推荐
python实现手写数字识别（小白入门）
原文MNIST Handwritten Digit Recognition in PyTorch 翻译用PyTorch实现MNIST手写数字识别(非常详细)
mnist.gz/mnist.csv数据集下载
mnist 数据集 下载 训练 测试 pytorchpytorch及torchvision下载不超过可看
清华镜像源下载pytorch及torchvision
配置环境miniconda+pycharm【机器学习】 的第四步 创建 虚拟环境
anaconda常用指令，更新查看添加下载源等
和第五步使用虚拟环境 7扩展 在虚拟环境中安装必要的包
注意
sklearn.externals.joblib导入问题from sklearn.externals import joblib改为import joblib
代码 python实现手写数字识别（小白入门）
项目结构
1.py
需要下载joblib包
import numpy as np
from sklearn.linear_model import LogisticRegression
import os
import joblib
#数据预处理
trainData = np.loadtxt(open('digits_training.csv', 'r'), delimiter=",",skiprows=1)#装载数据
MTrain, NTrain = np.shape(trainData) #行列数
print("训练集：",MTrain,NTrain)
xTrain = trainData[:,1:NTrain]
xTrain_col_avg = np.mean(xTrain, axis=0) #对各列求均值
xTrain =(xTrain- xTrain_col_avg)/255 #归一化
yTrain = trainData[:,0]
'''================================='''
#训练模型
model = LogisticRegression(solver='lbfgs', multi_class='multinomial', max_iter=500)
model.fit(xTrain, yTrain)
print("训练完毕")
'''================================='''
#测试模型
testData = np.loadtxt(open('digits_testing.csv', 'r'), delimiter=",",skiprows=1)
MTest,NTest = np.shape(testData)
print("测试集：",MTest,NTest)
xTest = testData[:,1:NTest]
xTest = (xTest-xTrain_col_avg) /255 # 使用训练数据的列均值进行处理
yTest = testData[:,0]
yPredict = model.predict(xTest)
errors = np.count_nonzero(yTest - yPredict) #返回非零项个数
print("预测完毕。错误：", errors, "条")
print("测试数据正确率:", (MTest - errors) / MTest)
'''================================='''
#保存模型
# 创建文件目录
dirs = 'testModel'
if not os.path.exists(dirs):
os.makedirs(dirs)
joblib.dump(model, dirs+'/model.pkl')
print("模型已保存")
结果1
2.py
需要下载cv2包
在test下放置几张数字图片
import cv2
import numpy as np
import joblib
map=cv2.imread(r"test/img1.png")
GrayImage = cv2.cvtColor(map, cv2.COLOR_BGR2GRAY)
# 获取图片的宽和高
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)
结果2
代码 用PyTorch实现MNIST手写数字识别(非常详细)
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 plt
n_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 = 0
correct = 0
with 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() # 不加这个，后面画图就会报错：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)
# 注意不要注释前面的“for epoch in range(1, n_epochs + 1):”部分，
# 不然报错：x and y must be the same size
# 为什么是“4”开始呢，因为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()
运行结果
运行之后项目结构
代码 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 plt
num_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=10
train_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 out
model = 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,right
with torch.no_grad():
correct,total=0,0
for images,labels in test_loader:
images=images.reshape(-1,28*28)
outputs=model(images)
num,right=acc(labels,outputs)
correct=correct+right
total=total+num
print('Accuracy of the network on the 10000 test images:{}%'.format(100*correct/total))
结果
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%