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, in_planes=None, planes=None, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(in_planes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu1 = nn.ReLU()
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
self.relu2 = nn.ReLU(inplace=True)
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 __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, model_name, input_size, hidden_size, batch_size, kernel_size,
out_channels, num_layers=1, dropout=0, bidirectional=False, bn=False):
super(LACModelUnit, self).__init__()
# 获得GPU数量
self.cuda_ids = np.arange(torch.cuda.device_count())
self.model_name = model_name
self.input_size = input_size
self.hidden_size = hidden_size
self.batch_size = int(batch_size / len(self.cuda_ids))
self.out_channels = out_channels
self.kernel_size = kernel_size
self.num_layers = num_layers
self.dropout = dropout
self.bidirectional = bidirectional
self.bn = bn
# 创建LSTM
self.rnn = modules.LSTM(self.input_size, self.hidden_size, self.num_layers,
batch_first=True, bidirectional=self.bidirectional)
# LSTM激活函数
self.rnn_act = modules.ReLU()
# 创建1D-CNN
self.cnn = modules.Conv1d(1, self.out_channels, self.kernel_size)
# BN层
self.bn = modules.BatchNorm1d(self.out_channels)
# 1D-CNN激活函数
self.cnn_act = modules.Tanh()
# Dropout层
self.drop = modules.Dropout(dropout)
# 初始化LSTM参数
self.lstm_hidden, self.lstm_cell = self.init_hidden_cell(self.batch_size)
def __init__(self,
n_inputs,
n_outputs,
kernel_size,
stride,
dilation,
padding,
dropout=0.2):
super(TemporalBlock, self).__init__()
# 定义残差模块的第一层扩张卷积
# 经过conv，输出的size为(Batch, input_channel, seq_len + padding)，并归一化模型的参数
self.conv1 = weight_norm(
modules.Conv1d(n_inputs,
n_outputs,
kernel_size,
stride=stride,
padding=padding,
dilation=dilation))
# 裁剪掉多出来的padding部分，维持输出时间步为seq_len
self.chomp1 = Chomp1d(padding)
self.relu1 = modules.ReLU()
self.dropout1 = modules.Dropout(dropout)
#定义残差模块的第二层扩张卷积
self.conv2 = weight_norm(
modules.Conv1d(n_outputs,
n_outputs,
kernel_size,
stride=stride,
padding=padding,
dilation=dilation))
self.chomp2 = Chomp1d(padding)
self.relu2 = modules.ReLU()
self.dropout2 = modules.Dropout(dropout)
# 将卷积模块进行串联构成序列
self.net = modules.Sequential(self.conv1, self.chomp1, self.relu1,
self.dropout1, self.conv2, self.chomp2,
self.relu2, self.dropout2)
# 如果输入通道和输出通道不相同，那么通过1x1卷积进行降维，保持通道相同
self.downsample = modules.Conv1d(n_inputs, n_outputs,
1) if n_inputs != n_outputs else None
self.relu = modules.ReLU()
self.init_weights()
def __init__(self, in_planes, reduction=16):
super(SELayer, self).__init__()
# 返回1X1大小的特征图，通道数不变
self.avg_pool = nn.AdaptiveAvgPool1d(1)
self.fc = nn.Sequential(
nn.Linear(in_planes, in_planes // reduction, bias=False),
nn.ReLU(), # inplace = True, 计算值直接覆盖之前的值,最好默认为False,否则报错
nn.Linear(in_planes // reduction, in_planes, bias=False),
nn.Sigmoid())
def conv_block(in_channels, out_channels):
return nn.Sequential(
nn.Conv1d(in_channels,
out_channels,
kernel_size=K_SIZE,
padding=PADDING),
nn.BatchNorm1d(out_channels),
nn.ReLU(),
nn.MaxPool1d(kernel_size=2),
)
def __init__(self, gate_channels, reduction_ratio=16):
super(ChannelGate, self).__init__()
self.gate_channels = gate_channels
self.gap1 = nn.AdaptiveAvgPool1d(output_size=1)
self.gap2 = nn.AdaptiveAvgPool1d(output_size=1)
self.mlp = nn.Sequential(
Flatten(),
nn.Linear(gate_channels, gate_channels // reduction_ratio),
nn.ReLU(),
nn.Linear(gate_channels // reduction_ratio, gate_channels))
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, DIM):
super().__init__()
NUM_BLOCK = 8
FEATURE_CHN = 64
x_dim = int(FEATURE_CHN *
(DIM // 2**NUM_BLOCK)) # 2048:8192; 1024:4096
feature = 256 # 100(original), 64(CW2SQ), 32, 16. choose: 256, 16
# print('The NUM of ConvBlocK: {}'.format(NUM_BLOCK))
print('The FC features: {}\n'.format(feature))
self.create_feat = nn.Linear(x_dim,
feature) # weight shape: (feature, x_dim)
self.discriminator = nn.Sequential(nn.BatchNorm1d(feature), nn.ReLU(),
nn.Linear(feature, 2))
def __init__(self, in_channels, out_channels, stride=1, M=2, r=16, L=32):
"""
:param in_channels: 输入通道维度
:param out_channels: 输出通道维度 原论文中 输入输出通道维度相同
:param stride: 步长，默认为1
:param M: 分支数
:param r: 特征Z的长度，计算其维度d 时所需的比率（论文中 特征S->Z 是降维，故需要规定 降维的下界）
:param L: 论文中规定特征Z的下界，默认为32
"""
super(SK_Conv1d, self).__init__()
d = max(in_channels // r, L) # 计算向量Z 的长度d
self.M = M
self.out_channels = out_channels
self.conv = nn.ModuleList() # 根据分支数量 添加 不同核的卷积操作
for i in range(M):
# 为提高效率，原论文中 扩张卷积5x5为 （3X3，dilation=2）来代替, 且论文中建议组卷积G=32,
# 每组计算只有out_channel/groups = 2 个channel参与.
self.conv.append(
nn.Sequential(
nn.Conv1d(in_channels,
out_channels,
3,
stride,
padding=1 + i,
dilation=1 + i,
groups=32,
bias=False), nn.BatchNorm1d(out_channels),
nn.ReLU(inplace=True)))
self.global_pool = nn.AdaptiveAvgPool1d(
1) # 自适应pool到指定维度, 这里指定为1，实现 GAP
self.fc1 = nn.Sequential(nn.Conv1d(out_channels, d, 1, bias=False),
nn.BatchNorm1d(d),
nn.ReLU(inplace=True)) # 降维
self.fc2 = nn.Conv1d(d, out_channels * M, 1, 1, bias=False) # 升维
# self.fcs = nn.ModuleList(self.fc1, self.fc2)
self.softmax = nn.Softmax(
dim=1) # 指定dim=1 使得两个全连接层对应位置进行softmax,保证 对应位置a+b+..=1
def __init__(self, n_states, n_actions, n_hidden, lr):
super(ActorCritic, self).__init__()
self.input = nn.Linear(n_states, n_hidden)
self.hidden_1 = nn.Linear(n_hidden, n_hidden)
self.hidden_2 = nn.Linear(n_hidden, n_hidden)
self.out_actor_sigma = nn.Linear(n_hidden, n_actions)
self.out_actor_mu = nn.Linear(n_hidden, n_actions)
self.out_critic = nn.Sequential(nn.Linear(n_hidden, n_hidden),
nn.ReLU(), nn.Linear(n_hidden, 1))
#self.bn_1 = nn.BatchNorm1d(n_hidden)
#self.bn_2 = nn.BatchNorm1d(n_hidden)
self.optimizer = optim.SGD(self.parameters(), lr=lr)
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 __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):
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, 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_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, 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, input_num, hidden_num, output_num):
super(Net, self).__init__()
self.seq = nm.Sequential(nm.Linear(input_num, hidden_num), nm.ReLU(),
nm.Linear(hidden_num, output_num))
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),
)
