pytorch自学P12-P16（b站up小土堆）[其一]

关于图片读写的操作

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

class Mydata(Dataset):

    def __init__(self, root_dir, label_dir):
        #根目录和标签目录合成path，获得图片路径地址
        self.root_dir = root_dir
        self.label_dir = label_dir
        self.path = os.path.join(self.root_dir, self.label_dir)
        self.img_path = os.listdir(self.path)
        #把图片地址输出成列表

    def __getitem__(self, idx):
        #获取功能，需要输入index
        img_name = self.img_path[idx]
        #输出图片名称
        img_item_path = os.path.join(self.root_dir, self.label_dir, img_name)
        #通过根目录，标签目录和图片名确定图片位置
        img = Image.open(img_item_path)
        label = self.label_dir
        return img, label

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

root_dir = "dataset/train"
ants_label_dir = "ants"
bees_label_dir = "bees"
ants_dataset = Mydata(root_dir, ants_label_dir)
bees_dataset = Mydata(root_dir, bees_label_dir)

tensorboard的可视化功能演示（绘制一张函数图像）

from torch.utils.tensorboard import SummaryWriter

writer = SummaryWriter("logs")

for i in range(100):
    writer.add_scalar("y=x", i, i)

writer.close()

P12_transform的应用

from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms

writer = SummaryWriter("logs")
img = Image.open("dataset/train/ants/0013035.jpg")
print(img)

#Totensor把图片集转化成tensor类型
trans_totensor = transforms.ToTensor()
img_tensor = trans_totensor(img)
writer.add_image("ToTensor", img_tensor)

#标准化操作
#归一化的公式：output[channel] = (input[channel] - mean[channel]) / std[channel]
print(img_tensor[0][0][0])
trans_norm = transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
#0.5对应RGB三层的均值和标准差
img_norm = trans_norm(img_tensor)
print(img_norm[0][0][0])
writer.add_image("Normalize", img_norm)

#设置大小
print(img.size)
trans_resize = transforms.Resize((300, 300))
#img PIL -> resize -> img_resize PIL
img_resize = trans_resize(img)
#img_resize PIL -> totensor -> img_resize.tensor
img_resize = trans_totensor(img_resize)
writer.add_image("Resize", img_resize, 0)
print(img_resize)

#Compose,把列表里的函数for执行
trans_resize_2 = transforms.Resize((200, 400))
#PIL->PIL->tensor
trans_compose = transforms.Compose([trans_resize_2, trans_totensor])
img_resize_2 = trans_compose(img)
writer.add_image("Resize_2", img_resize_2, 1)


#RandomCrop,随机裁剪
trans_random = transforms.RandomCrop((20, 10))
trans_compose_2 = transforms.Compose([trans_random, trans_totensor])
for i in range(10):
    img_crop = trans_compose_2(img)
    writer.add_image("RandomCrop", img_crop, i)
writer.close()

注：在新版中可以直接对PIL格式进行处理

#Compose,把列表里的函数for执行
trans_resize_2 = transforms.Resize((200, 400))
#PIL->PIL->tensor
trans_compose = transforms.Compose([trans_resize_2, trans_totensor])
img_resize_2 = trans_compose(img)
writer.add_image("Resize_2", img_resize_2, 1)

P14_在线数据集的下载

import torchvision
#定义训练集和测试集
train_set = torchvision.datasets.CIFAR10(root="./dataset", train=True, download=True)
test_set = torchvision.datasets.CIFAR10(root="./dataset", train=False, download=True)

print(test_set[0])
print(test_set.classes)
#test_set数据集由几个class组成
img, target = test_set[0]
print(img)
print(target)
#第一张图片是3，对应猫
print(test_set.classes[target])
img.show()

P14_对下载数据集可视化处理

import torchvision
from torch.utils.tensorboard import SummaryWriter

dataset_transform = torchvision.transforms.Compose([
    torchvision.transforms.ToTensor()
])

train_set = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=dataset_transform, download=True)
test_set = torchvision.datasets.CIFAR10(root="./dataset", train=False, transform=dataset_transform, download=True)

writer = SummaryWriter("p10")
for i in range(10):
    img, target = test_set[i]
    writer.add_image("test_set", img, i)

writer.close()

P15_DataLoader的使用

import torchvision
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=False)

#测试数据集中第一张图片及target,测试集数据由一张图片img和它所属的类别target组成
img, target = test_data[0]
print(img.shape)
print(target)

writer = SummaryWriter("dataloader")
step = 0
#把测试集的图片输出到tensorboard
for data in test_loader:
    imgs, targets = data
    writer.add_images("test_data", imgs, step)
    step = step + 1

writer.close()

P16_神经网络的基本模板

import torch
from torch import nn

class Tudui(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, input):
        output = input + 1
        return output

tudui = Tudui()
#进行土堆的初始化
x = torch.tensor(1.0)
#输入到forward的input中
output = tudui(x)
print(output)