系列文章:
y_pred = model(x_data)是 使用所有的数据
想进行批处理,了解几个概念
import torch
from torch.utils.data import Dataset #Dataset抽象子类,需要继承
from torch.utils.data import DataLoader #DataLoade用来加载数据
def getitem(self, index):
def len(self): 返回数据集长度
dataset = DiabetesDataset() 构造DiabetesDataset对象
train_loader = DataLoader(dataset=dataset,
batch_size=32,
shuffle=True,
num_workers=2) 初始化参数
import numpy as np
import torch
import matplotlib.pyplot as plt
# Dataset是抽象类
from torch.utils.data import Dataset
# DataLoader 是抽象类
from torch.utils.data import DataLoader
class LogisticRegressionModel(torch.nn.Module):
def __init__(self):
super(LogisticRegressionModel, self).__init__()
# 输入维度8输出维度6
self.lay1 = torch.nn.Linear(8,6)
self.lay2 = torch.nn.Linear(6,4)
self.lay3 = torch.nn.Linear(4,1)
self.sigmod = torch.nn.Sigmoid()
def forward(self,x):
x = self.sigmod(self.lay1(x))
x = self.sigmod(self.lay2(x))
x = self.sigmod(self.lay3(x))
return x
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, index):
return self.x_data[index], self.y_data[index]
def __len__(self):
return self.len
dataset = DiabetesDataset("./datasets/diabetes.csv.gz")
train_loader = DataLoader(dataset=dataset, batch_size=32, shuffle=True)
model = LogisticRegressionModel()
criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr=0.005)
epoch_list = []
loss_list = []
for epoch in range(100):
for i, data in enumerate(train_loader, 0):
# 1-加载数据
inputs, label = data
# 2-forward
y_pred = model(inputs)
loss = criterion(y_pred, label)
epoch_list.append(epoch)
loss_list.append(loss.item())
optimizer.zero_grad()
# 3-反向传播
loss.backward()
# Update
optimizer.step()
plt.plot(epoch_list, loss_list)
plt.xlabel("epoch")
plt.ylabel("loss")
plt.show()
MNIST数据集导入
import torch
from torch.utils.data import DataLoader,Dataset
from torchvision import datasets,transforms
train_dataset = datasets.MNIST(root='./datasets/mnist', train=True,
transform=transforms.ToTensor(),
download=True)
test_dataset = datasets.MNIST(root='./datasets/mnist', train=False,
transform=transforms.ToTensor(),
download=True)
train_loader = DataLoader(dataset=datasets, batch_size=32,
shuffle=True)
test_loader = DataLoader(dataset=test_dataset, batch_size=32,
shuffle=False)
for batch_idx, (inouts, target) in enumerate(test_loader):
pass