pytorch模型之Inception V3

02-10

在遷移學習中，我們需要對預訓練的模型進行fine-tune，而pytorch已經為我們提供了alexnet、densenet、inception、resnet、squeezenet、vgg的權重，這些模型會隨torch而一同下載（Ubuntu的用戶在torchvision/models目錄下，Windows的用戶在Anaconda3Libsite-packages orchvisionmodels目錄下）。

這次我們先來看下Inception V3。

寫在前面：論文的表格只是inception v2的結構（感謝 @郭翀在評論區指出錯誤）。文章的最後列出了inception v3的結構。

pytorch提供的有六種基本的inception模塊，分別是InceptionA——InceptionE。

InceptionA

結構：

代碼：

class InceptionA(nn.Module): def __init__(self, in_channels, pool_features): super(InceptionA, self).__init__() self.branch1x1 = BasicConv2d(in_channels, 64, kernel_size=1) # 1 self.branch5x5_1 = BasicConv2d(in_channels, 48, kernel_size=1) self.branch5x5_2 = BasicConv2d(48, 64, kernel_size=5, padding=2) self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1) self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1) self.branch3x3dbl_3 = BasicConv2d(96, 96, kernel_size=3, padding=1) self.branch_pool = BasicConv2d(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 torch.cat(outputs, 1)

筆者注：BasicConv2d是這裡定義的基本結構：Conv2D-->BN，下同。

InceptionB

結構：

代碼：

class InceptionB(nn.Module): def __init__(self, in_channels): super(InceptionB, self).__init__() self.branch3x3 = BasicConv2d(in_channels, 384, kernel_size=3, stride=2) self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1) self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1) self.branch3x3dbl_3 = BasicConv2d(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 torch.cat(outputs, 1)

InceptionC

結構：

代碼：

class InceptionC(nn.Module): def __init__(self, in_channels, channels_7x7): super(InceptionC, self).__init__() self.branch1x1 = BasicConv2d(in_channels, 192, kernel_size=1) c7 = channels_7x7 self.branch7x7_1 = BasicConv2d(in_channels, c7, kernel_size=1) self.branch7x7_2 = BasicConv2d(c7, c7, kernel_size=(1, 7), padding=(0, 3)) self.branch7x7_3 = BasicConv2d(c7, 192, kernel_size=(7, 1), padding=(3, 0)) self.branch7x7dbl_1 = BasicConv2d(in_channels, c7, kernel_size=1) self.branch7x7dbl_2 = BasicConv2d(c7, c7, kernel_size=(7, 1), padding=(3, 0)) self.branch7x7dbl_3 = BasicConv2d(c7, c7, kernel_size=(1, 7), padding=(0, 3)) self.branch7x7dbl_4 = BasicConv2d(c7, c7, kernel_size=(7, 1), padding=(3, 0)) self.branch7x7dbl_5 = BasicConv2d(c7, 192, kernel_size=(1, 7), padding=(0, 3)) self.branch_pool = BasicConv2d(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 torch.cat(outputs, 1)

InceptionD

結構：

代碼：

class InceptionD(nn.Module): def __init__(self, in_channels): super(InceptionD, self).__init__() self.branch3x3_1 = BasicConv2d(in_channels, 192, kernel_size=1) self.branch3x3_2 = BasicConv2d(192, 320, kernel_size=3, stride=2) self.branch7x7x3_1 = BasicConv2d(in_channels, 192, kernel_size=1) self.branch7x7x3_2 = BasicConv2d(192, 192, kernel_size=(1, 7), padding=(0, 3)) self.branch7x7x3_3 = BasicConv2d(192, 192, kernel_size=(7, 1), padding=(3, 0)) self.branch7x7x3_4 = BasicConv2d(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 torch.cat(outputs, 1)

InceptionE

結構：

代碼：

class InceptionE(nn.Module): def __init__(self, in_channels): super(InceptionE, self).__init__() self.branch1x1 = BasicConv2d(in_channels, 320, kernel_size=1) self.branch3x3_1 = BasicConv2d(in_channels, 384, kernel_size=1) self.branch3x3_2a = BasicConv2d(384, 384, kernel_size=(1, 3), padding=(0, 1)) self.branch3x3_2b = BasicConv2d(384, 384, kernel_size=(3, 1), padding=(1, 0)) self.branch3x3dbl_1 = BasicConv2d(in_channels, 448, kernel_size=1) self.branch3x3dbl_2 = BasicConv2d(448, 384, kernel_size=3, padding=1) self.branch3x3dbl_3a = BasicConv2d(384, 384, kernel_size=(1, 3), padding=(0, 1)) self.branch3x3dbl_3b = BasicConv2d(384, 384, kernel_size=(3, 1), padding=(1, 0)) self.branch_pool = BasicConv2d(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 torch.cat(outputs, 1)

Utility of Auxiliary Classifiers

在GoogLeNet中，作者認為中間層的特徵將有利於提高最終層的判斷力，所以在模型的中間層使用了輔助分類器。

結構：Pool——>1x1Conv——>5x5Conv——>FC

代碼:

class InceptionAux(nn.Module): def __init__(self, in_channels, num_classes): super(InceptionAux, self).__init__() self.conv0 = BasicConv2d(in_channels, 128, kernel_size=1) self.conv1 = BasicConv2d(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): # 17 x 17 x 768 x = F.avg_pool2d(x, kernel_size=5, stride=3) # 5 x 5 x 768 x = self.conv0(x) # 5 x 5 x 128 x = self.conv1(x) # 1 x 1 x 768 x = x.view(x.size(0), -1) # 768 x = self.fc(x) # 1000 return x

這樣，就可以實現InceptionV3的完整代碼：

def inception_v3(pretrained=False, **kwargs): r"""Inception v3 model architecture from `"Rethinking the Inception Architecture for Computer Vision" <http://arxiv.org/abs/1512.00567>`_. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet """ if pretrained: if transform_input not in kwargs: kwargs[transform_input] = True model = Inception3(**kwargs) model.load_state_dict(model_zoo.load_url(model_urls[inception_v3_google])) return model return Inception3(**kwargs)class Inception3(nn.Module): def __init__(self, num_classes=1000, aux_logits=True, transform_input=False): super(Inception3, self).__init__() self.aux_logits = aux_logits self.transform_input = transform_input self.Conv2d_1a_3x3 = BasicConv2d(3, 32, kernel_size=3, stride=2) self.Conv2d_2a_3x3 = BasicConv2d(32, 32, kernel_size=3) self.Conv2d_2b_3x3 = BasicConv2d(32, 64, kernel_size=3, padding=1) self.Conv2d_3b_1x1 = BasicConv2d(64, 80, kernel_size=1) self.Conv2d_4a_3x3 = BasicConv2d(80, 192, kernel_size=3) self.Mixed_5b = InceptionA(192, pool_features=32) self.Mixed_5c = InceptionA(256, pool_features=64) self.Mixed_5d = InceptionA(288, pool_features=64) self.Mixed_6a = InceptionB(288) self.Mixed_6b = InceptionC(768, channels_7x7=128) self.Mixed_6c = InceptionC(768, channels_7x7=160) self.Mixed_6d = InceptionC(768, channels_7x7=160) self.Mixed_6e = InceptionC(768, channels_7x7=192) if aux_logits: self.AuxLogits = InceptionAux(768, num_classes) self.Mixed_7a = InceptionD(768) self.Mixed_7b = InceptionE(1280) self.Mixed_7c = InceptionE(2048) self.fc = nn.Linear(2048, num_classes) 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.Tensor(X.rvs(m.weight.data.numel())) m.weight.data.copy_(values) elif isinstance(m, nn.BatchNorm2d): m.weight.data.fill_(1) m.bias.data.zero_() def forward(self, x): if self.transform_input: # 1 x = x.clone() x[:, 0] = x[:, 0] * (0.229 / 0.5) + (0.485 - 0.5) / 0.5 x[:, 1] = x[:, 1] * (0.224 / 0.5) + (0.456 - 0.5) / 0.5 x[:, 2] = x[:, 2] * (0.225 / 0.5) + (0.406 - 0.5) / 0.5 # 299 x 299 x 3 x = self.Conv2d_1a_3x3(x) # 149 x 149 x 32 x = self.Conv2d_2a_3x3(x) # 147 x 147 x 32 x = self.Conv2d_2b_3x3(x) # 147 x 147 x 64 x = F.max_pool2d(x, kernel_size=3, stride=2) # 73 x 73 x 64 x = self.Conv2d_3b_1x1(x) # 73 x 73 x 80 x = self.Conv2d_4a_3x3(x) # 71 x 71 x 192 x = F.max_pool2d(x, kernel_size=3, stride=2) # 35 x 35 x 192 x = self.Mixed_5b(x) # 35 x 35 x 256 x = self.Mixed_5c(x) # 35 x 35 x 288 x = self.Mixed_5d(x) # 35 x 35 x 288 x = self.Mixed_6a(x) # 17 x 17 x 768 x = self.Mixed_6b(x) # 17 x 17 x 768 x = self.Mixed_6c(x) # 17 x 17 x 768 x = self.Mixed_6d(x) # 17 x 17 x 768 x = self.Mixed_6e(x) # 17 x 17 x 768 if self.training and self.aux_logits: aux = self.AuxLogits(x) # 17 x 17 x 768 x = self.Mixed_7a(x) # 8 x 8 x 1280 x = self.Mixed_7b(x) # 8 x 8 x 2048 x = self.Mixed_7c(x) # 8 x 8 x 2048 x = F.avg_pool2d(x, kernel_size=8) # 1 x 1 x 2048 x = F.dropout(x, training=self.training) # 1 x 1 x 2048 x = x.view(x.size(0), -1) # 2048 x = self.fc(x) # 1000 (num_classes) if self.training and self.aux_logits: return x, aux return xclass InceptionA(nn.Module): def __init__(self, in_channels, pool_features): super(InceptionA, self).__init__() self.branch1x1 = BasicConv2d(in_channels, 64, kernel_size=1) self.branch5x5_1 = BasicConv2d(in_channels, 48, kernel_size=1) self.branch5x5_2 = BasicConv2d(48, 64, kernel_size=5, padding=2) self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1) self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1) self.branch3x3dbl_3 = BasicConv2d(96, 96, kernel_size=3, padding=1) self.branch_pool = BasicConv2d(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 torch.cat(outputs, 1)class InceptionB(nn.Module): def __init__(self, in_channels): super(InceptionB, self).__init__() self.branch3x3 = BasicConv2d(in_channels, 384, kernel_size=3, stride=2) self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1) self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1) self.branch3x3dbl_3 = BasicConv2d(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 torch.cat(outputs, 1)class InceptionC(nn.Module): def __init__(self, in_channels, channels_7x7): super(InceptionC, self).__init__() self.branch1x1 = BasicConv2d(in_channels, 192, kernel_size=1) c7 = channels_7x7 self.branch7x7_1 = BasicConv2d(in_channels, c7, kernel_size=1) self.branch7x7_2 = BasicConv2d(c7, c7, kernel_size=(1, 7), padding=(0, 3)) self.branch7x7_3 = BasicConv2d(c7, 192, kernel_size=(7, 1), padding=(3, 0)) self.branch7x7dbl_1 = BasicConv2d(in_channels, c7, kernel_size=1) self.branch7x7dbl_2 = BasicConv2d(c7, c7, kernel_size=(7, 1), padding=(3, 0)) self.branch7x7dbl_3 = BasicConv2d(c7, c7, kernel_size=(1, 7), padding=(0, 3)) self.branch7x7dbl_4 = BasicConv2d(c7, c7, kernel_size=(7, 1), padding=(3, 0)) self.branch7x7dbl_5 = BasicConv2d(c7, 192, kernel_size=(1, 7), padding=(0, 3)) self.branch_pool = BasicConv2d(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 torch.cat(outputs, 1)class InceptionD(nn.Module): def __init__(self, in_channels): super(InceptionD, self).__init__() self.branch3x3_1 = BasicConv2d(in_channels, 192, kernel_size=1) self.branch3x3_2 = BasicConv2d(192, 320, kernel_size=3, stride=2) self.branch7x7x3_1 = BasicConv2d(in_channels, 192, kernel_size=1) self.branch7x7x3_2 = BasicConv2d(192, 192, kernel_size=(1, 7), padding=(0, 3)) self.branch7x7x3_3 = BasicConv2d(192, 192, kernel_size=(7, 1), padding=(3, 0)) self.branch7x7x3_4 = BasicConv2d(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 torch.cat(outputs, 1)class InceptionE(nn.Module): def __init__(self, in_channels): super(InceptionE, self).__init__() self.branch1x1 = BasicConv2d(in_channels, 320, kernel_size=1) self.branch3x3_1 = BasicConv2d(in_channels, 384, kernel_size=1) self.branch3x3_2a = BasicConv2d(384, 384, kernel_size=(1, 3), padding=(0, 1)) self.branch3x3_2b = BasicConv2d(384, 384, kernel_size=(3, 1), padding=(1, 0)) self.branch3x3dbl_1 = BasicConv2d(in_channels, 448, kernel_size=1) self.branch3x3dbl_2 = BasicConv2d(448, 384, kernel_size=3, padding=1) self.branch3x3dbl_3a = BasicConv2d(384, 384, kernel_size=(1, 3), padding=(0, 1)) self.branch3x3dbl_3b = BasicConv2d(384, 384, kernel_size=(3, 1), padding=(1, 0)) self.branch_pool = BasicConv2d(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 torch.cat(outputs, 1)class InceptionAux(nn.Module): def __init__(self, in_channels, num_classes): super(InceptionAux, self).__init__() self.conv0 = BasicConv2d(in_channels, 128, kernel_size=1) self.conv1 = BasicConv2d(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): # 17 x 17 x 768 x = F.avg_pool2d(x, kernel_size=5, stride=3) # 5 x 5 x 768 x = self.conv0(x) # 5 x 5 x 128 x = self.conv1(x) # 1 x 1 x 768 x = x.view(x.size(0), -1) # 768 x = self.fc(x) # 1000 return xclass 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)

筆者注：# 1的作用是歸一化。pytorch的inception v3訓練的時候用的均值和標準差為[0.5,0.5,0.5] [0.5,0.5,0.5]。而之前那些CNN模型的歸一化，均值和標準差為[0.229,0.224,0.225] [0.485,0.456,0.406]。所以這行的語句是將後者的歸一化變成前者的歸一化。

（為表示感謝，將Basic Fan的筆記展出）

inception v3結構

（無中間輔助層）