动手学深度学习(Pytorch版)代码实践 -卷积神经网络-24深度卷积神经网络AlexNet

24深度卷积神经网络AlexNet

python 复制代码
import torch
from torch import nn
import liliPytorch as lp
import liliPytorch as lp
import matplotlib.pyplot as plt

dropout1 = 0.5
#Alexnet架构
net = nn.Sequential(
    nn.Conv2d(1, 96, kernel_size=11, stride=4, padding=1),
    nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),

    nn.Conv2d(96, 256, kernel_size=5, padding=2),
    nn.ReLU(),
    nn.MaxPool2d(kernel_size=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, 256, kernel_size=3, padding=1),
    nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    
    nn.Flatten(),
    nn.Linear(6400, 4096),
    nn.ReLU(),
    nn.Dropout(dropout1),
    nn.Linear(4096, 4096),
    nn.ReLU(),
    nn.Dropout(dropout1),
    nn.Linear(4096,10)
)

#魔改一下
lilinet = nn.Sequential(
    nn.Conv2d(1, 96, kernel_size=11, stride=4, padding=1),
    nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),

    nn.Conv2d(96, 256, kernel_size=5, padding=2),
    nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    nn.MaxPool2d(kernel_size=3, stride=2),

    nn.Flatten(),
    nn.Linear(6400, 4096),
    nn.ReLU(),
    nn.Dropout(dropout1),
    nn.Linear(4096, 4096),
    nn.ReLU(),
    nn.Dropout(dropout1),
    nn.Linear(4096,10)
)


# 通过在每一层打印输出的形状,我们可以检查模型
X = torch.rand(size=(1, 1, 224, 224), dtype=torch.float32) 
for layer in net:
    X = layer(X) # 将输入依次通过每一层
    print(layer.__class__.__name__, 'output shape: \t', X.shape) # 打印每一层的输出形状
"""
Conv2d output shape:     torch.Size([1, 96, 54, 54])
ReLU output shape:       torch.Size([1, 96, 54, 54])
MaxPool2d output shape:          torch.Size([1, 96, 26, 26])
Conv2d output shape:     torch.Size([1, 256, 26, 26])
ReLU output shape:       torch.Size([1, 256, 26, 26])
MaxPool2d output shape:          torch.Size([1, 256, 12, 12])
Conv2d output shape:     torch.Size([1, 384, 12, 12])
ReLU output shape:       torch.Size([1, 384, 12, 12])
Conv2d output shape:     torch.Size([1, 384, 12, 12])
ReLU output shape:       torch.Size([1, 384, 12, 12])
Conv2d output shape:     torch.Size([1, 256, 12, 12])
ReLU output shape:       torch.Size([1, 256, 12, 12])
MaxPool2d output shape:          torch.Size([1, 256, 5, 5])
Flatten output shape:    torch.Size([1, 6400])
Linear output shape:     torch.Size([1, 4096])
ReLU output shape:       torch.Size([1, 4096])
Dropout output shape:    torch.Size([1, 4096])
Linear output shape:     torch.Size([1, 4096])
ReLU output shape:       torch.Size([1, 4096])
Dropout output shape:    torch.Size([1, 4096])
Linear output shape:     torch.Size([1, 10])
"""

#读取数据集
batch_size = 64
train_iter, test_iter = lp.loda_data_fashion_mnist(batch_size,  resize=224) # 加载Fashion-MNIST数据集

#Alexnet架构
# lr, num_epochs = 0.01, 10
# batch_size = 128
# lp.train_ch6(net, train_iter, test_iter, num_epochs, lr, lp.try_gpu())
# loss 0.329, train acc 0.879, test acc 0.883

# 魔改
lr, num_epochs = 0.1, 10
lp.train_ch6(lilinet, train_iter, test_iter, num_epochs, lr, lp.try_gpu())
plt.show() # 显示训练曲线

#lr, num_epochs = 0.01, 10
#batch_size = 128
#loss 0.356, train acc 0.868, test acc 0.870

#lr, num_epochs = 0.1, 10
#batch_size = 64
#loss 0.212, train acc 0.920, test acc 0.903

运行结果:

相关推荐
chanalbert11 分钟前
信息检索技术综述:从传统稀疏检索到现代深度学习方法
人工智能·深度学习·全文检索
fsnine1 小时前
深度学习——迁移学习
人工智能·深度学习·机器学习
CoovallyAIHub1 小时前
AI帮你打标签!这个开源神器让数据标注快了90%
深度学习·算法·计算机视觉
九章云极AladdinEdu4 小时前
临床数据挖掘与分析:利用GPU加速Pandas和Scikit-learn处理大规模数据集
人工智能·pytorch·数据挖掘·pandas·scikit-learn·paddlepaddle·gpu算力
九章云极AladdinEdu13 小时前
存算一体芯片生态评估:从三星PIM到知存科技WTM2101
人工智能·pytorch·科技·架构·开源·gpu算力
max50060015 小时前
实时多模态电力交易决策系统:设计与实现
图像处理·人工智能·深度学习·算法·音视频
尝试经历体验16 小时前
pycharm突然不能正常运行
python·深度学习·pycharm
大千AI助手16 小时前
灾难性遗忘:神经网络持续学习的核心挑战与解决方案
人工智能·深度学习·神经网络·大模型·llm·持续学习·灾难性遗忘
七元权17 小时前
论文阅读-SelectiveStereo
论文阅读·深度学习·双目深度估计·selectivestereo