GoogleNet的inception
发布时间
阅读量：
阅读量
V3版本由于其较高的计算负担，在采用了多个Inception模块的情况下运行得较为吃力。这些模块主要包括非对称卷积层、卷积与池化融合层以及轻量化设计层。通过非对称卷积替代传统的大尺寸卷积操作，在保持相同感受野的基础上显著降低了计算开销；此外还引入了卷积池化融合机制，在减少大量运算的同时保证了网络性能不受明显影响；在轻量化设计方面，则采用步长等于2代替池化操作，并通过1x1的小核卷积组合实现特征融合功能以达到与传统大核卷积相近的效果
lass Inception3(nn.Module):
def __init__(self, num_classes=1000, aux_logits=True, transform_input=False,
inception_blocks=None, init_weights=None):
super(Inception3, self).__init__()
if inception_blocks is None:
inception_blocks = [
BasicConv2d, InceptionA, InceptionB, InceptionC,
InceptionD, InceptionE, InceptionAux
]
if init_weights is None:
warnings.warn('The default weight initialization of inception_v3 will be changed in future releases of '
'torchvision. If you wish to keep the old behavior (which leads to long initialization times'
' due to scipy/scipy#11299), please set init_weights=True.', FutureWarning)
init_weights = True
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.maxpool1 = nn.MaxPool2d(kernel_size=3, stride=2)
self.Conv2d_3b_1x1 = conv_block(64, 80, kernel_size=1)
self.Conv2d_4a_3x3 = conv_block(80, 192, kernel_size=3)
self.maxpool2 = nn.MaxPool2d(kernel_size=3, stride=2)
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.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.dropout = nn.Dropout()
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 = self.maxpool1(x)
# 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 = self.maxpool2(x)
# 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 = self.avgpool(x)
# N x 2048 x 1 x 1
x = self.dropout(x)
# 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: torch.Tensor, aux: Optional[Tensor]) -> InceptionOutputs:
if self.training and self.aux_logits:
return InceptionOutputs(x, aux)
else:
return x # type: ignore[return-value]
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)采用两个3\times 3卷积去替代单个5\times 5卷积，在保证同样宽广的感受野范围内整体表现更加优异，并通过多层级卷积的融合处理进一步提升了整体性能
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)一种降低分辨率的方法主要通过池化操作以及增加跳跃性来实现对特征图空间分辨率的降低。与传统仅通过直接池化来降低特征图分辨率相比这一方法在保留更多细节信息的同时能够更有效地平衡计算效率与模型性能之间的关系其核心思路本质上是将空间分辨率减半从而达到压缩特征维度的目的
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)这种就是利用1xn和nx1不断的卷积，计算量会小很多
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)基于类似原理, 这种途径能够有效利用高维信息, 进一步保障特征, 值得探讨, 具有参考价值
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)全部评论 (0)
还没有任何评论哟~