0


【头歌】机器学习 --- 神经网络

第1关:神经网络基本概念

c

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 *********#
train_data = pd.read_csv('./step2/train_data.csv')
train_label = pd.read_csv('./step2/train_label.csv')
train_label = train_label['target']
test_data = pd.read_csv('./step2/test_data.csv')
mlp = MLPClassifier(solver='lbfgs',max_iter=30, alpha=1e-4,hidden_layer_sizes=(20, ))
mlp.fit(train_data, train_label)
predict = mlp.predict(test_data)
df = pd.DataFrame({'result':predict}) 
df.to_csv('./step2/result.csv', index=False)
#********* End *********#

** 第4关:使用pytorch搭建卷积神经网络识别手写数字**

#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 *********#
train_loader = Data.DataLoader(
    dataset=train_data,
    batch_size=64,
    num_workers=2,
    shuffle=True
)
# 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()
# SGD表示使用随机梯度下降方法,lr为学习率,momentum为动量项系数
optimizer = torch.optim.SGD(cnn.parameters(), lr=0.01, momentum=0.9)
# 交叉熵损失函数
loss_func = nn.CrossEntropyLoss()
EPOCH = 3
for e in range(EPOCH):
    for x, y in train_loader:
        batch_x = Variable(x)
        batch_y = Variable(y)
        outputs = cnn(batch_x)
        loss = loss_func(outputs, batch_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()                    
           
#********* End *********#
#保存模型
torch.save(cnn.state_dict(), './step3/cnn.pkl')

本文转载自: https://blog.csdn.net/qq_63142181/article/details/128085870
版权归原作者 MQiyirs 所有, 如有侵权,请联系我们删除。

“【头歌】机器学习 --- 神经网络”的评论:

还没有评论