pytorch学习笔记1

一剑斩蛟龙

已于 2024-01-14 11:10:58 修改

阅读量1k

点赞数 18

文章标签： pytorch 学习笔记

于 2024-01-14 11:09:50 首次发布

本文链接：https://blog.csdn.net/weixin_46466484/article/details/135580821

版权

pytorch学习

python学习

dir()；打开
help()；说明书

pytorch获取数据

dataset

提供一种方式去获取数据及其label
功能1：如何获取每一个数据及其label

功能2：告诉我们总共有多少数据

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

class MyData(Dataset):
    def __init__(self,root_dir,label_dir):
        self.root_dir=root_dir
        self.label_dir=label_dir
        self.path=os.path.join(self.root_dir,self.label_dir)
        slef.img_path=os.listdir(self.path)
    
    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)
        
        
root_dir="dataset/train"
ants_label_dir="ants"
bees_lable_dir="bees"
ants_dataset=nyData(root_dir,ants_label_dir)
bees_dataset=MyData(root_dir,bees_label_dir)
train_ddataset=ants_dataset+bees_dataset# 数据集拼接

dataloader

tensorboard

form torch.utils.tensorboard import SummaryWriter

writer=SummaryWriter("logs")

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

命令行输入 tensorboard --logdir=logs --port=6008 #指定读取的文件夹，端口号，默认为6006

  from PIL import Image

  img=Image.open("1.jpg")

  type(img)#

  import opencv as cv2

  import numpy as np

  img_array=np.array(img)

  writer.add_image("test",img_aray,1,dataformats='HWC')

torchvision 中的transforms

工具箱：totensor resize


from torchvision import transforms
# transforms.totensor
# 为什么需要tensor数据类型
img_path="1.jpg"
img=Image.open(img_path)
tensor_trans=transforms.ToTensor()
tensor_img=tensor_trans(img)
````

- 常见的Transforms

  ```python
  输入   PIL       Image.open()
  输出   tensor     ToTensor()
  作用    narrays    cv2.imread()
  from PIL import Image
  form torchvision import transforms
  from torch.utils.tensorboard import SummaryWriter

  writer = SummaryWriter('logs')
  img= Image.open('1.jpg')
  #ToTensor
  trans_totensor=transforms.ToTensor()
  img_tensor=trans_totensor(img)
  writer.add_image('ToTensor',img_tensor)

  # tensorboard --logdir=logs

  # Normalize
  trans_norm=transform.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5])
  img_norm=trans_norm(img_tensor)
  writer.add_image("Normalize",img_norm)

  # Resize
  trans_resize=transforms.Resize(512,512)
  img_resize=trans_resize(img)
  img_resize=trans_totensor(img_resize)
  writer.add_image('Resize',img_resize)

  # Compose --resize

  trans_resize_2=transforms.Resize(512)
  trans_compose=transforms.Compose([trans_resize_2,
                                   trans_totensor])

  img_resize_2=trans_compose(img)
  writer.add_image("resize",img_resize_2,2)

  # RandomCrop
  trans_random=transforms.RandomCrop(512)
  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()

标准数据集的使用 torchvision

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

  train_set=torchvision.datasets.CIFAR10(root='./datasets',train=True,download=True,transform=dataset_transform)
  test_set=torchvision.datasets.CIFAR10(root='./datasets',train=False,download=True,transform=dataset_transform)
  img,target=test_set[0]
  import 
  writer=SummaryWriter('p10')
  for i in range(10):
      img,target=test_set[i]
      writer.add_image("test_set",img,i)
  writer.close()

  # tensorboard --logdir="p10"

DataLoader的使用
- 如何取数据，将数据与标签打包返回

import torchvision
form torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
test_data=torchvision.datasets.CIFAR10(root='./dataset',train=False,transform=torchvision.transforms.ToTensor())
test_loader=DataLoader(dataset=test_data,batch_size=4,shuttle=True,num_works=0,drop_last=False)
#测试数据集中第一张图片及target
img,target=test_data[0]

writer=SummaryWriter('dataloader')
step=0
for data in test_loader:
    imgs,targets=data
    writer.add_images('test_data',imgs,step)
    step+=1
writer.close()

nn.module使用

import torch.nn as nn 
import torch.nn.functional as F
class Model(nn.Module):
    def __init__(self):
        self.conv1=nn.Conv2d(1,20,5)
        self.conv2-nn.Conv2d(20,20,5)
    def forward(self,x):
        x=F.relu(slef.conv1(x))
        return F.relu(self.conv2(x))

Convolution Layers
- 对应位置相乘相加。。卷积核大小，步长，padding；；；padding=1,stride=1,得到与输入相同尺度的输出

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

import torch.nn.functional as F
output=F.conv2d(input,kernel,stride=1)
print(output)

#conv2d
in_channel(int),out_channel(int),kernel_size(int or tuple)
stride(int),padding(int)
import torch 
import torchvision
import torch.nn as nn
from torch.utils.data import Dataloader
dataset=torchvision.datasets.FIFAR10('./data',train=False,transform=torchvision.transforms.ToTensor(),download=True)
dataloader=Dataloader(dataset,batch_size=64)

class Model(nn.Module):
    def __init__(self):
        super(Model,slef).__init__()
        self.conv1=nn.Conv2d(3,6,3)
        
    def forward(slef,x):
        x=self.conv1(x)
        return x
   

writer=SummaryWriter('./logs')
step=0
model=Model()
for data in dataloader:
    imgs,targets=data
    output=model(imgs)
    
    writer.add_images('input',imgs,step)
    
   
    writer.add_images('output', torch.reshape(output,(-1,3,30,30)),step)
    step+=1

池化层

下采样

imoprt torch
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]],dtype=torch.float32)
input=torch.reshape(input,(-1,1,5,5))

class model(nn.Moule):
    def __init__(self):
        super(model,self).__init__()
        self.maxpoll1=nn.MaxPool2d(kernel_size=3,ceil_mode=True)
    def forward(self,input):
        output=self.maxpool1(input)
        return output
    
model=model()
output=model(input)

非线性激活

引入非线性， relu sigmoid


import torch
import torch.nn as nn

input=torch.tensor([[1,-0.5],
                  [-1,3]])
torch.reshape(input,(-1,1,2,2))

class Model(nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        self.relu=nn.Relu()
        
    def forward(self,x):
        return self.relu(x)
    
Model=Model()
output=Model(input)

Sequential

CIFAR10 model搭建

import torch
import torch.nn as nn

class Model(nn.module):
    def __init__(self):
        super(Model,self).__init__()
        self.conv1=nn.Conv2d(3,32,5,padding=2)
        self.maxpool1=nn.MaxPool2d(2)
        self.conv2=nn.Conv2d(32,32,5,padding=2)
        self.maxpool2=nn.MaxPool2d(2)
        self.conv3=nn.Conv2d(32,64,5,padding=2)
        self.maxpool3=nn.MaxPool2d(2)
        self.flatten=nn.Flatten()
        self.linear1=nn.Linear(1024,64)
        self.linear2=nn.Linear(64,10)
        
        
        #self.model1=nn.Sequential(nn.Conv2d(3,32,5,padding=2),
                                 nn.Maxppool2d(2),
                                 nn.Conv2d(32,32,5,padding=2),
                                 nn.Maxppool2d(2),
                                 nn.Conv2d(32,64,5,padding=2),
                                 nn.Maxppool2d(2),
                                 nn.Flatten(),
                                 nn.Linear(1024,64)
                                 nn.Linear(64,10))
    def forward(self,x):
        x=self.conv1(x)
        x=self.maxpoo11(x)
        x=self.conv2(x)
        x=self.maxpool2(x)
        x=self.conv3(x)
        x=self.maxpool3(x)
        x=self.flatten(x)
        x=self.linear1(x)
        x=self.linear2(x)
        
        #x=self.model1(x)
        return x
Model=Model()

一剑斩蛟龙

关注

18
点赞
踩
21

收藏

觉得还不错? 一键收藏
0
评论
pytorch学习笔记1

torchvision 中的transforms。功能1：如何获取每一个数据及其label。标准数据集的使用 torchvision。提供一种方式去获取数据及其label。功能2：告诉我们总共有多少数据。
复制链接

扫一扫