基于pytorch框架，采用神经网络和CNN网络实现Mnist数据集，该示例训练，相当于语言编程界的“hello world”入门程序。
文章目录
前言一、Mnist数据模型简介二数据集的下载2.1网址下载2.2 基于pytorch框架自带模块加载2.3基于tensorflow自带框架加载（CNN）前言
基于pytorch框架实现Mnist数据集，掌握机器学习中第一个“hello world”程序
一、Mnist数据模型简介
MNIST数据集是由0 到9 的数字图像构成的。它包含了60000张图片作为训练数据，10000张图片作为测试数据。每一张图片都有对应的标签数字。图片大小均为 28 * 28，单通道灰度图像（0~255）。
二数据集的下载
2.1网址下载
数据下载地址：/exdb/mnist/
下载后将文件放入相应的工作目录，然后进行加载：
'''采用已经下载好的本地minist数据集进行训练'''data_path=Path('data')path=data_path/'mnist'path.mkdir(parents=True,exist_ok=True)#url="/exdb/mnist/"filename="mnist.pkl.gz"if not (path/filename).exists():content=requests.get(filename).content(path/filename).open('wb').write(content)#with gzip.open((path/filename).as_posix(),'rb')as f:((x_train,y_train),(x_valid,y_valid),_)=pickle.load(f,encoding='latin-1')#784=28*28 黑白单通道print(x_train.shape)print(y_train.shape)print(x_valid.shape)print(y_valid.shape)plt.imshow(x_train[0].reshape((28,28)),cmap='gray')plt.show()x_train,y_train,x_valid,y_valid=map(torch.tensor,(x_train,y_train,x_valid,y_valid))n,c=x_train.shape
2.2 基于pytorch框架自带模块加载
from torchvision.datasets import mnistimport torchvision.transforms as transformsimport matplotlib.pyplot as pltimport torchfrom torch import nntransforms=pose([transforms.ToTensor(),transforms.Normalize([0.5],[0.5])])train_dataset=mnist.MNIST(root='./DATA',#下载数据，存放在DATA目录下train=True,#下载完成后告知默认的为训练集，如果为FALSE:则为测试集transform=transforms,download=True)test_dataset=mnist.MNIST(root='./DATA',train=False,transform=transforms,download=True)print('length of train_data',len(train_dataset))print('shape of train_data',train_dataset.data.shape)print('Target shape of train_data',train_dataset.targets.shape)print('length of train_data',len(test_dataset))print('shape of train_data',test_dataset.data.shape)print('Target shape of train_data',test_dataset.targets.shape)#显示图片data,targets=train_dataset.data[:6],train_dataset.targets[:6]fig=plt.figure(figsize=(5,5))for i in range(6):plt.subplot(2,3,(i+1))#子图从1开始，2行3列plt.tight_layout()#显示紧凑plt.imshow(data[i],cmap='gray')#以灰度图形式显示，去掉后可能为彩色plt.title('target:{}'.format(i))plt.xticks([])#去掉X坐标轴plt.yticks([])#去掉Y坐标轴plt.show()#超参数train_batch_size=128test_batch_size=54#加载数据，可迭代对象from torch.utils.data import DataLoaderfrom torch.nn import functional as Ftrain_loader=DataLoader(train_dataset,batch_size=train_batch_size,shuffle=True)test_loader=DataLoader(test_dataset,batch_size=test_batch_size,shuffle=False)#构建网络class Net(nn.Module):def __init__(self,in_dim,n_hidden1,n_hidden2,out_dim):super(Net,self).__init__()self.layer1=nn.Sequential(nn.Linear(in_dim,n_hidden1),nn.BatchNorm1d(n_hidden1))self.layer2 = nn.Sequential(nn.Linear(n_hidden1, n_hidden2), nn.BatchNorm1d(n_hidden2))self.layer3 = nn.Sequential(nn.Linear(n_hidden2, out_dim))def forward(self,x):x=F.relu(self.layer1(x))x=F.relu(self.layer2(x))x=self.layer3(x)return xmodel=Net(28*28,256,128,10)print(model)#定义损失函数和优化器import torch.optim as optim#超参数learning_rate=0.01momentum=0.5criterion=nn.CrossEntropyLoss()optimizer=optim.SGD(model.parameters(),lr=learning_rate,momentum=momentum)#训练模型num_epoches=10device=torch.device("cuda:0" if torch.cuda.is_available() else "cpu")model.to(device)train_losses=[]train_accs=[]for epoch in range(num_epoches):train_loss=0train_acc=0for img,label in train_loader:img=img.to(device)label=label.to(device)img=img.view(img.size(0),-1)out=model(img)loss=criterion(out,label)optimizer.zero_grad()loss.backward()optimizer.step()train_loss+=loss.item()pred=out.argmax(dim=1)train_acc +=(pred==label).sum().item()/img.size(0)train_loss=train_loss/len(train_loader)train_acc=train_acc/len(train_loader)train_losses.append(train_loss)train_accs.append(train_acc)print('Epoch:{},Train loss:{},Train acc:{}'.format(epoch,train_losses,train_acc))
2.3基于tensorflow自带框架加载（CNN）
import tensorflow as tfmnist=tf.keras.datasets.mnist(x_train,y_train),(x_label,y_label)=mnist.load_data()print(x_train.shape)print(y_train.shape)print(x_label.shape)print(y_label.shape)import ossave_dir='./MNIST_DATA/RAW/'if os.path.exists(save_dir)is False:os.mkdir(save_dir)import matplotlib.pyplot as plt#显示前20张图片for i in range(6):plt.subplot(2, 3, (i + 1)) # 子图从1开始，2行3列plt.tight_layout() # 显示紧凑plt.imshow(x_train[i], cmap='gray') # 以灰度图形式显示，去掉后可能为彩色plt.title('target:{}'.format(i))plt.xticks([]) # 去掉X坐标轴plt.yticks([]) # 去掉Y坐标轴plt.show()'''导入的训练集的shape为(60000,28,28)。若是全连接神经网络，需要reshape为(60000,784)；而卷积神经网络因为必须先进行卷积与池化运算，所以必须保持图像的维数。所以reshape转换为(60000,28,28,1)，即60000张图像，每一张为28(宽)*28(高)*1(单色)。'''#数据处理，数据导入后预处理才能够输入模型进行训练x_train=x_train.reshape(x_train.shape[0],28,28,1).astype('float32')x_label=x_label.reshape(x_label.shape[0],28,28,1).astype('float32')#标准化操作x_train,x_label=x_train/255.0,x_label/255.0#搭建模型model=tf.keras.models.Sequential([tf.keras.layers.Conv2D(input_shape=(28,28,1),filters=16,kernel_size=(5,5),padding='same',activation='relu'),tf.keras.layers.MaxPool2D(pool_size=(2,2)),tf.keras.layers.Conv2D(filters=32,kernel_size=(3,3),padding='same',activation='relu'),tf.keras.layers.MaxPool2D(pool_size=(2,2)),tf.keras.layers.Dropout(0.25),tf.keras.layers.Flatten(),tf.keras.layers.Dense(128,activation='relu'),tf.keras.layers.Dropout(0.5),tf.keras.layers.Dense(10,activation='softmax')])print(model.summary())#训练模型''''''pile(loss='sparse_categorical_crossentropy',optimizer='adam',metrics=['accuracy'])model.fit(x=x_train,y=y_train,validation_split=0.3,epochs=20,batch_size=100,verbose=2)
