PyTorch加载数据

PyTorch加载数据

Dataset:提供一种方式去获取数据及其label。

Dataloader:为后面的网络提供不同的数据形式。

导入包

from torch.utils.data import Dataset
from PIL import Image
import os

定义MyData类

class MyData(Dataset):

    def __init__(self, root_dir, label_dir):#初始化类
        self.root_dir = root_dir
        self.label_dir = label_dir
        self.path = os.path.join(self.root_dir,self.label_dir)#拼接路径
        self.img_path = os.listdir(self.path)#以列表形式获得图片的地址

    def __getitem__(self, idx):
        img_name = self.img_path[idx]
        img_item_path = os.path.join(self.root_dir,self.label_dir,img_name)
        img = Image.open(img_item_path)
        label = self.label_dir
        return img,label

    def __len__(self):
        return len(self.img_path)

测试

root_dir = "dataset/train"    #根路径
ants_label_dir = "ants_image" #标签路径
bees_label_dir = "bees_image"
ants_dataset = MyData(root_dir,ants_label_dir)
bees_dataset = MyData(root_dir,bees_label_dir)
train_dataset = ants_dataset + bees_dataset
print(len(train_dataset))

路径：

DataLoader:

import torch
import numpy as np
from torch.utils.data import Dataset
from torch.utils.data import 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,index):
        return self.x_data[index],self.y_data[index]
    
    def __len__(self):
        return self.len
    
dataset = DiabetesDataset('E:\\learning\\coding\\jupyter\\diabetes.csv.gz')
train_loader = DataLoader(dataset=dataset,
                          batch_size=32,
                          shuffle=True,
                          num_workers=0)

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()
criterion = torch.nn.BCELoss(size_average=True)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)


for epoch in range(100):
    for i,data in enumerate(train_loader,0):
        #准备数据
        inputs, labels = data
        #前向传播
        y_pred = model(inputs)
        loss = criterion(y_pred,labels)
        print(epoch,i,loss.item())
        #反向传播
        optimizer.zero_grad()
        loss.backward()
        #更新
        optimizer.step()