基于pytorch平台实现对MNIST数据集的分类分析（前馈神经网络softmax）基础版

Posted 2022-04-25 我是一颗跳跳糖哦

基于pytorch平台实现对MNIST数据集的分类分析（前馈神经网络、softmax）基础版

---

文章目录

• 基于pytorch平台实现对MNIST数据集的分类分析（前馈神经网络、softmax）基础版
• 前言
• 一、基于“前馈神经网络”模型，分类分析
• 二、基于“softmax”模型，分类分析
• 总结

---

前言

本篇文章，将基于pytorch平台实现对MNIST数据集的分类分析，并分别以分类“的准确度”和“混淆矩阵”为衡量指标，分析模型的精度。

---

一、基于“前馈神经网络”模型，分类分析

注意：
根目录’E:\\深度学习’，在这里根据自己实际情况建立；
运行程序时将自动下载数据集，数据集将下载至先前建立的根目录中，用于训练模型及测试。

import torch
from torch import nn
from torch.autograd import Variable
from torch.utils.data import DataLoader
import torchvision.datasets as dsets
import torchvision.transforms as transforms

batch_size = 100
# MNIST dataset
train_dataset = dsets.MNIST(root='E:\\深度学习', train=True, transform=transforms.ToTensor(), download=True)
test_dataset = dsets.MNIST(root='E:\\深度学习', train=False, transform=transforms.ToTensor(), download=True)
# load_data
train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=True)



# original_data
print("train_data:", train_dataset.train_data.size())
print("train_labels:", train_dataset.train_labels.size())
print("test_data:", test_dataset.test_data.size())
print("test_labels:", test_dataset.test_labels.size())
# shuffle batch_size data
print("batch_size:", train_loader.batch_size)
print("load_train_data:", train_loader.dataset.train_data.shape)
print("load_train_labels:", train_loader.dataset.train_labels.shape)


input_size = 784
hidden_size = 500
num_classes = 10

# #定义神经网络模型
#一般把网络中具有可学习参数的层（如全连接层、卷积层等）放在构造函数__init__()中
class Neural_net(nn.Module):
    #最重要__init__初始化方法，便于一些参数的传递
    def __init__(self, input_num, hidden_size, output_num):
        super(Neural_net, self).__init__()#调用父类构造函数，以继承父类一些属性
        self.layers1 = nn.Linear(input_num, hidden_size)
        self.layers2 = nn.Linear(hidden_size, output_num)

    # 最重要的forward方法，便于进行前向传播
    def forward(self, x):
        out = self.layers1(x)
        out = torch.relu(out)
        out = self.layers2(out)
        return out
net = Neural_net(input_size, hidden_size, num_classes)
print(net)


# training
learning_rate = 1e-1
num_epoches = 5
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(net.parameters(), lr=learning_rate)
for epoch in range(num_epoches):
    print("current epoch = ".format(epoch))
    for i, (images,labels) in enumerate(train_loader):
        images = Variable(images.view(-1, 28*28))
        labels = Variable(labels)

        outputs = net(images)
        loss = criterion(outputs, labels)  # calculate loss
        optimizer.zero_grad()  # clear net state before backward
        loss.backward()
        optimizer.step()   # update parameters

        if i%100 == 0:
            print("current loss = %.5f" %loss.item())


# prediction
total = 0
correct = 0
for images, labels in test_loader:
    images = Variable(images.view(-1, 28*28))
    labels = Variable(labels)
    outputs = net(images)

    _,predicts = torch.max(outputs.data, 1)
    total += labels.size(0)
    correct += (predicts == labels).sum()
    from sklearn.metrics import confusion_matrix
    C2 = confusion_matrix(predicts, labels, labels=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
    import sklearn
    acc = sklearn.metrics.accuracy_score(labels, predicts)
print("混淆矩阵",C2)
print("混淆矩阵中的准确率为", acc)
print("Accuracy = %.2f" %(100*correct/total))

二、基于“softmax”模型，分类分析

import torch
import torch.utils.data as Data
from torchvision import datasets,transforms
import torchvision
from torch.autograd import  Variable
import numpy as np
import matplotlib.pyplot as plt

transform=transforms.Compose([transforms.ToTensor(),transforms.Normalize(mean=[0.5,],std=[0.5,])])
data_train=datasets.MNIST(root="D:\\jupyter_data",  transform=transform, train=True,
                          download=True
                          )
data_test=datasets.MNIST(root="D:\\jupyter_data", transform=transform, train=False)


batch = 256
train_iter = Data.DataLoader(dataset=data_train, batch_size=batch, shuffle=True)
test_iter = Data.DataLoader(data_test,batch, shuffle=True)
print(train_iter)


#定义和初始化模型
for X,y in train_iter:
    print(X.shape)
    print(X.view(X.shape[0],-1).shape)
    break

num_inputs = 784
num_outputs = 10
class LinearNet(torch.nn.Module):
    def __init__(self,num_inputs,num_outputs):
        super(LinearNet,self).__init__()
        self.linear = torch.nn.Linear(num_inputs,num_outputs)
    def forword(self,X): #这里X是28行28列.
        y=self.linear(X.view(X.shape[0],-1))
        return y  #参数中的-1就代表这个位置由其他位置的数字来推断,根据上面得到的shape，一批是256个，所以这里的shape[0]是256
net = LinearNet(num_inputs, num_outputs)
torch.nn.init.normal_(net.linear.weight, mean=0, std=0.01)
torch.nn.init.constant_(net.linear.bias, val=0)

print(net)
for X,y in train_iter:
    y_pre = net.forword(X)
    print(y_pre.shape)
    print(y_pre.view(y_pre.shape[0],-1).shape)
    break
#定义损失函数
loss = torch.nn.CrossEntropyLoss()

#定义优化算法
optimizer = torch.optim.SGD(net.linear.parameters(),lr=0.1)

#训练模型
epoch_size = 3
def softmax_train(train_iter, test_iter, epoch_size, loss, optimizer, net, batchsize):
    for epoch in range(0, epoch_size+1):
        train_acc_count = 0
        train_loss = 0
        n = 0
        for X,y in train_iter:
            y_pre = net.forword(X)
            l = loss(y_pre, y).sum() #注意要加起来，这个是softmax+交叉熵的，之前的线性回归不用
            optimizer.zero_grad() #梯度清零
            l.backward()
            optimizer.step()
            #准确率
            train_acc_count += (y_pre.argmax(dim=1) == y).sum().item()
            train_loss += l.item() #
            n += y.shape[0]
        print('epoch %d,loss %.4f, train acc %.3f'% (epoch + 1, train_loss/n ,train_acc_count/n))
softmax_train(train_iter, test_iter, epoch_size, loss, optimizer, net, batch)

def test_acc(test_iter, net):
    test_acc_count = 0
    n = 0
    for X,y in test_iter:
        y_pre = net.forword(X)
        test_acc_count += (y_pre.argmax(dim=1) == y).sum().item()
        n += y.shape[0]
        #y = y.detach().numpy()
        #y_pre = y_pre.detach().numpy()
        from sklearn.metrics import confusion_matrix
        C2 = confusion_matrix(y_pre.argmax(dim=1), y, labels=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
        import sklearn
        acc = sklearn.metrics.accuracy_score(y, y_pre.argmax(dim=1) )
    print("混淆矩阵", C2)
    print("混淆矩阵中的准确率为", acc)
    print('test acc %.3f'% (test_acc_count/n))


test_acc(test_iter, net)

总结

以上是基于pytorch平台实现对MNIST数据集的分类分析（前馈神经网络、softmax）的“基础版”，升级版在下一篇博客基于pytorch平台实现对MNIST数据集的分类分析（前馈神经网络、softmax）升级版