mmclassification backbone01-AlexNet

AlexNet是直筒结构。

(1) 参数num_classes=-1，则用作backbone，该backbone有3个conv+relu+maxPooling，中间2个conv+relu，共含5个卷积组成。

(2) 参数num_classes>0，则用作分类网络，前面的5层卷积后，先view，再接分类器，该分类器由2个dropout+linear+relu、1个linear输出层，共含3个全连接层组成。

@BACKBONES.register_module()
class AlexNet(BaseBackbone):
    """`AlexNet <https://en.wikipedia.org/wiki/AlexNet>`_ backbone.

    The input for AlexNet is a 224x224 RGB image.

    Args:
        num_classes (int): number of classes for classification.
            The default value is -1, which uses the backbone as
            a feature extractor without the top classifier.
    """

    def __init__(self, num_classes=-1):
        super(AlexNet, self).__init__()
        self.num_classes = num_classes
        self.features = nn.Sequential(
            # 3个conv+relu+maxPool，中间有2个conv+relu
            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),

            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),

            nn.Conv2d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),

            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        if self.num_classes > 0:
            self.classifier = nn.Sequential(
                nn.Dropout(),
                nn.Linear(256 * 6 * 6, 4096),
                nn.ReLU(inplace=True),

                nn.Dropout(),
                nn.Linear(4096, 4096),
                nn.ReLU(inplace=True),

                nn.Linear(4096, num_classes),
            )

    def forward(self, x):
        """5个卷积层、view、3个全连接层"""
        x = self.features(x)  # Only for backbone
        if self.num_classes > 0:  # for classification. 224*224 images.
            x = x.view(x.size(0), 256 * 6 * 6)
            x = self.classifier(x)

        return x