample))
self.in_planes = planes * block.expansion
for i in range(1, len(blocks)):
layers.append(
block(self.in_planes,
planes,
stride=1,
dilation=blocks[i] * dilation))
return nn.Sequential(*layers)
def __init__(self):
super(VectorBranch, self).__init__()
output_channel = regular_config.num_keypoint * 2
self.conv1 = Residual(256, 256)
self.conv2 = Residual(256, 256)
self.up16to8 = nn.UpsamplingBilinear2d(scale_factor=2)
self.up8to4 = nn.UpsamplingBilinear2d(scale_factor=2)
self.conv3 = Residual(256, 128)
self.conv4 = Residual(128, 64)
self.up4to2 = nn.UpsamplingBilinear2d(scale_factor=2)
self.conv5 = Residual(64, 64)
self.up2to1 = nn.UpsamplingBilinear2d(scale_factor=2)
self.conv6 = Residual(64, output_channel)
self.conv11 = nn.Conv2d(output_channel,
output_channel,
kernel_size=1,
stride=1)
def __init__(self, block, layers, BatchNorm=None):
super(ResNet, self).__init__()
if BatchNorm is None:
BatchNorm = nn.BatchNorm2d
self._BatchNorm = BatchNorm
# resnet head
self.in_planes = 64
self.conv1 = nn.Conv2d(3,
self.in_planes,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = BatchNorm(self.in_planes)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
# middle
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block,
128,
layers[1],
stride=2,
dilation=1)
self.layer3 = self._make_layer(block,
256,
layers[2],
stride=2,
dilation=1)
blocks = [1, 2, 4]
self.layer4 = self._make_multi_grid_layer(block,
512,
blocks=blocks,
stride=1,
dilation=2)
def __init__(self, in_channels, key_channels, scale=1, bn_type=None):
super(ObjectAttentionBlock, self).__init__()
self.scale = scale
self.in_channels = in_channels
self.key_channels = key_channels
self.pool = nn.MaxPool2d(kernel_size=(scale, scale))
self.f_pixel = nn.Sequential(
nn.Conv2d(in_channels=self.in_channels, out_channels=self.key_channels, kernel_size=1, stride=1,
padding=0, bias=False),
nn.BatchNorm2d(self.key_channels),
nn.ReLU(inplace=True),
nn.Conv2d(in_channels=self.key_channels, out_channels=self.key_channels, kernel_size=1, stride=1,
padding=0, bias=False),
nn.BatchNorm2d(self.key_channels),
nn.ReLU(inplace=True)
)
self.f_object = nn.Sequential(
nn.Conv2d(in_channels=self.in_channels, out_channels=self.key_channels, kernel_size=1, stride=1, padding=0,
bias=False),
nn.BatchNorm2d(self.key_channels),
nn.ReLU(inplace=True),
nn.Conv2d(in_channels=self.key_channels, out_channels=self.key_channels, kernel_size=1, stride=1, padding=0,
bias=False),
nn.BatchNorm2d(self.key_channels),
nn.ReLU(inplace=True)
)
self.f_down = nn.Sequential(
nn.Conv2d(in_channels=self.in_channels, out_channels=self.key_channels, kernel_size=1, stride=1, padding=0,
bias=False),
nn.BatchNorm2d(self.key_channels),
nn.ReLU(inplace=True)
)
self.f_up = nn.Sequential(
nn.Conv2d(in_channels=self.key_channels, out_channels=self.in_channels, kernel_size=1, stride=1, padding=0,
bias=False),
nn.BatchNorm2d(self.key_channels),
nn.ReLU(inplace=True)
)
def __init__(self):
super(CNNNet, self).__init__()
self.cnn_layer = nn.Sequential(nn.Conv2d(in_channels=1))
self.fc_layer = nn.Sequential()
def __init__(self):
nn.Module.__init__(self)
self.cn1 = nn.Conv2d(3, 3, kernel_size=3, stride=1)
self.mp1 = nn.MaxPool2d(kernel_size=2,
stride=2,
return_indices=True)
def __init__(self):
nn.Module.__init__(self)
self.cn1 = nn.Conv2d(3, 3, kernel_size=3, stride=1)
self.mp1 = nn.Conv2d(3, 3, kernel_size=2, stride=2)
def __init__(self, num_class=10):
super(VGG16, self).__init__()
self.feature = modules.Sequential(
# #1,
modules.Conv2d(3, 64, kernel_size=3, padding=1),
modules.BatchNorm2d(64),
modules.ReLU(True),
#2
modules.Conv2d(64, 64, kernel_size=3, padding=1),
modules.BatchNorm2d(64),
modules.ReLU(True),
modules.MaxPool2d(kernel_size=2, stride=2),
#3
modules.Conv2d(64, 128, kernel_size=3, padding=1),
modules.BatchNorm2d(128),
modules.ReLU(True),
# modules.MaxPool2d(kernel_size=2,stride=2),
#4
modules.Conv2d(128, 128, kernel_size=3, padding=1),
modules.BatchNorm2d(128),
modules.ReLU(True),
modules.MaxPool2d(kernel_size=2, stride=2),
#5
modules.Conv2d(128, 256, kernel_size=3, padding=1),
modules.BatchNorm2d(256),
modules.ReLU(True),
#6
modules.Conv2d(256, 256, kernel_size=3, padding=1),
modules.BatchNorm2d(256),
modules.ReLU(True),
#7
modules.Conv2d(256, 256, kernel_size=3, padding=1),
modules.BatchNorm2d(256),
modules.ReLU(True),
modules.MaxPool2d(kernel_size=2, stride=2),
#8
modules.Conv2d(256, 512, kernel_size=3, padding=1),
modules.BatchNorm2d(512),
modules.ReLU(True),
#9
modules.Conv2d(512, 512, kernel_size=3, padding=1),
modules.BatchNorm2d(512),
modules.ReLU(True),
#10
modules.Conv2d(512, 512, kernel_size=3, padding=1),
modules.BatchNorm2d(512),
modules.ReLU(True),
modules.MaxPool2d(kernel_size=2, stride=2),
#11
modules.Conv2d(512, 512, kernel_size=3, padding=1),
modules.BatchNorm2d(512),
modules.ReLU(True),
#12
modules.Conv2d(512, 512, kernel_size=3, padding=1),
modules.BatchNorm2d(512),
modules.ReLU(True),
#13
modules.Conv2d(512, 512, kernel_size=3, padding=1),
modules.BatchNorm2d(512),
modules.ReLU(True),
modules.MaxPool2d(kernel_size=2, stride=2),
modules.AvgPool2d(kernel_size=1, stride=1),
)
# 全连接层
self.classifier = modules.Sequential(
# #14
modules.Linear(512, 4096),
modules.ReLU(True),
modules.Dropout(),
#15
modules.Linear(4096, 4096),
modules.ReLU(True),
modules.Dropout(),
#16
modules.Linear(4096, num_class),
)
x_out = self.spatial(x_compress)
scale = torch.sigmoid(x_out)
# broadcasting [None, chn, 2048] * [None, 1, 2048]=>[None, chn, 2048]
return x * scale
class CBAM(nn.Module):
def __init__(self, gate_channels, reduction_ratio=16):
super(CBAM, self).__init__()
self.ChannelGate = ChannelGate(gate_channels, reduction_ratio)
self.SpatialGate = SpatialGate()
def forward(self, x):
"""
:param x: [None, chn, 2048]
:return: [None, chn, 2048]
"""
x_out = self.ChannelGate(x) # [None, chn, 2048]
x_out = self.SpatialGate(x_out)
return x_out
if __name__ == '__main__':
pass
l1 = nn.Conv2d(10, 12, kernel_size=2)
l2 = nn.AdaptiveAvgPool1d(1)
for name, parameter in l2.named_parameters():
print(name, ':', parameter.size())
# print(l1.parameters().shape)
# print(l1.named_parameters())
