pytorch入门（一）

import torch
# 显示是否使用GPU
print(torch.cuda.is_available())
# 查看成员以及手册
print(dir(torch))
print(dir(torch.AVG))  # =>abc
print(help(torch.AVG))

# pytorch的加载数据方法：
# 一、 Dataset：提供一种方式及其label
# 二、Dataloader：为网络提供不同的数据形式

二、数据集加载 Dataset

from torch.utils.data import Dataset
import cv2
from PIL import Image
import os

# dataset代码实战
class MyData(Dataset):
    def __init__(self, root_dir, label_path):
        # 初始化操作
        self.root_dir = root_dir
        self.label_path = label_path
        self.img_dir = os.path.join(self.root_dir, self.label_path)
        self.img_path_list = os.listdir(self.img_dir)
        print(self.img_path_list)

    def __getitem__(self, index):
        # 获取数据集元素的信息
        img_path = self.img_path_list[index]
        print("getitem:",img_path)
        img = Image.open(os.path.join(self.img_dir ,img_path))
        label = self.label_path
        return img, label

    def __len__(self):
        # 返回长度
        return len(self.img_path_list)


ant_dataset = MyData(r"E:\\data\\hymenoptera_data\\train","ants")  # dataset
bee_dataset = MyData(r"E:\\data\\hymenoptera_data\\train","bees")  # dataset

# img, label = ant_dataset[0]
# # 可以把dataset当成数组的新式，每次都会执行__getitem__函数获取对应index的信息：img、label
# print(img, label)
# img.show()

# 数据集拼接操作，两个数据集相加操作:
train_dataset = ant_dataset+bee_dataset
print(len(train_dataset),len(ant_dataset),len(bee_dataset)) 

三、tensorboard的使用

from torch.utils.tensor
writer = SummaryWriter("logs2")   # 自动创建
图片添加：writer.add_image("Tensor_img",transe_img )
低纬数据：writer.add_scalar("y=x",2*i,i)

# Tensorboard的使用：训练可视化：loss
# 以前只能在tf中使用
# 图像变化，transform的使用

from torch.utils.tensorboard import SummaryWriter  # 写入、可视化操作（pip install ）
writer = SummaryWriter("logs")
for i in range(100):
    writer.add_scalar("y=x",2*i,i)  #低纬数据
writer.close()

from torch.utils.tensorboard import SummaryWriter
# 创建实例化对象、并且指定保存文件路径(自动创建文件夹）
writer = SummaryWriter("logs2")   # 创建保存文件
transe_img = tensor_trans(img)
print(transe_img)
# 添加
writer.add_image("Tensor_img",transe_img )
# 关闭
writer.close()

 

四、transforms工具包（浏览）、tensor的属性

from torchvision import transforms
# 一、 ctrl+tal=7： 显示脚本所有的内容
# 查看transforms.py、工具箱:totensor、resize
# 二、 transforms.ToTensor
from PIL import Image
img_path =  "E:\\data\\hymenoptera_data\\train\\ants\\69639610_95e0de17aa.jpg"
img = Image.open(img_path) 
print(img)  # 
# img.show()

tensor_trans = transforms.ToTensor()
print(tensor_trans)  #ToTensor()  对象
transe_img = tensor_trans(img)  # 转换
print(transe_img)  # tensor([[[0.9294, 0.933……

print(transforms.ToTensor()(img))  # 等同上面的过程

transform（ctrl+ Alt +7）显示的脚本属性功能

ipython运行后显示的tensor属性：包含grad等梯度下降所需的属性

五、 transforms工具箱的进一步了解

*补充知识（内置函数__call__():可以利用 对象名() 调用） tansforms实现变化的本质就是调用__call__()方法

class Person:
    def __call__(self, name):
        print("__call__","hello",name)
    def hello(self,name):
        print("hello",name)

p = Person()
p("hdl")  #可以利用这种形式调用—__call__
p.hello("hdl2")

 Compose源码截取：transforms together(操作的集合)

class Compose(object):
    """Composes several transforms together.

    Args:
        transforms (list of ``Transform`` objects): list of transforms to compose.

    Example:
        >>> transforms.Compose([
        >>>     transforms.CenterCrop(10),
        >>>     transforms.ToTensor(),
        >>> ])
    """

归一化操作：Normal

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

# 提前准备PIL图片、SummaryWriter文件
img_path =  "E:\\data\\hymenoptera_data\\train\\ants\\69639610_95e0de17aa.jpg"
img = Image.open(img_path)
writer = SummaryWriter("logs4")

# 定义操作
T1_Totensor = transforms.ToTensor()
T2_Normalize1 = transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5])
T3_Normalize2 = transforms.Normalize([3,4,5],[3,4,5])
T4_Normalize3 = transforms.Normalize([7,4,9],[1,3,6])

# 实现操作、获取图片
tensor_img = T1_Totensor(img)
normal_img1 = T2_Normalize1(tensor_img)
normal_img2 = T3_Normalize2(tensor_img)
normal_img3 = T4_Normalize3(tensor_img)

# 写入文件：add_image(tag, img_tensor, global_step=None)
writer.add_image("tensor_img", tensor_img)
writer.add_image("normal_img", normal_img1,1)
writer.add_image("normal_img", normal_img2,2)
writer.add_image("normal_img", normal_img3,3)

normal_img可以看出图片变化情况

pycharm取消大小写匹配

 Transforms.Resize((512,512))  #PIL->PIL

# Resize操作
T5_Resize512 = transforms.Resize((512,512))   # PIL -> PIL
print(img.size)
img512 = T5_Resize512(img)
print(img512.size)
tensor_img512 = T1_Totensor(img512)

 Transforms.Compose()

# Compose操作！
T6_Compose = transforms.Compose([T5_Resize512,T1_Totensor])
imgCompose = T6_Compose(img)
print(imgCompose.shape)
# 一步
print(transforms.Compose([T5_Resize512,T1_Totensor])(img).shape)  #torch.Size([3, 512, 512])

 Transforms.RandomCrop 随机裁剪

# 随机裁剪
T7_RandomCrop = transforms.RandomCrop(50)
T8_RandomCropWH = transforms.RandomCrop((50,100))
T9_ComT7 = transforms.Compose([T7_RandomCrop,T1_Totensor])
T10_ComT8 = transforms.Compose([T8_RandomCropWH,T1_Totensor])


for i in range(10):
    img_crop = T9_ComT7(img)
    writer.add_image("crop",img_crop,i)
    
for i in range(10):
    img_crop = T10_ComT8(img)
    writer.add_image("crop2",img_crop,i)

 

六、 datasets与transforms的联合使用

  torchvision模块介绍（包含dataset、transforms）

# torchvision的各种模块
from torchvision import transforms  # 图像操作
from torchvision import datasets  # 数据集
from torchvision import models   # 常见的神经网络，有的预训练好了
from torchvision import ops  # 少见的操作
from torchvision import utils # 常见的小工具

1. torchvision.datasets.CIFAR10 数据集的获取

import torchvision

# 获取dataset里面的数据集
train_set = torchvision.datasets.CIFAR10("./dataset",train=True,download=True)   # 自动下载数据集
test_set = torchvision.datasets.CIFAR10("./dataset",train=False,download=True)
img, target = train_set[0]   
print("shape",len(train_set))  # 50000
print("shape",len(test_set))  # 10000

# 无trainfrom：  6
# 有trainfrom：tensor([[[0.2314,……  6


# 将数据集写入tensorboard
writer = SummaryWriter("logs4")
for i in range(10):
    img, target = train_set[i]
    writer.add_image("dataset1",img,i)

dataset.CIFAR10参数：

• 1. 自动创建文件夹 
• 2. 是否是训练集
• 3.是否从网上下载（先判断是否存在，可以点击函数进去查看下载地址）
• 4. transform：获取数据的批量操作

七、 DataLoader（torch.utils.data）

实现批量抽取：

img, target = train_set[0]，

img1, target1 = train_set[1]，

img2, target2 = train_set[2]，

img3, target3 = train_set[3]

打包返回

imgs = img，img1，img2，img3

targets = target,  target1,  target2,  target3 

# dataloader: 从dataset取数据的工具,可迭代对象
from torch.utils.data import DataLoader
test_Loader = DataLoader(dataset=test_set, batch_size=64, shuffle=True, num_workers=0, drop_last=False)
i = 0
for data in test_Loader:
    imgs, targets = data  # torch.Size([4, 3, 32, 32]) tensor([5, 6, 2, 8])
    writer.add_images("loader1", imgs, i)  # 添加多张图片：add_images
    i+=1
    print("第{}次迭代".format(i))  # 157次迭代，157*64=10000

writer.close()

参数介绍：

• dataset：dataset对象，从里面取数据
• batch_size：一次取多少张
• shuffle（False）：是否打乱
• num_workers（0）：多线程，默认为0，仅主线程工作
• drop_last（Ture）：最后不满batch_size的样本是否丢弃

 分两批取数据

for epoch in range(2):
    i = 0
    for data in test_Loader:
        imgs, targets = data  # torch.Size([4, 3, 32, 32]) tensor([5, 6, 2, 8])
        writer.add_images("loader:Epoch_{}".format(epoch), imgs, i)  # 添加多张图片：add_images
        i+=1

 

八、torch.nn(Netual Net)

nn各模块介绍

第一个网络

import torch
from torch import nn

class Net1(nn.Module):
    def __init__(self):
        super(Net1, self).__init__()
        # 通常在这里定义变化的方法

    def forward(self,input):
        # 可使用 output = 网络对象名(input)
        print("forward run")
        output = input+1
        return output

n1 = Net1()
x = torch.tensor(1.0)  # tensor(1.)
o = n1(x) #tensor(2.)
print(o)

 卷积操作演示:torch.nn.functional.conv2d（用于2维数据，conv1d，conv3d不常用）

import torch.nn.functional as F

input = torch.tensor([
    [1,2,0,3,1],
    [0,1,2,3,1],
    [1,2,1,0,0],
    [5,2,3,1,1],
    [2,1,0,1,1]
])

kernel = torch.tensor([
    [1,2,1],
    [0,1,0],
    [2,1,0]
])
print(input.shape)
print(kernel.shape)
input = torch.reshape(input, [1,1,5,5])
kernel = torch.reshape(kernel, (1,1,3,3))
print(input.shape)
print(kernel.shape)

import torch.nn.functional as F

output = F.conv2d(input, kernel, stride=1)
print(output)
'''tensor([[[[10, 12, 12],
          [18, 16, 16],
          [13,  9,  3]]]])'''

output = F.conv2d(input, kernel, stride=2)
print(output)
'''tensor([[[[10, 12],
          [13,  3]]]])'''

output = F.conv2d(input, kernel, stride=1, padding=1)
print(output)
'''tensor([[[[ 1,  3,  4, 10,  8],
          [ 5, 10, 12, 12,  6],
          [ 7, 18, 16, 16,  8],
          [11, 13,  9,  3,  4],
          [14, 13,  9,  7,  4]]]])'''

搭建卷积（from torch.nn import Conv2d）网络

import torch
import torchvision
from torch import nn
import torchvision
from torch.nn import Conv2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset = torchvision.datasets.CIFAR10("dataset", train=False, transform=torchvision.transforms.ToTensor(),
                                       download=True)

dataloader = DataLoader(dataset, batch_size=64)

class Net2_conv(nn.Module):
    def __init__(self):
        super(Net2_conv, self).__init__()
        self.conv1 = Conv2d(in_channels=3, out_channels=6, kernel_size=3, stride=1,padding=0)

    def forward(self, input):
        x = self.conv1(input)
        return x

n2 = Net2_conv()
print(n2)

writer = SummaryWriter("logs5")
step = 0
for data in dataloader:
    imgs, targets = data
    output = n2(imgs)  # torch.Size([64, 3, 32, 32])  ->  torch.Size([64, 6, 30, 30])
    # torch.Size([64, 6, 30, 30]) -》 torch.Size([-1, 3, 30, 30])
    output = torch.reshape(output, (-1,3,30,30))  # torch.Size([128, 3, 30, 30])
    writer.add_images("input",imgs,step)
    writer.add_images("output",output,step)  # 卷积后的图像：超过3个通道不知道怎么显示：尺寸变换
    step = step+1

注意

• 搭建卷积层的Conv2d来自 torch.nn，而上一个实例（基于过程的卷积变换）的conv2d来自torch.nn.functional
• tensorboard显示的图片只能是三通道的，超过的可以通过torch.reshape变换

 

可以看出相邻两列的图片来自同一个卷积源

池化层

最大池化（下采样）