# AlexNet

**Repository Path**: deepmodels/alex-net

## Basic Information

- **Project Name**: AlexNet
- **Description**: alexnet训练cifar10
- **Primary Language**: Unknown
- **License**: MulanPSL-1.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-09-17
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# AlexNet

#### 介绍
alexnet训练cifar10

#### 软件架构
软件架构说明

第一层：卷积层1，输入为 224 × 224 × 3 224 \times 224 \times 3224×224×3的图像，卷积核的数量为96，论文中两片GPU分别计算48个核; 卷积核的大小为 11 × 11 × 3 11 \times 11 \times 311×11×3; stride = 4, stride表示的是步长， pad = 0, 表示不扩充边缘;
卷积后的图形大小是怎样的呢？
wide = (224 + 2 * padding - kernel_size) / stride + 1 = 54
height = (224 + 2 * padding - kernel_size) / stride + 1 = 54
dimention = 96
然后进行 (Local Response Normalized), 后面跟着池化pool_size = (3, 3), stride = 2, pad = 0 最终获得第一层卷积的feature map
最终第一层卷积的输出为

第二层：卷积层2, 输入为上一层卷积的feature map， 卷积的个数为256个，论文中的两个GPU分别有128个卷积核。卷积核的大小为：5 × 5 × 48 5 \times 5 \times 485×5×48; pad = 2, stride = 1; 然后做 LRN， 最后 max_pooling, pool_size = (3, 3), stride = 2;

第三层：卷积3, 输入为第二层的输出，卷积核个数为384, kernel_size = (3 × 3 × 256 3 \times 3 \times 2563×3×256)， padding = 1, 第三层没有做LRN和Pool

第四层：卷积4, 输入为第三层的输出，卷积核个数为384, kernel_size = (3 × 3 3 \times 33×3), padding = 1, 和第三层一样，没有LRN和Pool

第五层：卷积5, 输入为第四层的输出，卷积核个数为256, kernel_size = (3 × 3 3 \times 33×3), padding = 1。然后直接进行max_pooling, pool_size = (3, 3), stride = 2;

第6,7,8层是全连接层，每一层的神经元的个数为4096，最终输出softmax为1000,因为上面介绍过，ImageNet这个比赛的分类个数为1000。全连接层中使用了RELU和Dropout。

数据下载地址：[CIFAR-10](http://http://www.cs.toronto.edu/~kriz/cifar.html)

```
class AlexNet(nn.Cell):
    """AlexNet"""
    def __init__(self,num_classes=10, channel=3):
        super(AlexNet,self).__init__()
        super(AlexNet, self).__init__()
        self.conv1 = conv(channel, 96, 11, stride=4)
        self.conv2 = conv(96, 256, 5, pad_mode="same")
        self.conv3 = conv(256, 384, 3, pad_mode="same")
        self.conv4 = conv(384, 384, 3, pad_mode="same")
        self.conv5 = conv(384, 256, 3, pad_mode="same")
        self.relu = nn.ReLU()
        self.max_pool2d = P.MaxPool(ksize=3, strides=2)
        self.flatten = nn.Flatten()
        self.fc1 = fc_with_initialize(6 * 6 * 256, 4096)
        self.fc2 = fc_with_initialize(4096, 4096)
        self.fc3 = fc_with_initialize(4096, num_classes)

    def construct(self, x):
        x = self.conv1(x)
        x = self.relu(x)
        x = self.max_pool2d(x)
        x = self.conv2(x)
        x = self.relu(x)
        x = self.max_pool2d(x)
        x = self.conv3(x)
        x = self.relu(x)
        x = self.conv4(x)
        x = self.relu(x)
        x = self.conv5(x)
        x = self.relu(x)
        x = self.max_pool2d(x)
        x = self.flatten(x)
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        x = self.relu(x)
        x = self.fc3(x)
        return x
```