Pytorch深度学习实践笔记8（b站刘二大人）

🎬个人简介：一个全栈工程师的升级之路！
📋个人专栏：pytorch深度学习
🎀CSDN主页发狂的小花
🌄人生秘诀：学习的本质就是极致重复!

《PyTorch深度学习实践》完结合集_哔哩哔哩_bilibili

1 Pytorch 数据加载

2 Dataset和DataLoader

3 程序

1 Pytorch 数据加载

epoch、Batch-size 、iteration

例如下图：
8个样本、shuffle是打乱样本的顺序，Batch-szie为2，iteration 就是 8 / 2 为4，epoch是训练集进行几个轮次的迭代。

2 Dataset和DataLoader

Dataset 是一个抽象类，使用时必须进行重写，from 在torch.utils.data Dataset
（1）重写时，需要根据数据来进行构造__init__(self,filepath)
（2）__getitem__(self,index)用来让数据可以进行索引操作
（3）__len__(self)用来获取数据集的大小
DataLoader 用来加载数据为mini-Batch ，支持Batch-size 的设置，shuffle支持数据的打乱顺序。

参数说明：

from torch.utils.data import DataLoader
 
test_load = DataLoader(dataset=test_data, batch_size=4 , shuffle= True, num_workers=0,drop_last=False)

batch_size=4表示每次取四个数据
shuffle= True表示开启数据集随机重排，即每次取完数据之后，打乱剩余数据的顺序，然后再进行下一次取
num_workers=0表示在主进程中加载数据而不使用任何额外的子进程，如果大于0，表示开启多个进程，进程越多，处理数据的速度越快，但是会使电脑性能下降，占用更多的内存
drop_last=False表示不丢弃最后一个批次，假设我数据集有10个数据，我的batch_size=3，即每次取三个数据，那么我最后一次只有一个数据能取，如果设置为true，则不丢弃这个包含1个数据的子集数据，反之则丢弃

数据转换为dataset形式，进行DataLoader的使用

x_data = torch.tensor([[1.0],[2.0],[3.0],[4.0],[5.0],[6.0],[7.0],[8.0],[9.0]])
y_data = torch.tensor([[2.0],[4.0],[6.0],[8.0],[10.0],[12.0],[14.0],[16.0],[18.0]])

dataset = Data.TensorDataset(x_data,y_data)

loader = Data.DataLoader(  
    dataset=dataset,  
    batch_size=BATCH_SIZE,  
    shuffle=True,  
    num_workers=0  
)

pytorch中的DataLoader_pytorch dataloader-CSDN博客

3 程序

数据分为训练集和测试集：Adam 训练

import torch
import numpy as np
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
from sklearn.model_selection import train_test_split

import matplotlib.pyplot as plt
 
 
# 读取原始数据，并划分训练集和测试集
raw_data = np.loadtxt('./dataset/diabetes.csv.gz', delimiter=',', dtype=np.float32)
X = raw_data[:, :-1]
Y = raw_data[:, [-1]]
Xtrain, Xtest, Ytrain, Ytest = train_test_split(X,Y,test_size=0.1)
Xtest = torch.from_numpy(Xtest)
Ytest = torch.from_numpy(Ytest)
 
# 将训练数据集进行批量处理
# prepare dataset
 
class DiabetesDataset(Dataset):
    def __init__(self, data,label):
 
        self.len = data.shape[0] # shape(多少行，多少列)
        self.x_data = torch.from_numpy(data)
        self.y_data = torch.from_numpy(label)
 
    def __getitem__(self, index):
        return self.x_data[index], self.y_data[index]
 
    def __len__(self):
        return self.len
 
 
train_dataset = DiabetesDataset(Xtrain,Ytrain)
train_loader = DataLoader(dataset=train_dataset, batch_size=16, shuffle=True, num_workers=0) #num_workers 多线程
 
# design model using class
 
 
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, 2)
        self.linear4 = torch.nn.Linear(2, 1)
        self.sigmoid = torch.nn.Sigmoid()
 
    def forward(self, x):
        x = self.sigmoid(self.linear1(x))
        x = self.sigmoid(self.linear2(x))
        x = self.sigmoid(self.linear3(x))
        x = self.sigmoid(self.linear4(x))
        return x
 
 
model = Model()
 
# construct loss and optimizer
criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
 
epoch_list = []
loss_list = []

# training cycle forward, backward, update
def train(epoch):
    for i, data in enumerate(train_loader, 0):
        inputs, labels = data
        y_pred = model(inputs)
 
        loss = criterion(y_pred, labels)
 
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        return loss.item()

 
 
def test():
    with torch.no_grad():
        y_pred = model(Xtest)
        y_pred_label = torch.where(y_pred>=0.5,torch.tensor([1.0]),torch.tensor([0.0]))
        acc = torch.eq(y_pred_label, Ytest).sum().item() / Ytest.size(0)
        print("test acc:", acc)
 
if __name__ == '__main__':
    for epoch in range(10000):
        loss_val = train(epoch)
        print("epoch: ",epoch," loss: ",loss_val)
        epoch_list.append(epoch)
        loss_list.append(loss_val)
    test()

    plt.plot(epoch_list,loss_list)
    plt.title("Adam")
    plt.xlabel("Epoch")
    plt.ylabel("Loss")
    plt.savefig("./data/pytorch7_1.png")

简单的程序

import torch
import numpy as np
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
 
# prepare dataset
 
 
class DiabetesDataset(Dataset):
    def __init__(self, filepath):
        xy = np.loadtxt(filepath, delimiter=',', dtype=np.float32)
        self.len = xy.shape[0] # shape(多少行，多少列)
        self.x_data = torch.from_numpy(xy[:, :-1])
        self.y_data = torch.from_numpy(xy[:, [-1]])
 
    def __getitem__(self, index):
        return self.x_data[index], self.y_data[index]
 
    def __len__(self):
        return self.len
 
 
dataset = DiabetesDataset('./dataset/diabetes.csv.gz')
train_loader = DataLoader(dataset=dataset, batch_size=32, shuffle=True, num_workers=0) #num_workers 多线程
 
 
# design model using class
 
 
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()
 
    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()
 
# construct loss and optimizer
criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)
 
# training cycle forward, backward, update
if __name__ == '__main__':
    for epoch in range(100):
        for i, data in enumerate(train_loader, 0): # train_loader 是先shuffle后mini_batch
            inputs, labels = data
            y_pred = model(inputs)
            loss = criterion(y_pred, labels)
            print(epoch, i, loss.item())
 
            optimizer.zero_grad()
            loss.backward()
 
            optimizer.step()