def __init__(self,output_dim=6, dropout=False): super(ResidualAttentionModel_92_Small, self).__init__() self.conv1 = nn.Sequential( nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias = False), nn.BatchNorm2d(64), nn.ReLU(inplace=True) ) self.dropout = dropout self.mpool1 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.ResidualBlock1 = ResidualBlock(64, 256) if self.dropout: self.dp_1 = nn.Dropout(0.2) self.dp_2 = nn.Dropout(0.0) self.dp_3 = nn.Dropout(0.0) self.attention_module1 = AttentionModule_stage1(256, 256) self.ResidualBlock2 = ResidualBlock(256, 512, 2) self.attention_module2 = AttentionModule_stage2(512, 512) self.attention_module2_2 = AttentionModule_stage2(512, 512) # tbq add self.ResidualBlock3 = ResidualBlock(512, 1024, 3) self.mpool2 = nn.Sequential( nn.BatchNorm2d(1024), nn.ReLU(inplace=True), nn.AvgPool2d(kernel_size=8, stride=3) ) self.fc = nn.Linear(1024,output_dim) #self.softmax = nn.Softmax(dim=1) for m in self.children(): if isinstance(m, nn.Conv2d): nn.init.xavier_uniform_(m.weight.data) nn.init.xavier_uniforml_(m.bias.data)
def __init__(self, in_channels, out_channels, size1=(28, 28), size2=(14, 14)): super(AttentionModule_stage2, self).__init__() self.first_ResidualBlocks = ResidualBlock(in_channels, out_channels) self.trunk_branches = nn.Sequential( ResidualBlock(in_channels, out_channels), ResidualBlock(in_channels, out_channels)) self.mpool1 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.softmax1_blocks = ResidualBlock(in_channels, out_channels) self.skip1_connection_ResidualBlock = ResidualBlock( in_channels, out_channels) self.mpool2 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.softmax2_blocks = nn.Sequential( ResidualBlock(in_channels, out_channels), ResidualBlock(in_channels, out_channels)) self.interpolation2 = nn.UpsamplingBilinear2d(size=size2) self.softmax3_blocks = ResidualBlock(in_channels, out_channels) self.interpolation1 = nn.UpsamplingBilinear2d(size=size1) self.softmax4_blocks = nn.Sequential( nn.BatchNorm2d(out_channels), nn.ReLU(inplace=True), nn.Conv2d(out_channels, out_channels, kernel_size=1, stride=1, bias=False), nn.BatchNorm2d(out_channels), nn.ReLU(inplace=True), nn.Conv2d(out_channels, out_channels, kernel_size=1, stride=1, bias=False), nn.Sigmoid()) self.last_blocks = ResidualBlock(in_channels, out_channels)
def __init__(self, in_channels, out_channels, size=(8, 8)): super(AttentionModule_stage3_cifar, self).__init__() self.first_ResidualBlocks = ResidualBlock(in_channels, out_channels) self.trunk_branches = nn.Sequential( ResidualBlock(in_channels, out_channels), ResidualBlock(in_channels, out_channels)) self.middle_2r_blocks = nn.Sequential( ResidualBlock(in_channels, out_channels), ResidualBlock(in_channels, out_channels)) self.conv1_1_blocks = nn.Sequential( nn.BatchNorm2d(out_channels), nn.ReLU(inplace=True), nn.Conv2d(out_channels, out_channels, kernel_size=1, stride=1, bias=False), nn.BatchNorm2d(out_channels), nn.ReLU(inplace=True), nn.Conv2d(out_channels, out_channels, kernel_size=1, stride=1, bias=False), nn.Sigmoid()) self.last_blocks = ResidualBlock(in_channels, out_channels)
def __init__(self, in_channels, out_channels, size=(8, 8)): super(AttentionModule_stage2_cifar, self).__init__() self.first_ResidualBlocks = ResidualBlock(in_channels, out_channels) self.trunk_branches = nn.Sequential( ResidualBlock(in_channels, out_channels), ResidualBlock(in_channels, out_channels)) self.mpool1 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) # 4*4 self.middle_2r_blocks = nn.Sequential( ResidualBlock(in_channels, out_channels), ResidualBlock(in_channels, out_channels)) self.interpolation1 = nn.UpsamplingBilinear2d(size=size) # 8*8 self.conv1_1_blocks = nn.Sequential( nn.BatchNorm2d(out_channels), nn.ReLU(inplace=True), nn.Conv2d(out_channels, out_channels, kernel_size=1, stride=1, bias=False), nn.BatchNorm2d(out_channels), nn.ReLU(inplace=True), nn.Conv2d(out_channels, out_channels, kernel_size=1, stride=1, bias=False), nn.Sigmoid()) self.last_blocks = ResidualBlock(in_channels, out_channels)
def __init__(self, output_dim): super(ResidualAttentionModel_92_32input_update, self).__init__() self.conv1 = nn.Sequential( nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1, bias=False), nn.BatchNorm2d(32), nn.ReLU(inplace=True) ) # 32*32 # self.mpool1 = nn.MaxPool2d(kernel_size=2, stride=2, padding=0) # 16*16 self.ResidualBlock1 = ResidualBlock(32, 128) # 32*32 self.attention_module1 = AttentionModule_stage1_cifar(128, 128, size1=(32, 32), size2=(16, 16)) # 32*32 self.ResidualBlock2 = ResidualBlock(128, 256, 2) # 16*16 self.attention_module2 = AttentionModule_stage2_cifar(256, 256, size=(16, 16)) # 16*16 self.attention_module2_2 = AttentionModule_stage2_cifar(256, 256, size=(16, 16)) # 16*16 # tbq add self.ResidualBlock3 = ResidualBlock(256, 512, 2) # 4*4 self.attention_module3 = AttentionModule_stage3_cifar(512, 512) # 8*8 self.attention_module3_2 = AttentionModule_stage3_cifar(512, 512) # 8*8 # tbq add self.attention_module3_3 = AttentionModule_stage3_cifar(512, 512) # 8*8 # tbq add self.ResidualBlock4 = ResidualBlock(512, 1024) # 8*8 self.ResidualBlock5 = ResidualBlock(1024, 1024) # 8*8 self.ResidualBlock6 = ResidualBlock(1024, 1024) # 8*8 self.mpool2 = nn.Sequential( nn.BatchNorm2d(1024), nn.ReLU(inplace=True), nn.AvgPool2d(kernel_size=8) ) self.fc = nn.Linear(1024, output_dim)