机器学习 --- 神经网络

第1关：神经网络基本概念

第2关：激活函数

#encoding=utf8

def relu(x):
    '''
    x:负无穷到正无穷的实数
    '''
    #********* Begin *********#
    if x <= 0:
        return 0
    else:
        return x
    #********* End *********#

第3关：反向传播算法

#encoding=utf8
import os
import pandas as pd
from sklearn.neural_network import MLPClassifier

if os.path.exists('./step2/result.csv'):
    os.remove('./step2/result.csv')
    
#********* Begin *********#
#获取训练数据
train_data = pd.read_csv('./step2/train_data.csv')
#获取训练标签
train_label = pd.read_csv('./step2/train_label.csv')
train_label = train_label['target']
#获取测试数据
test_data = pd.read_csv('./step2/test_data.csv')

#调用MLP模型并进行训练
mlp = MLPClassifier(solver='lbfgs',max_iter =500,
           alpha=1e-3,hidden_layer_sizes=(100,),learning_rate_init=0.0001)
mlp.fit(train_data, train_label)

#预测
result = mlp.predict(test_data)
#保存
save_df = pd.DataFrame({'result':result})
save_df.to_csv('./step2/result.csv',index=0)
#********* End *********#

第4关：使

#encoding=utf8
import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
import os
if os.path.exists('./step3/cnn.pkl'):
    os.remove('./step3/cnn.pkl')
    
#加载数据             
train_data = torchvision.datasets.MNIST(
    root='./step3/mnist/',
    train=True,                                     # this is training data
    transform=torchvision.transforms.ToTensor(),    # Converts a PIL.Image or numpy.ndarray to                                                    
    download=False,
)
#取6000个样本为训练集
train_data_tiny = []

for i in range(6000):
    train_data_tiny.append(train_data[i])

train_data = train_data_tiny

#********* Begin *********#
#构建卷积神经网络模型
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(         # input shape (1, 28, 28)
            nn.Conv2d(
                in_channels=1,              # input height
                out_channels=16,            # n_filters
                kernel_size=5,              # filter size
                stride=1,                   # filter movement/step
                padding=2,                  # if want same width and length of this image after con2d, padding=(kernel_size-1)/2 if stride=1
            ),                              # output shape (16, 28, 28)
            nn.ReLU(),                      # activation
            nn.MaxPool2d(kernel_size=2),    # choose max value in 2x2 area, output shape (16, 14, 14)
        )
        self.conv2 = nn.Sequential(         # input shape (16, 14, 14)
            nn.Conv2d(16, 32, 5, 1, 2),     # output shape (32, 14, 14)
            nn.ReLU(),                      # activation
            nn.MaxPool2d(2),                # output shape (32, 7, 7)
        )
        self.out = nn.Linear(32 * 7 * 7, 10)   # fully connected layer, output 10 classes
    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)           # flatten the output of conv2 to (batch_size, 32 * 7 * 7)
        output = self.out(x)
        return output
cnn = CNN()              

optimizer = torch.optim.Adam(cnn.parameters(), lr = 0.01)
#交叉熵损失函数
loss_func = nn.CrossEntropyLoss()

train_loader = Data.DataLoader(dataset=train_data, batch_size=64, shuffle=True)
for step, (x, y) in enumerate(train_loader): 
    b_x = Variable(x)
    b_y = Variable(y) 
    output = cnn(b_x)
    loss = loss_func(output, b_y)
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

#********* End *********#
#保存模型
torch.save(cnn.state_dict(), './step3/cnn.pkl')

用pytorch搭建卷积神经网络识别手写数字