2015年由google团队提出,论文地址Batch Normalization: Accelerating Deep Network Training b y Reducing Internal Covariate Shift, Rethinking the Inception Architecture for Computer Vision
问题:representatial bottleneck,特征描述瓶颈是指中间某层对特征空间维度进行较大比例的压缩(比如使用pooling),导致很多特征丢失,虽然pooling是CNN结构中必须的功能,但我们可以通过一些优化方法来减少pooling造成的损失。特征数目越多收敛的越快。
一些特征的结构
1.卷积分解
将5×5的卷积分解成2个3×3的卷积运算以提升计算速度。
在本文中,作者将n×n的卷积核尺寸分解为1×n和n×1两个卷积。
模块中的滤波器组被扩展(变得更宽而不是更深),以解决特征瓶颈。如果该模块没有被扩展宽度,而是变得更深,那么维度会过多减少,造成信息损失。
2.辅助分类器的效用
辅助分类器在训练前期并没有起什么作用,到了训练的后期才开始在精度上超过没有辅助分类器的网络,并达到稍微高的平稳期。并且,在去除这两个辅助分类器后并没有不利的影响,因此在Inception V1中提到的帮助低层网络更快的训练是有问题的。如果这两个分支有BN或Dropout住分类器的效果会更好,这是BN可充当正则化器的一个微弱证据。
3.高效降低Grid Size
有两种方式:(1)先池化再Inception,(2)先Inception再池化
左边特征先减少的话容易造成特征丢失,即bottleneck问题;右边会极大增加计算量
并行操作,一边减小特征图尺寸,一边增加特征图数量
辅助分类器:
pytorch实现
InceptionOutputs = namedtuple('InceptionOutputs', ['logits', 'aux_logits'])
InceptionOutputs.__annotations__ = {'logits': torch.Tensor, 'aux_logits': Optional[torch.Tensor]}
class BasicConv2d(nn.Module):
def __init__(self, in_channels, out_channels, **kwargs):
super(BasicConv2d, self).__init__()
self.conv = nn.Conv2d(in_channels, out_channels, bias=False, **kwargs)
self.bn = nn.BatchNorm2d(out_channels, eps=0.001)
def forward(self, x):
x = self.conv(x)
x = self.bn(x)
return F.relu(x, inplace=True)
class InceptionAux(nn.Module):
def __init__(self, in_channels, num_classes, conv_block=None):
super(InceptionAux, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
self.conv0 = conv_block(in_channels, 128, kernel_size=1)
self.conv1 = conv_block(128, 768, kernel_size=5)
self.conv1.stddev = 0.01
self.fc = nn.Linear(768, num_classes)
self.fc.stddev = 0.001
def forward(self, x):
# N x 768 x 17 x 17
x = F.avg_pool2d(x, kernel_size=5, stride=3)
# N x 768 x 5 x 5
x = self.conv0(x)
# N x 128 x 5 x 5
x = self.conv1(x)
# N x 768 x 1 x 1
# Adaptive average pooling
x = F.adaptive_avg_pool2d(x, (1, 1)) # 输出尺寸大小
# N x 768 x 1 x 1
x = torch.flatten(x, 1)
# N x 768
x = self.fc(x)
# N x 1000
return x
class InceptionA(nn.Module):
def __init__(self, in_channels, pool_features, conv_block=None):
super(InceptionA, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
self.branch1x1 = conv_block(in_channels, 64, kernel_size=1)
self.branch5x5_1 = conv_block(in_channels, 48, kernel_size=1)
self.branch5x5_2 = conv_block(48, 64, kernel_size=5, padding=2)
self.branch3x3dbl_1 = conv_block(in_channels, 64, kernel_size=1)
self.branch3x3dbl_2 = conv_block(64, 96, kernel_size=3, padding=1)
self.branch3x3dbl_3 = conv_block(96, 96, kernel_size=3, padding=1)
self.branch_pool = conv_block(in_channels, pool_features, kernel_size=1)
def _forward(self, x):
branch1x1 = self.branch1x1(x)
branch5x5 = self.branch5x5_1(x)
branch5x5 = self.branch5x5_2(branch5x5)
branch3x3dbl = self.branch3x3dbl_1(x)
branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)
branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
branch_pool = self.branch_pool(branch_pool)
outputs = [branch1x1, branch5x5, branch3x3dbl, branch_pool]
return outputs
def forward(self, x):
outputs = self._forward(x)
return torch.cat(outputs, 1)
class InceptionB(nn.Module):
def __init__(self, in_channels, conv_block=None):
super(InceptionB, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
self.branch3x3 = conv_block(in_channels, 384, kernel_size=3, stride=2)
self.branch3x3dbl_1 = conv_block(in_channels, 64, kernel_size=1)
self.branch3x3dbl_2 = conv_block(64, 96, kernel_size=3, padding=1)
self.branch3x3dbl_3 = conv_block(96, 96, kernel_size=3, stride=2)
def _forward(self, x):
branch3x3 = self.branch3x3(x)
branch3x3dbl = self.branch3x3dbl_1(x)
branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)
branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)
outputs = [branch3x3, branch3x3dbl, branch_pool]
return outputs
def forward(self, x):
outputs = self._forward(x)
return torch.cat(outputs, 1)
class InceptionC(nn.Module):
def __init__(self, in_channels, channels_7x7, conv_block=None):
super(InceptionC, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
self.branch1x1 = conv_block(in_channels, 192, kernel_size=1)
c7 = channels_7x7
self.branch7x7_1 = conv_block(in_channels, c7, kernel_size=1)
self.branch7x7_2 = conv_block(c7, c7, kernel_size=(1, 7), padding=(0, 3))
self.branch7x7_3 = conv_block(c7, 192, kernel_size=(7, 1), padding=(3, 0))
self.branch7x7dbl_1 = conv_block(in_channels, c7, kernel_size=1)
self.branch7x7dbl_2 = conv_block(c7, c7, kernel_size=(7, 1), padding=(3, 0))
self.branch7x7dbl_3 = conv_block(c7, c7, kernel_size=(1, 7), padding=(0, 3))
self.branch7x7dbl_4 = conv_block(c7, c7, kernel_size=(7, 1), padding=(3, 0))
self.branch7x7dbl_5 = conv_block(c7, 192, kernel_size=(1, 7), padding=(0, 3))
self.branch_pool = conv_block(in_channels, 192, kernel_size=1)
def _forward(self, x):
branch1x1 = self.branch1x1(x)
branch7x7 = self.branch7x7_1(x)
branch7x7 = self.branch7x7_2(branch7x7)
branch7x7 = self.branch7x7_3(branch7x7)
branch7x7dbl = self.branch7x7dbl_1(x)
branch7x7dbl = self.branch7x7dbl_2(branch7x7dbl)
branch7x7dbl = self.branch7x7dbl_3(branch7x7dbl)
branch7x7dbl = self.branch7x7dbl_4(branch7x7dbl)
branch7x7dbl = self.branch7x7dbl_5(branch7x7dbl)
branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
branch_pool = self.branch_pool(branch_pool)
outputs = [branch1x1, branch7x7, branch7x7dbl, branch_pool]
return outputs
def forward(self, x):
outputs = self._forward(x)
return torch.cat(outputs, 1)
class InceptionD(nn.Module):
def __init__(self, in_channels, conv_block=None):
super(InceptionD, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
self.branch3x3_1 = conv_block(in_channels, 192, kernel_size=1)
self.branch3x3_2 = conv_block(192, 320, kernel_size=3, stride=2)
self.branch7x7x3_1 = conv_block(in_channels, 192, kernel_size=1)
self.branch7x7x3_2 = conv_block(192, 192, kernel_size=(1, 7), padding=(0, 3))
self.branch7x7x3_3 = conv_block(192, 192, kernel_size=(7, 1), padding=(3, 0))
self.branch7x7x3_4 = conv_block(192, 192, kernel_size=3, stride=2)
def _forward(self, x):
branch3x3 = self.branch3x3_1(x)
branch3x3 = self.branch3x3_2(branch3x3)
branch7x7x3 = self.branch7x7x3_1(x)
branch7x7x3 = self.branch7x7x3_2(branch7x7x3)
branch7x7x3 = self.branch7x7x3_3(branch7x7x3)
branch7x7x3 = self.branch7x7x3_4(branch7x7x3)
branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)
outputs = [branch3x3, branch7x7x3, branch_pool]
return outputs
def forward(self, x):
outputs = self._forward(x)
return torch.cat(outputs, 1)
class InceptionE(nn.Module):
def __init__(self, in_channels, conv_block=None):
super(InceptionE, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
self.branch1x1 = conv_block(in_channels, 320, kernel_size=1)
self.branch3x3_1 = conv_block(in_channels, 384, kernel_size=1)
self.branch3x3_2a = conv_block(384, 384, kernel_size=(1, 3), padding=(0, 1))
self.branch3x3_2b = conv_block(384, 384, kernel_size=(3, 1), padding=(1, 0))
self.branch3x3dbl_1 = conv_block(in_channels, 448, kernel_size=1)
self.branch3x3dbl_2 = conv_block(448, 384, kernel_size=3, padding=1)
self.branch3x3dbl_3a = conv_block(384, 384, kernel_size=(1, 3), padding=(0, 1))
self.branch3x3dbl_3b = conv_block(384, 384, kernel_size=(3, 1), padding=(1, 0))
self.branch_pool = conv_block(in_channels, 192, kernel_size=1)
def _forward(self, x):
branch1x1 = self.branch1x1(x)
branch3x3 = self.branch3x3_1(x)
branch3x3 = [
self.branch3x3_2a(branch3x3),
self.branch3x3_2b(branch3x3),
]
branch3x3 = torch.cat(branch3x3, 1)
branch3x3dbl = self.branch3x3dbl_1(x)
branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
branch3x3dbl = [
self.branch3x3dbl_3a(branch3x3dbl),
self.branch3x3dbl_3b(branch3x3dbl),
]
branch3x3dbl = torch.cat(branch3x3dbl, 1)
branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
branch_pool = self.branch_pool(branch_pool)
outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool]
return outputs
def forward(self, x):
outputs = self._forward(x)
return torch.cat(outputs, 1)
class Inception3(nn.Module):
def __init__(self, num_classes=1000, aux_logits=True, transform_input=False,
inception_blocks=None, init_weights=True):
super(Inception3, self).__init__()
if inception_blocks is None:
inception_blocks = [
BasicConv2d, InceptionA, InceptionB, InceptionC,
InceptionD, InceptionE, InceptionAux
]
assert len(inception_blocks) == 7
conv_block = inception_blocks[0]
inception_a = inception_blocks[1]
inception_b = inception_blocks[2]
inception_c = inception_blocks[3]
inception_d = inception_blocks[4]
inception_e = inception_blocks[5]
inception_aux = inception_blocks[6]
self.aux_logits = aux_logits
self.transform_input = transform_input
self.Conv2d_1a_3x3 = conv_block(3, 32, kernel_size=3, stride=2)
self.Conv2d_2a_3x3 = conv_block(32, 32, kernel_size=3)
self.Conv2d_2b_3x3 = conv_block(32, 64, kernel_size=3, padding=1)
self.Conv2d_3b_1x1 = conv_block(64, 80, kernel_size=1)
self.Conv2d_4a_3x3 = conv_block(80, 192, kernel_size=3)
self.Mixed_5b = inception_a(192, pool_features=32)
self.Mixed_5c = inception_a(256, pool_features=64)
self.Mixed_5d = inception_a(288, pool_features=64)
self.Mixed_6a = inception_b(288)
self.Mixed_6b = inception_c(768, channels_7x7=128)
self.Mixed_6c = inception_c(768, channels_7x7=160)
self.Mixed_6d = inception_c(768, channels_7x7=160)
self.Mixed_6e = inception_c(768, channels_7x7=192)
if aux_logits:
self.AuxLogits = inception_aux(768, num_classes)
self.Mixed_7a = inception_d(768)
self.Mixed_7b = inception_e(1280)
self.Mixed_7c = inception_e(2048)
self.fc = nn.Linear(2048, num_classes)
if init_weights:
for m in self.modules():
if isinstance(m, nn.Conv2d) or isinstance(m, nn.Linear):
import scipy.stats as stats
stddev = m.stddev if hasattr(m, 'stddev') else 0.1
X = stats.truncnorm(-2, 2, scale=stddev)
values = torch.as_tensor(X.rvs(m.weight.numel()), dtype=m.weight.dtype)
values = values.view(m.weight.size())
with torch.no_grad():
m.weight.copy_(values)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def _transform_input(self, x):
if self.transform_input:
x_ch0 = torch.unsqueeze(x[:, 0], 1) * (0.229 / 0.5) + (0.485 - 0.5) / 0.5
x_ch1 = torch.unsqueeze(x[:, 1], 1) * (0.224 / 0.5) + (0.456 - 0.5) / 0.5
x_ch2 = torch.unsqueeze(x[:, 2], 1) * (0.225 / 0.5) + (0.406 - 0.5) / 0.5
x = torch.cat((x_ch0, x_ch1, x_ch2), 1)
return x
def _forward(self, x):
# N x 3 x 299 x 299
x = self.Conv2d_1a_3x3(x)
# N x 32 x 149 x 149
x = self.Conv2d_2a_3x3(x)
# N x 32 x 147 x 147
x = self.Conv2d_2b_3x3(x)
# N x 64 x 147 x 147
x = F.max_pool2d(x, kernel_size=3, stride=2)
# N x 64 x 73 x 73
x = self.Conv2d_3b_1x1(x)
# N x 80 x 73 x 73
x = self.Conv2d_4a_3x3(x)
# N x 192 x 71 x 71
x = F.max_pool2d(x, kernel_size=3, stride=2)
# N x 192 x 35 x 35
x = self.Mixed_5b(x)
# N x 256 x 35 x 35
x = self.Mixed_5c(x)
# N x 288 x 35 x 35
x = self.Mixed_5d(x)
# N x 288 x 35 x 35
x = self.Mixed_6a(x)
# N x 768 x 17 x 17
x = self.Mixed_6b(x)
# N x 768 x 17 x 17
x = self.Mixed_6c(x)
# N x 768 x 17 x 17
x = self.Mixed_6d(x)
# N x 768 x 17 x 17
x = self.Mixed_6e(x)
# N x 768 x 17 x 17
aux_defined = self.training and self.aux_logits
if aux_defined:
aux = self.AuxLogits(x)
else:
aux = None
# N x 768 x 17 x 17
x = self.Mixed_7a(x)
# N x 1280 x 8 x 8
x = self.Mixed_7b(x)
# N x 2048 x 8 x 8
x = self.Mixed_7c(x)
# N x 2048 x 8 x 8
# Adaptive average pooling
x = F.adaptive_avg_pool2d(x, (1, 1))
# N x 2048 x 1 x 1
x = F.dropout(x, training=self.training)
# N x 2048 x 1 x 1
x = torch.flatten(x, 1)
# N x 2048
x = self.fc(x)
# N x 1000 (num_classes)
return x, aux
@torch.jit.unused
def eager_outputs(self, x, aux):
# type: (Tensor, Optional[Tensor]) -> InceptionOutputs
if self.training and self.aux_logits:
return InceptionOutputs(x, aux)
else:
return x
def forward(self, x):
x = self._transform_input(x)
x, aux = self._forward(x)
aux_defined = self.training and self.aux_logits
if torch.jit.is_scripting():
if not aux_defined:
warnings.warn("Scripted Inception3 always returns Inception3 Tuple")
return InceptionOutputs(x, aux)
else:
return self.eager_outputs(x, aux)
Inception模块