论文要点：AlexNet（模型M+公式F+代码C）

学语音的Shannon

已于 2024-05-10 14:19:56 修改

阅读量172

点赞数 2

文章标签：人工智能深度学习

于 2024-05-10 13:51:34 首次发布

本文链接：https://blog.csdn.net/qq_26911523/article/details/138663175

版权

# AlexNet

论文：ImageNet classification with deep convolutional neural networks by By Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton

1. 模型：

2. 代码：

# 代码来自动手学深度学习 by 李沐
# 实现AlexNet
import torch
from d2l import torch as d2l
from torch import nn

net = nn.Sequential(nn.Conv2d(1, 96, kernel_size=11, stride=4, padding=1), nn.ReLU(), 
                    nn.MaxPool2d(3, stride=2), 
                    nn.Conv2d(96, 256, kernel_size=5, padding=2), nn.ReLU(), 
                    nn.MaxPool2d(3, stride=2), 
                    nn.Conv2d(256, 384, kernel_size=3, padding=1), nn.ReLU(),
                    nn.Conv2d(384, 384, kernel_size=3, padding=1), nn.ReLU(),
                    nn.Conv2d(384, 384, kernel_size=3, padding=1), nn.ReLU(),
                    nn.MaxPool2d(3, stride=2), 
                    nn.Flatten(),
                    nn.Linear(9600, 4096), nn.ReLU(), nn.Dropout(p=0.5),
                    nn.Linear(4096, 4096), nn.ReLU(), nn.Dropout(p=0.5),
                    nn.Linear(4096, 10)
                   )

batch_size = 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)

lr, num_epochs = 0.01, 10
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())