1106-Dataset&DataLoader、softmax分类器

Dataset&DataLoader

代码

import numpy as np
import torch
from torch.utils.data import Dataset,DataLoader

class DiabetesDataset(Dataset):
    def __init__(self,filepath):
        xy=np.loadtxt(filepath,delimiter=',',dtype=np.float32)
        self.len=xy.shape[0]
        self.x_data=torch.from_numpy(xy[:,:-1])
        self.y_data=torch.from_numpy(xy[:,[-1]])

    def __getitem__(self, item):
        return self.x_data[item],self.y_data[item]

    def __len__(self):
        return self.len

dataset=DiabetesDataset('diabetes.csv.gz')
train_loader=DataLoader(dataset=dataset,batch_size=32,shuffle=True,num_workers=2)

class Model(torch.nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        self.linear1=torch.nn.Linear(8,6)
        self.linear2 = torch.nn.Linear(6,4)
        self.linear3 = torch.nn.Linear(4,1)
        self.sigmoid=torch.nn.Sigmoid()
        self.activate=torch.nn.ReLU()

    def forward(self,x):
        x=self.sigmoid(self.linear1(x))
        x = self.sigmoid(self.linear2(x))
        x = self.sigmoid(self.linear3(x))
        return x

model=Model()

criterion=torch.nn.BCELoss(reduction='sum')
optimizer=torch.optim.SGD(model.parameters(),lr=0.01)
if __name__ == '__main__':
    
    for epoch in range(100):
        for i,data in enumerate(train_loader,0):
            inputs,labels=data
            y_pred=model(inputs)
            loss=criterion(y_pred,labels)
            print(epoch,i,loss.item())

            optimizer.zero_grad()
            loss.backward()

            optimizer.step()

实战泰坦尼克号

代码：

import numpy as np
import pandas as pd
from torch.utils.data import Dataset
import torch

class TaiDataset(Dataset):
    def __init__(self,filepath):
        feature= ["Pclass", "Sex", "SibSp", "Parch", "Fare"]
        data=pd.read_csv(filepath)
        self.len=data.shape[0]

        self.x_data=torch.from_numpy(np.array(pd.get_dummies(data[feature])))
        self.y_data=torch.from_numpy(np.array(data['Survived']))

    def __getitem__(self, item):
        return self.x_data[item],self.y_data[item]

    def __len__(self):
        return self.len

#建立数据集
dataset=TaiDataset('./taitannik/train.csv')
# 建立数据集加载器
from torch.utils.data import DataLoader
train_loader = DataLoader(dataset=dataset, batch_size=2, shuffle=True, num_workers=2)

class Model(torch.nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        self.linear1 = torch.nn.Linear(6,3)
        self.linear2 = torch.nn.Linear(3,1)
        self.sigmoid=torch.nn.Sigmoid()

    def forward(self,x):
        x=self.sigmoid(self.linear1(x))
        x = self.sigmoid(self.linear2(x))
        return x
    def predict(self,x):
        with torch.no_grad():
            x=self.sigmoid(self.linear1(x))
            x=self.sigmoid(self.linear2(x))
            y=[]
            for i in x:
                if i>0.5:
                    y.append(1)
                else:
                    y.append(0)
            return y
model=Model()
criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr=0.005)
#train
if __name__ == '__main__':
    for epoch in range(100):
        for i, data in enumerate(train_loader, 0):
            inputs, labels = data
            # 这里先转换了一下数据类型。
            inputs = inputs.float()
            labels = labels.float()

            y_pred = model(inputs)
            # 将维度压缩至1维。
            y_pred = y_pred.squeeze(-1)
            loss = criterion(y_pred, labels)
            print(epoch, i, loss.item())

            optimizer.zero_grad()
            loss.backward()

            optimizer.step()
    # 读取test文件
    test_data = pd.read_csv("./taitannik/test.csv")
    features = ["Pclass", "Sex", "SibSp", "Parch", "Fare"]
    test = torch.from_numpy(np.array(pd.get_dummies(test_data[features])))

    # 进行预测
    y = model.predict(test.float())

    # 输出预测结果到文件
    output = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': y})
    output.to_csv('./taitannik/my_predict.csv', index=False)

预测

 

 Softmax分类

手写体分类

import torch
import numpy as np
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

batch_size=64
transform=transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,),(0.3081,))
])

train_dataset=datasets.MNIST(root='../dataset/mnist',train=True,download=True,transform=transform)
train_loader=DataLoader(train_dataset,shuffle=True,batch_size=batch_size)

test_dataset=datasets.MNIST(root='../dataset/mnist',train=False,download=True,transform=transform)
test_loader=DataLoader(test_dataset,shuffle=True,batch_size=batch_size)

class Net(torch.nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        self.l1=torch.nn.Linear(784,512)
        self.l2 = torch.nn.Linear(512,256)
        self.l3 = torch.nn.Linear(256,128)
        self.l4 = torch.nn.Linear(128,64)
        self.l5 = torch.nn.Linear(64,10)

    def forward(self,x):
        x=x.view(-1,784)
        x=F.relu(self.l1(x))
        x=F.relu(self.l2(x))
        x=F.relu(self.l3(x))
        x=F.relu(self.l4(x))
        return self.l5(x)

model=Net()
criterion=torch.nn.CrossEntropyLoss()
optimizer=optim.SGD(model.parameters(),lr=0.01,momentum=0.5)

def train(epoch):
    running_loss=0.0
    for batch_idx,data in enumerate(train_loader,0):
        inputs,target=data
        optimizer.zero_grad()

        outputs=model(inputs)
        loss=criterion(outputs,target)
        loss.backward()
        optimizer.step()

        running_loss+=loss.item()
        if batch_size%300==299:
            print('[%d, %5d] loss: %.3f'% (epoch+1,batch_size+1,running_loss/300))
            running_loss=0.0
def test():
    correct=0
    total=0
    with torch.no_grad():
        for data in test_loader:
            images,labels=data
            outputs=model(images)
            _,predicted=torch.max(outputs.data,dim=1)
            total+=labels.size(0)
            correct+=(predicted == labels).sum().item()
        print('Accuracy on test set : %d %%' % (100*correct/total))

if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()

结果