1 AlphaTree

很多论文对算法模型的描述都有自己的风格, 对于我们这些刚入门的小生算是一个大大的挑战, 而我们希望有个大牛能用一种绘图描绘方式统一描述这些模型, 这个希望被深度神经网络(DNN)与对抗神经网络(GAN)模型总览图示实现了. 这个AlphaTree可贵之处是定义了一套图标, 如下:

Conv + Max: .

止于重复造轮子, 详细的算法模式可以直接进入here.

如果图上再标上所使用的激活函数就更美了

1.1 Object Classification

1.1.1 LeNet

论文"Gradient-based learning applied to document recognition"
模型结构(激活函数From Sigmoid to ReLU)

数据变化

see more for details.

1.1.2 AlexNet

论文"Imagenet classification with deep convolutional neural networks"
模型结构(移除LRN层, 激活函数ReLU)
数据变化

see more for details.

参考代码:

class AlexNet(nn.Module):
    def __init__(self, num_classes=1000):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            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),
        )
        self.avgpool = nn.AdaptiveAvgPool2d((6, 6))
        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):
        x = self.features(x)
        x = self.avgpool(x)
        x = x.view(x.size(0), 256 * 6 * 6)
        x = self.classifier(x)
        return x

注意:

Here the output channel is 64 not 96, and using zero-padding(2)

1.1.3 VGG

论文"Very deep convolutional networks for large-scale image recognition"
VGG配置表

VGG19模型结构

see more for details.

参考代码:

cfg = {
    "E": [
        64, 64, "M",
        128, 128, "M",
        256, 256, 256, 256, "M",
        512, 512, 512, 512, "M",
        512, 512, 512, 512, "M",
    ],
}

class VGG(nn.Module):
    def __init__(self, features, num_classes=1000, init_weights=True):
        super(VGG, self).__init__()
        self.features = features
        self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
        self.classifier = nn.Sequential(
            nn.Linear(512 * 7 * 7, 4096),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(4096, num_classes),
        )
        if init_weights:
            self._initialize_weights()

    def forward(self, x):
        x = self.features(x)
        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.classifier(x)
        return x

def make_layers(cfg):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == "M":
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    return nn.Sequential(*layers)

def vgg19(**kwargs):
    return VGG(make_layers(cfg["E"]), **kwargs)

1.2 Object Detection

1.3 Object Segmentation

(draft)机器学习算法汇总

2019-08-26
ML

(draft)机器学习算法汇总

1 AlphaTree