推薦

python實現手寫數字識別（小白入門）

原文MNIST Handwritten Digit Recognition in PyTorch
翻譯用PyTorch實現MNIST手寫數字識別(非常詳細)
mnist.gz/mnist.csv數據集下載

mnist 數據集 下載 訓練 測試 pytorch
pytorch及torchvision下載不超過可看
清華鏡像源下載pytorch及torchvision

配置環境miniconda+pycharm【機器學習】
的第四步 創建 虛擬環境
anaconda常用指令，更新查看添加下載源等
和第五步使用虛擬環境 7擴展 在虛擬環境中安裝必要的包

注意

sklearn.externals.joblib導入問題
from sklearn.externals import joblib改為import joblib

代碼 python實現手寫數字識別（小白入門）

項目結構

1.py

需要下載joblib包

import numpy as np from sklearn.linear_model import LogisticRegression import os import joblib#數據預處理 trainData = np.loadtxt(open('digits_training.csv', 'r'), delimiter=",",skiprows=1)#裝載數據 MTrain, NTrain = np.shape(trainData) #行列數 print("訓練集：",MTrain,NTrain) xTrain = trainData[:,1:NTrain] xTrain_col_avg = np.mean(xTrain, axis=0) #對各列求均值 xTrain =(xTrain- xTrain_col_avg)/255 #歸一化 yTrain = trainData[:,0]'''=================================''' #訓練模型 model = LogisticRegression(solver='lbfgs', multi_class='multinomial', max_iter=500) model.fit(xTrain, yTrain) print("訓練完畢")'''=================================''' #測試模型 testData = np.loadtxt(open('digits_testing.csv', 'r'), delimiter=",",skiprows=1) MTest,NTest = np.shape(testData) print("測試集：",MTest,NTest) xTest = testData[:,1:NTest] xTest = (xTest-xTrain_col_avg) /255 # 使用訓練數據的列均值進行處理 yTest = testData[:,0] yPredict = model.predict(xTest) errors = np.count_nonzero(yTest - yPredict) #返回非零項個數 print("預測完畢。錯誤：", errors, "條") print("測試數據正確率:", (MTest - errors) / MTest)'''=================================''' #保存模型# 創建文件目錄 dirs = 'testModel' if not os.path.exists(dirs):os.makedirs(dirs) joblib.dump(model, dirs+'/model.pkl') print("模型已保存")

結果1

2.py

需要下載cv2包

在test下放置幾張數字圖片

import cv2 import numpy as np import joblibmap=cv2.imread(r"test/img1.png") GrayImage = cv2.cvtColor(map, cv2.COLOR_BGR2GRAY) # 獲取圖片的寬和高 width, height = map.shape[:2][::-1] ret,thresh2=cv2.threshold(GrayImage,width,height,cv2.THRESH_BINARY_INV) Image=cv2.resize(thresh2,(28,28)) img_array = np.asarray(Image) z=img_array.reshape(1,-1)'''================================================'''model = joblib.load('testModel'+'/model.pkl') yPredict = model.predict(z) print(yPredict) y=str(yPredict) cv2.putText(map,y, (10,20), cv2.FONT_HERSHEY_SIMPLEX,0.7,(0,0,255), 2, cv2.LINE_AA) cv2.imshow("map",map) cv2.waitKey(0)

結果2

代碼 用PyTorch實現MNIST手寫數字識別(非常詳細)

pytorch.c

import torch import torchvision from torch.utils.data import DataLoader import torch.nn as nn import torch.nn.functional as F import torch.optim as optim import matplotlib.pyplot as pltn_epochs = 3 batch_size_train = 64 batch_size_test = 1000 learning_rate = 0.01 momentum = 0.5 log_interval = 10 random_seed = 1 torch.manual_seed(random_seed)train_loader = torch.utils.data.DataLoader(torchvision.datasets.MNIST('./data/', train=True, download=True,transform=torchvision.transforms.Compose([torchvision.transforms.ToTensor(),torchvision.transforms.Normalize((0.1307,), (0.3081,))])),batch_size=batch_size_train, shuffle=True) test_loader = torch.utils.data.DataLoader(torchvision.datasets.MNIST('./data/', train=False, download=True,transform=torchvision.transforms.Compose([torchvision.transforms.ToTensor(),torchvision.transforms.Normalize((0.1307,), (0.3081,))])),batch_size=batch_size_test, shuffle=True)examples = enumerate(test_loader) batch_idx, (example_data, example_targets) = next(examples) # print(example_targets) # print(example_data.shape)fig = plt.figure() for i in range(6):plt.subplot(2, 3, i + 1)plt.tight_layout()plt.imshow(example_data[i][0], cmap='gray', interpolation='none')plt.title("Ground Truth: {}".format(example_targets[i]))plt.xticks([])plt.yticks([]) plt.show()class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(1, 10, kernel_size=5)self.conv2 = nn.Conv2d(10, 20, kernel_size=5)self.conv2_drop = nn.Dropout2d()self.fc1 = nn.Linear(320, 50)self.fc2 = nn.Linear(50, 10)def forward(self, x):x = F.relu(F.max_pool2d(self.conv1(x), 2))x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))x = x.view(-1, 320)x = F.relu(self.fc1(x))x = F.dropout(x, training=self.training)x = self.fc2(x)return F.log_softmax(x, dim=1)network = Net() optimizer = optim.SGD(network.parameters(), lr=learning_rate, momentum=momentum)train_losses = [] train_counter = [] test_losses = [] test_counter = [i * len(train_loader.dataset) for i in range(n_epochs + 1)]def train(epoch):network.train()for batch_idx, (data, target) in enumerate(train_loader):optimizer.zero_grad()output = network(data)loss = F.nll_loss(output, target)loss.backward()optimizer.step()if batch_idx % log_interval == 0:print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(epoch, batch_idx * len(data),len(train_loader.dataset),100. * batch_idx / len(train_loader),loss.item()))train_losses.append(loss.item())train_counter.append((batch_idx * 64) + ((epoch - 1) * len(train_loader.dataset)))torch.save(network.state_dict(), './model.pth')torch.save(optimizer.state_dict(), './optimizer.pth')def test():network.eval()test_loss = 0correct = 0with torch.no_grad():for data, target in test_loader:output = network(data)test_loss += F.nll_loss(output, target, reduction='sum').item()pred = output.data.max(1, keepdim=True)[1]correct += pred.eq(target.data.view_as(pred)).sum()test_loss /= len(test_loader.dataset)test_losses.append(test_loss)print('\nTest set: Avg. loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(test_loss, correct, len(test_loader.dataset),100. * correct / len(test_loader.dataset)))train(1)test() # 不加這個，后面畫圖就會報錯：x and y must be the same size for epoch in range(1, n_epochs + 1):train(epoch)test()fig = plt.figure() plt.plot(train_counter, train_losses, color='blue') plt.scatter(test_counter, test_losses, color='red') plt.legend(['Train Loss', 'Test Loss'], loc='upper right') plt.xlabel('number of training examples seen') plt.ylabel('negative log likelihood loss')examples = enumerate(test_loader) batch_idx, (example_data, example_targets) = next(examples) with torch.no_grad():output = network(example_data) fig = plt.figure() for i in range(6):plt.subplot(2, 3, i + 1)plt.tight_layout()plt.imshow(example_data[i][0], cmap='gray', interpolation='none')plt.title("Prediction: {}".format(output.data.max(1, keepdim=True)[1][i].item()))plt.xticks([])plt.yticks([]) plt.show()# ----------------------------------------------------------- #continued_network = Net() continued_optimizer = optim.SGD(network.parameters(), lr=learning_rate, momentum=momentum)network_state_dict = torch.load('model.pth') continued_network.load_state_dict(network_state_dict) optimizer_state_dict = torch.load('optimizer.pth') continued_optimizer.load_state_dict(optimizer_state_dict)# 注意不要注釋前面的“for epoch in range(1, n_epochs + 1):”部分， # 不然報錯：x and y must be the same size # 為什么是“4”開始呢，因為n_epochs=3，上面用了[1, n_epochs + 1) for i in range(4, 9):test_counter.append(i * len(train_loader.dataset))train(i)test()fig = plt.figure() plt.plot(train_counter, train_losses, color='blue') plt.scatter(test_counter, test_losses, color='red') plt.legend(['Train Loss', 'Test Loss'], loc='upper right') plt.xlabel('number of training examples seen') plt.ylabel('negative log likelihood loss') plt.show()

運行結果

運行之后項目結構

代碼 自己

import torch import torchvision from torch.utils.data import DataLoader import torch.nn as nn import torch.nn.functional as F import torch.optim as optim # import matplotlib.pyplot as pltnum_epochs = 6 batch_size = 100 learning_rate = 0.1 momentum = 0.5 log_interval = 10 random_seed = 1 torch.manual_seed(random_seed) input_size=28*28 num_classes=10train_dataset= torchvision.datasets.MNIST('./data/', train=True, download=True,transform=torchvision.transforms.Compose([torchvision.transforms.ToTensor(),torchvision.transforms.Normalize((0.1307,), (0.3081,))])) test_dataset=torchvision.datasets.MNIST('./data/', train=False, download=True,transform=torchvision.transforms.Compose([torchvision.transforms.ToTensor(),torchvision.transforms.Normalize((0.1307,), (0.3081,))]))train_loader = torch.utils.data.DataLoader(dataset=train_dataset,batch_size=batch_size, shuffle=True) test_loader = torch.utils.data.DataLoader(dataset=test_dataset,batch_size=batch_size, shuffle=False)class NeuralNet(nn.Module):def __init__(self,input_size,hidden_size,num_classes):super(NeuralNet, self).__init__()self.fc1=nn.Linear(input_size,hidden_size[0])self.fc2=nn.Linear(hidden_size[0],hidden_size[1])self.fc3=nn.Linear(hidden_size[1],num_classes)self.relu = nn.ReLU()def forward(self, x):out = self.fc1(x)out = self.relu(out)out = self.fc2(out)out = self.relu(out)out = self.fc3(out)return outmodel = NeuralNet(input_size, [256, 64], num_classes)criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(model.parameters(), lr=learning_rate)for epoch in range(num_epochs):for i,(images,labels) in enumerate(train_loader):images=images.reshape(-1,28*28)outputs=model(images)labels_onehot = F.one_hot(labels)loss=criterion(outputs,labels_onehot.float())optimizer.zero_grad()loss.backward()optimizer.step()if i % 600 == 0:print("Epoch :{} \t Loss:{:.6f}".format(epoch, loss.item()))torch.save(model,'model_total.ckpt') # torch.save(net.state_dict(),'model_para.ckpt')#-------------------------------------------------------------------model=torch.load('model_total.ckpt') ''' net=NeuralNet(input_size,[500,100],num_classes) net.load_state_dict(torch.load('model_para.ckpt')) '''def acc(labels,outputs):_,predicted=torch.max(outputs.data,1)num=len(labels)right=(predicted==labels).sum().item()return num,rightwith torch.no_grad():correct,total=0,0for images,labels in test_loader:images=images.reshape(-1,28*28)outputs=model(images)num,right=acc(labels,outputs)correct=correct+righttotal=total+numprint('Accuracy of the network on the 10000 test images:{}%'.format(100*correct/total))

結果

Epoch :0 Loss:2.294961 Epoch :1 Loss:0.086749 Epoch :2 Loss:0.101823 Epoch :3 Loss:0.045709 Epoch :4 Loss:0.053201 Epoch :5 Loss:0.032638 Accuracy of the network on the 10000 test images:98.0%

總結

以上是生活随笔為你收集整理的实验3 手写字体识别【机器学习】的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。