Pytorch搭建LeNet5
1. LeNet神经网络介绍
LeNet神经网络由深度学习三巨头之一的Yan LeCun提出，他同时也是卷积神经网络 (CNN，Convolutional Neural Networks)之父。LeNet主要用来进行手写字符的识别与分类，并在美国的银行中投入了使用。LeNet的实现确立了CNN的结构，现在神经网络中的许多内容在LeNet的网络结构中都能看到，例如卷积层，Pooling层，ReLU层。虽然LeNet早在20世纪90年代就已经提出了，但由于当时缺乏大规模的训练数据，计算机硬件的性能也较低，因此LeNet神经网络在处理复杂问题时效果并不理想。虽然LeNet网络结构比较简单，但是刚好适合神经网络的入门学习。
2. LeNet神经网络结构
3. Pytorch搭建LeNet5
import torch.nn as nn
from collections import OrderedDict
import torch
# 利用torch.nn.Sequential和collections.OrderedDict()来构建每一个layer
class C1(nn.Module):
def __init__(self):
super(C1, self).__init__()
self.c1 = nn.Sequential(OrderedDict([ # 1代表输入通道数，6代表输出通道数，5代表卷积核的大小5x5,默认stride=1
('c1', nn.Conv2d(1, 6, 5)), # 6@28×28
('relu1', nn.ReLU()),
('s2', nn.MaxPool2d(2, 2)) # 6@14x14,通道数不变，超参数2分别表示池化大小和步长
]))
def forward(self, img):
output = self.c1(img) # 输入是1x32x32
return output
class C3(nn.Module):
def __init__(self):
super(C3, self).__init__()
self.c3 = nn.Sequential(OrderedDict([
('c3', nn.Conv2d(6, 16, 5)), # 16@10×10
('relu2', nn.ReLU()),
('s4', nn.MaxPool2d(2, 2)) # 16@5×5
]))
def forward(self, img):
output = self.c3(img)
return output
class C5(nn.Module):
def __init__(self):
super(C5, self).__init__()
self.c5 = nn.Sequential(OrderedDict([
('c5', nn.Conv2d(16, 120, 5)), # 120@1x1
('relu3', nn.ReLU())
]))
def forward(self, img):
output = self.c5(img)
return output
class F6(nn.Module):
def __init__(self):
super(F6, self).__init__()
self.f6 = nn.Sequential(OrderedDict([
('f4', nn.Linear(120, 84)),
('relu4', nn.ReLU())
]))
def forward(self, img):
output = self.f6(img)
return output
class F7(nn.Module):
def __init__(self):
super(F7, self).__init__()
self.f7 = nn.Sequential(OrderedDict([
('f7', nn.Linear(84, 10)),
('sig8', nn.LogSoftmax(dim=-1))
]))
def forward(self, img):
output = self.f7(img)
return output
class LeNet5(nn.Module):
"""
Input - 1x32x32
Output - 10
"""
def __init__(self):
super(LeNet5, self).__init__()
self.c1 = C1()
self.c3_1 = C3()
self.c3_2 = C3()
self.c5 = C5()
self.f6 = F6()
self.f7 = F7()
def forward(self, img):
output = self.c1(img)
x = self.c3_1(output)
output = self.c3_2(output)
output += x
output = self.c5(output)
output = output.view(img.size(0), -1) # 将卷积层的输出摊平为120维向量
output = self.f6(output) # 全连接层将120维变为84维
output = self.f7(output) # 全连接层将84维变为10维，用于预测输出的结果
return output
if __name__ == '__main__':
model = LeNet5() # 网络实例化
print(model)
in_put = torch.rand(1, 1, 32, 32) # 随机构建一张一个通道的32*32的输入图片
out = model(in_put)
print(out) # 哪一维的数字最大，输入就属于那一类别
LeNet5(
(c1): C1(
(c1): Sequential(
(c1): Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1))
(relu1): ReLU()
(s2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
)
(c3_1): C3(
(c3): Sequential(
(c3): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
(relu2): ReLU()
(s4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
)
(c3_2): C3(
(c3): Sequential(
(c3): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
(relu2): ReLU()
(s4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
)
(c5): C5(
(c5): Sequential(
(c5): Conv2d(16, 120, kernel_size=(5, 5), stride=(1, 1))
(relu3): ReLU()
)
)
(f6): F6(
(f6): Sequential(
(f4): Linear(in_features=120, out_features=84, bias=True)
(relu4): ReLU()
)
)
(f7): F7(
(f7): Sequential(
(f7): Linear(in_features=84, out_features=10, bias=True)
(sig8): LogSoftmax()
)
)
)
tensor([[-2.2676, -2.2554, -2.3434, -2.3523, -2.4532, -2.2200, -2.1823, -2.3595,
-2.3212, -2.2984]], grad_fn=<LogSoftmaxBackward>)
Process finished with exit code 0