6_dataset_loader

数据加载

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


class DiabetesDataset(Dataset):
    def __init__(self):
        super(DiabetesDataset, self).__init__()
        xy = np.loadtxt('.//data//diabetes.csv.gz', delimiter=',', dtype=np.float32)
        self.len = xy.shape[0]
        self.x_data = torch.from_numpy(xy[:, 0 : -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

    def run(self):
        dataset = DiabetesDataset()
        train_loader = DataLoader(dataset=dataset, batch_size=32, shuffle=True, num_workers=2)

        for epoch in range(2):
            for i, data in enumerate(train_loader, 0):
                # 获取输入
                inputs, labels = data
                # 包装在Variable中
                inputs, labels = Variable(inputs), Variable(labels)
                print(epoch, i, 'inputs', inputs.data, 'labels', labels.data)


if __name__ == "__main__":
    print("Life is short, You need Python!")
    d = DiabetesDataset()
    d.run()