pytorch学习1

dir():打开
help()：说明书
dataset是提供一种方式去获取数据及其lable
dataloader：为后面的网络提供不同的数据形式
我们要实现的功能：
1.我们要获取每一个数据及其lable
2.获取总共有多少数据

数据集的组织形式：1.训练数据集和验证数据集
2.训练图片和label（ocr数据集）（ocr就是字符识别，这个数据集是用来训练识别文字的）
3.lable直接写数据名字上

读取数据集

from torch.utils.data import Dataset, DataLoader
import numpy as np
from PIL import Image
import os
from torchvision import transforms
from torch.utils.tensorboard import SummaryWriter
from torchvision.utils import make_grid

writer = SummaryWriter("logs")

class MyData(Dataset):

    def __init__(self, root_dir, image_dir, label_dir, transform):
        self.root_dir = root_dir
        self.image_dir = image_dir
        self.label_dir = label_dir
        self.label_path = os.path.join(self.root_dir, self.label_dir)
        self.image_path = os.path.join(self.root_dir, self.image_dir)
        self.image_list = os.listdir(self.image_path)
        self.label_list = os.listdir(self.label_path)
        self.transform = transform
        # 因为label 和 Image文件名相同，进行一样的排序，可以保证取出的数据和label是一一对应的
        self.image_list.sort()
        self.label_list.sort()

    def __getitem__(self, idx):
        img_name = self.image_list[idx]
        label_name = self.label_list[idx]
        img_item_path = os.path.join(self.root_dir, self.image_dir, img_name)
        label_item_path = os.path.join(self.root_dir, self.label_dir, label_name)
        img = Image.open(img_item_path)

        with open(label_item_path, 'r') as f:
            label = f.readline()

        # img = np.array(img)
        img = self.transform(img)
        sample = {'img': img, 'label': label}
        return sample

    def __len__(self):
        assert len(self.image_list) == len(self.label_list)
        return len(self.image_list)

if __name__ == '__main__':
    transform = transforms.Compose([transforms.Resize((256, 256)), transforms.ToTensor()])
    root_dir = "dataset/train"
    image_ants = "ants_image"
    label_ants = "ants_label"
    ants_dataset = MyData(root_dir, image_ants, label_ants, transform)
    image_bees = "bees_image"
    label_bees = "bees_label"
    bees_dataset = MyData(root_dir, image_bees, label_bees, transform)
    train_dataset = ants_dataset + bees_dataset

    # transforms = transforms.Compose([transforms.Resize(256, 256)])
    dataloader = DataLoader(train_dataset, batch_size=1, num_workers=2)

    writer.add_image('error', train_dataset[119]['img'])
    writer.close()
    # for i, j in enumerate(dataloader):
    #     # imgs, labels = j
    #     print(type(j))
    #     print(i, j['img'].shape)
    #     # writer.add_image("train_data_b2", make_grid(j['img']), i)
    #
    # writer.close()

数据下载

import torchvision

# 准备的测试数据集
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor())

test_loader = DataLoader(dataset=test_data, batch_size=64, shuffle=True, num_workers=0, drop_last=True)

# 测试数据集中第一张图片及target
img, target = test_data[0]
print(img.shape)
print(target)

writer = SummaryWriter("dataloader")
for epoch in range(2):
    step = 0
    for data in test_loader:
        imgs, targets = data
        # print(imgs.shape)
        # print(targets)
        writer.add_images("Epoch: {}".format(epoch), imgs, step)
        step = step + 1

writer.close()