Pytorch学习笔记-(xiaotudui)
常用的包import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriterPytorch
pytorch安装
准备环境
[*]安装Ancona工具
[*]安装python语言
[*]安装pycharm工具
以上工作安装完成后，开始真正的pytorch安装之旅，别担心，很容易
1.打开Ancona Prompt创建一个pytorch新环境
conda create -n pytorch python=版本号比如3.11后面步骤都是y同意安装
2.激活环境
同样在Ancona Prompt中继续输入如下指令
conda activate pytorch
3.去pytorch官网找到下载pytorch指令，根据个人配置进行选择
[*]window下一般选择Conda
[*]Linux下一般选择Pip
这里要区分自己电脑是否含有独立显卡，没有的选择cpu模式就行。
如果有独立显卡，那么去NVIDIA官网查看自己适合什么版本型号进行选择即可。
如果有独立显卡，在Ancona Prompt中输入如下指令，返回True即可确认安装成功。
torch.cuda.is_available()如果没有cpu我们通过pycharm来进行判断，首先创建一个pytorch工程，如下所示：
import torch
print(torch.cuda.is_available())
print(torch.backends.cudnn.is_available())
print(torch.cuda_version)
print(torch.backends.cudnn.version())
print(torch.__version__)是不是发现输出false， false， None, None，是不是以为错了。不，那是因为我们安装的是CPU版本的，压根就没得cuda，cudnn这个东西。我们只要检测python版本的torch（PyTorch）在就行。
ok！恭喜你成功完成安装pytroch！接下来开启你的学习之路吧！
引言：python中的两大法宝函数
[*]这里1、2、3、4是分隔区
# 查看torch里面有什么
for i in range(len(dir(torch))):
print(f"{dir(torch)}")
pytorch加载数据初认识
import import torch
from torch.utils.data import Dataset
[*]看看Dataset里面有什么：
Dataset代码实战
from torch.utils.data import Dataset
from 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)# 根路径和最后的路径进行拼接
self.img_path = os.listdir(self.path)# 路径地址img_path 就是第一张地址
def __getitem__(self, idx):
"""
读取每个照片
:param idx:
:return:
"""
img_name = self.img_path
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):
"""
查看图片个数，即数据集个数
:return:
"""
return len(self.img_path)
# img_path = "E:\\Project\\Code_Python\\Learn_pytorch\\learn_pytorch\\dataset\\training_set\\cats\\cat.1.jpg"
# img = Image.open(img_path)
# print(img)
# img.show()
root_dir = "dataset/training_set"
cats_label_dir = "cats"
dogs_label_dir = "dogs"
cats_dataset = MyData(root_dir, cats_label_dir)
dogs_dataset = MyData(root_dir, dogs_label_dir)
img1, label1 = cats_dataset
img2, label2 = dogs_dataset
# img1.show()
# img2.show()
train_dataset = cats_dataset + dogs_dataset # 合并数据集
print(len(train_dataset))
print(len(cats_dataset))
print(len(dogs_dataset))TensorBoard的使用（一）
from torch.utils.tensorboard import SummaryWriter
writer = SummaryWriter("logs")# 事件文件存储地址
# writer.add_image()
# y = x
for i in range(100):
writer.add_scalar("y=2x", 2*i, i)# 标量的意思 参数2*i 是x轴i是y轴
writer.close()
[*]安装tensorboard
pip install tensorboard
[*]运行tensorboard
tensorboard --logdir="logs" --port=6007（这里是指定端口号，也可以不写--port，默认6006）
[*]利用Opencv读取图片，获得numpy型图片数据
[*]import numpy as np
from torch.utils.tensorboard import SummaryWriter
import cv2
writer = SummaryWriter("logs")# 事件文件存储地址
img_array = cv2.imread("./dataset/training_set/cats/cat.2.jpg")
# print(img_array.shape)
writer.add_image("test",img_array,2,dataformats='HWC')
# y = x
for i in range(100):
writer.add_scalar("y=2x", 2 * i, i)# 标量的意思
writer.close()
Transforms使用
!(./pytorch截图/Snipaste_2023-11-01_10-52-09.png)from torchvision import transforms
from PIL import Image
# python当中的用法
# tensor数据类型
# 通过transforms.ToTensor去解决两个问题
# 1.transforms如何使用（pyhton）
# 2.为什么需要Tensor数据类型：因为里面包装了神经网络模型训练的数据类型
# 绝对路径 E:\Project\Code_Python\Learn_pytorch\learn_pytorch\dataset\training_set\cats\cat.6.jpg
# 相对路径 dataset/training_set/cats/cat.6.jpg
img_path = "dataset/training_set/cats/cat.6.jpg"
img = Image.open(img_path)
# 1.transforms如何使用（pyhton）
tensor_trans = transforms.ToTensor()
tensor_img = tensor_trans(img)
print(tensor_img.shape)
常见的Transforms
from PIL import Image
from torchvision import transforms
from torch.utils.tensorboard import SummaryWriter
writer = SummaryWriter("logs")
img = Image.open("dataset/training_set/cats/cat.11.jpg")
print(img)
# ToTensor的使用
trans_totensor = transforms.ToTensor()
img_tensor = trans_totensor(img)
writer.add_image("ToTensor", img_tensor)
# Normalize
print(img_tensor)
trans_norm = transforms.Normalize(, )
img_norm = trans_norm(img_tensor)
print(img_norm)
writer.add_image("Normalize", img_norm, 0)
# Resize
print(img.size)
trans_resize = transforms.Resize((512, 512))
# img PIL -> resize -> img_resize PIL
img_resize = trans_resize(img)
# img_resize PIL -> totensor -> img_resize tensor
img_resize = trans_totensor(img_resize)
# print(img_resize)
writer.add_image("Resize", img_resize, 1)
# Compose - resize - 2
trans_resize_2 = transforms.Resize(144)
# PIL -> PIL -> tensor数据类型
trans_compose = transforms.Compose()
img_resize_2 = trans_compose(img)
writer.add_image("Resize_Compose", img_resize_2, 2)
writer.close()torchvision中的数据集使用
import torchvision
from torch.utils.tensorboard import SummaryWriter
dataset_transforms = torchvision.transforms.Compose([
torchvision.transforms.ToTensor()
])
# 下载数据集
train_set = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=dataset_transforms, download=True)
test_set = torchvision.datasets.CIFAR10(root="./dataset", train=False, transform=dataset_transforms, download=True)
print(test_set)
print(test_set.classes)
img, target = test_set
print(img)
print(target)
print(test_set.classes)
# img.show()
writer = SummaryWriter("p10")
for i in range(10):
img, target = test_set
writer.add_image("test_set", img, i)
writer.close()
DataLoad的使用
import torchvision
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
# 准备的测试数据集
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)
# 这里数据集是之前官网下载下来的
# 测试数据集中第一张图片及target
img, target = test_data
print(img.shape)
print(target)
writer = SummaryWriter("dataloader")
step = 0
for data in test_loader:
imgs, targets = data
# print(imgs.shape)
# print(targets)
writer.add_images("test_data", imgs, step)
step = step + 1
writer.close()
[*]最后一次数据不满足64张于是将参数设置drop_last=True
import torchvision
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
# 准备的测试数据集
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)
# 这里数据集是之前官网下载下来的
# 测试数据集中第一张图片及target
img, target = test_data
print(img.shape)
print(target)
writer = SummaryWriter("dataloader_drop_last")
step = 0
for data in test_loader:
imgs, targets = data
# print(imgs.shape)
# print(targets)
writer.add_images("test_data", imgs, step)
step = step + 1
writer.close()
[*]shuffle 使用
[*]True 两边图片选取不一样
[*]False两边图片选取一样
import torchvision
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
# 准备的测试数据集
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)
# 这里数据集是之前官网下载下来的
# 测试数据集中第一张图片及target
img, target = test_data
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("Eopch: {}".format(epoch), imgs, step)
step = step + 1
writer.close()
神经网络的基本骨架
import torch
from torch import nn
class ConvModel(nn.Module):
def __init__(self, *args, **kwargs) -> None:
super().__init__(*args, **kwargs)
def forward(self, input):
output = input + 1
return output
convmodel = ConvModel()
x = torch.tensor(1.0)
output = convmodel(x)
print(output)卷积操作
import torch
import torch.nn.functional as F
# 卷积输入
input = torch.tensor([,
,
,
,
])
# 卷积核
kernel = torch.tensor([,
,
])
# 进行尺寸转换
input = torch.reshape(input, (1, 1, 5, 5))
kernel = torch.reshape(kernel, (1, 1, 3, 3))
print(input.shape)
print(kernel.shape)
output = F.conv2d(input, kernel, stride=1)
print(output)
output2 = F.conv2d(input, kernel, stride=2)
print(output2)
[*]padding
# padding默认填充值是0
output3 = F.conv2d(input, kernel, stride=1, padding=1)
print(output3)结果：
tensor([[[[ 1,3,4, 10,8],
[ 5, 10, 12, 12,6],
[ 7, 18, 16, 16,8],
,
]]])
神经网络-卷积层
import torch
import torchvision
from torch.utils.data import DataLoader
from torch import nn
from torch.nn import Conv2d
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 NN_Conv2d(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = Conv2d(in_channels=3, out_channels=6, kernel_size=3, stride=1, padding=0)
def forward(self, x):
x = self.conv1(x)
return x
nn_conv2d = NN_Conv2d()
# print(nn_conv2d)
writer = SummaryWriter("./logs")
step = 0
for data in dataloader:
imgs, targets = data
output = nn_conv2d(imgs)
print(f"imgs: {imgs.shape}")
print(f"output: {output.shape}")
# 输入的大小 torch.Size()
writer.add_images("input", imgs, step)
# 卷积后输出的大小 torch.Size(
output = torch.reshape(output, (-1, 3, 30, 30))
writer.add_images("output", output, step)
step += 1
# import numpy as np
import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.tensorboard import SummaryWriter
import cv2
from torchvision import transforms
# 创建卷积模型
class NN_Conv2d(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = Conv2d(in_channels=3, out_channels=6, kernel_size=3, stride=1, padding=1)
def forward(self, x):
x = self.conv1(x)
return x
nn_conv2d = NN_Conv2d()
writer = SummaryWriter('logs_test')
input_img = cv2.imread("dataset/ice.jpg")
# 转化为tensor类型
trans_tensor = transforms.ToTensor()
input_img = trans_tensor(input_img)
# 设置input输入大小
input_img = torch.reshape(input_img, (-1, 3, 1312, 2100))
print(input_img.shape)
writer.add_images("input_img", input_img, 1)
# 进行卷积输出
output = nn_conv2d(input_img)
output = torch.reshape(output, (-1, 3, 1312, 2100))
print(output.shape)
writer.add_images('output_test', output, 1)
writer.close()
神经网络-最大池化
import torch
from torch import nn
from torch.nn import MaxPool2d
input_img = torch.tensor([,
,
,
,
], dtype=torch.float32)
input_img = torch.reshape(input_img, (-1, 1, 5, 5))
print(input_img.shape)
# 简单的搭建卷积神经网络
class Nn_Conv_Maxpool(nn.Module):
def __init__(self):
super().__init__()
self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=True)
def forward(self, input_img):
output = self.maxpool1(input_img)
return output
nn_conv_maxpool = Nn_Conv_Maxpool()
output = nn_conv_maxpool(input_img)
print(output)import torch
import torchvision
from torch import nn
from torch.nn import MaxPool2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
dataset = torchvision.datasets.CIFAR10('./dataset', train=False, download=True,
transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=64)
# 简单的搭建卷积神经网络
class Nn_Conv_Maxpool(nn.Module):
def __init__(self):
super().__init__()
self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=True)
def forward(self, input_img):
output = self.maxpool1(input_img)
return output
nn_conv_maxpool = Nn_Conv_Maxpool()
writer = SummaryWriter('logs_maxpool')
step = 0
for data in dataloader:
imgs, targets = data
writer.add_images('input', imgs, step)
output = nn_conv_maxpool(imgs)
writer.add_images('output', output, step)
step += 1
writer.close()
神经网络-非线性激活
[*]ReLU
import torch
from torch import nn
from torch.nn import ReLU
input = torch.tensor([,
[-1, 3]])
input = torch.reshape(input, (-1, 1, 2, 2))
print(input.shape)
class Nn_Network_Relu(nn.Module):
def __init__(self):
super().__init__()
self.relu1 = ReLU()
def forward(self, input):
output = self.relu1(input)
return output
nn_relu = Nn_Network_Relu()
output = nn_relu(input)
print(outputz)
[*]使用图片进行演示
import torch
import torchvision
from torch import nn
from torch.nn import ReLU
from torch.nn import Sigmoid
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
input = torch.tensor([,
[-1, 3]])
input = torch.reshape(input, (-1, 1, 2, 2))
print(input.shape)
dataset = torchvision.datasets.CIFAR10('./dataset', train=False, download=True,
transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=64)
class Nn_Network_Relu(nn.Module):
def __init__(self):
super().__init__()
self.relu1 = ReLU()
self.sigmoid1 = Sigmoid()
def forward(self, input):
output = self.sigmoid1(input)
return output
nn_relu = Nn_Network_Relu()
nn_sigmoid = Nn_Network_Relu()
writer = SummaryWriter('logs_sigmoid')
step = 0
for data in dataloader:
imgs, targets = data
writer.add_images("input_imgs", imgs, step)
output = nn_sigmoid(imgs)
writer.add_images("output", output, step)
step += 1
writer.close()
神经网络-线性层及其他层
[*]线性层（linear layer）通常也被称为全连接层（fully connected layer）。在深度学习模型中，线性层和全连接层指的是同一种类型的神经网络层，它将输入数据与权重相乘并加上偏置，然后通过一个非线性激活函数输出结果。可以实现特征提取、降维等功能。
[*]以VGG16网络模型为例，全连接层共有3层，分别是4096-4096-1000，这里的1000为ImageNet中数据集类别的数量。
import torch
import torchvision
from torch.utils.data import DataLoader
from torch import nn
from torch.nn import Linear
dataset = torchvision.datasets.CIFAR10('./dataset', train=False, transform=torchvision.transforms.ToTensor(),
download=True)
dataloader = DataLoader(dataset, batch_size=64)
class Nn_LinearModel(nn.Module):
def __init__(self):
super().__init__()
self.linear1 = Linear(196608, 10)
def forward(self, input):
output = self.linear1(input)
return output
nn_linearmodel = Nn_LinearModel()
for data in dataloader:
imgs, targets = data
print(imgs.shape)
output = torch.flatten(imgs)
print(output.shape)
output = nn_linearmodel(output)
print(output.shape)
[*]torch.flatten: 将输入（Tensor）展平为一维张量
[*]batch_size 一般不展开，以MNIST数据集的一个 batch 为例将其依次转化为例：
-> ->
神经网络-实践以及Sequential
import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear
class Nn_SeqModel(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = Conv2d(3, 32, 5, padding=2)
self.maxpool1 = MaxPool2d(2)
self.conv2 = Conv2d(32, 32, 5, padding=2)
self.maxpool2 = MaxPool2d(2)
self.conv3 = Conv2d(32, 64, 5, padding=2)
self.maxpool3 = MaxPool2d(2)
self.flatten = Flatten()
self.linear1 = Linear(1024, 64)
self.linear2 = Linear(64, 10)
def forward(self, x):
x = self.conv1(x)
x = self.maxpool1(x)
x = self.conv2(x)
x = self.maxpool2(x)
x = self.conv3(x)
x = self.maxpool2(x)
x = self.flatten(x)
x = self.linear1(x)
x = self.linear2(x)
return x
if __name__ == '__main__':
nn_seqmodel = Nn_SeqModel()
print(nn_seqmodel)
# 对网络模型进行检验
input = torch.ones((64, 3, 32, 32))
output = nn_seqmodel(input)
print(output.shape)Nn_SeqModel(
(conv1): Conv2d(3, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(maxpool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(conv2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(maxpool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(conv3): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(maxpool3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(flatten): Flatten(start_dim=1, end_dim=-1)
(linear1): Linear(in_features=1024, out_features=64, bias=True)
(linear2): Linear(in_features=64, out_features=10, bias=True)
)
torch.Size()
[*]Sequential 使代码更加简洁
import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
class Nn_SeqModel(nn.Module):
def __init__(self):
super().__init__()
# self.conv1 = Conv2d(3, 32, 5, padding=2)
# self.maxpool1 = MaxPool2d(2)
# self.conv2 = Conv2d(32, 32, 5, padding=2)
# self.maxpool2 = MaxPool2d(2)
# self.conv3 = Conv2d(32, 64, 5, padding=2)
# self.maxpool3 = MaxPool2d(2)
# self.flatten = Flatten()
# self.linear1 = Linear(1024, 64)
# self.linear2 = Linear(64, 10)
self.model1 = Sequential(
Conv2d(3, 32, 5, padding=2),
MaxPool2d(2),
Conv2d(32, 32, 5, padding=2),
MaxPool2d(2),
Conv2d(32, 64, 5, padding=2),
MaxPool2d(2),
Flatten(),
Linear(1024, 64),
Linear(64, 10)
)
def forward(self, x):
# x = self.conv1(x)
# x = self.maxpool1(x)
# x = self.conv2(x)
# x = self.maxpool2(x)
# x = self.conv3(x)
# x = self.maxpool2(x)
# x = self.flatten(x)
# x = self.linear1(x)
# x = self.linear2(x)
x = self.model1(x)
return x
if __name__ == '__main__':
nn_seqmodel = Nn_SeqModel()
print(nn_seqmodel)
# 对网络模型进行检验
input = torch.ones((64, 3, 32, 32))
output = nn_seqmodel(input)
print(output.shape)Nn_SeqModel(
(model1): Sequential(
(0): Conv2d(3, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(4): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(5): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(6): Flatten(start_dim=1, end_dim=-1)
(7): Linear(in_features=1024, out_features=64, bias=True)
(8): Linear(in_features=64, out_features=10, bias=True)
)
)
torch.Size()
if __name__ == '__main__':
nn_seqmodel = Nn_SeqModel()
print(nn_seqmodel)
# 对网络模型进行检验
input = torch.ones((64, 3, 32, 32))
output = nn_seqmodel(input)
print(output.shape)
# 查看网络结构
writer = SummaryWriter('./logs_seq')
writer.add_graph(nn_seqmodel, input)
writer.close()
[*]查看网络结构
损失函数与反向传播
[*]loos 损失函数
[*]注意输入和输出
import torch
from torch.nn import L1Loss
inputs = torch.tensor(, dtype=torch.float32)
targets = torch.tensor(, dtype=torch.float32)
inputs = torch.reshape(inputs, (1, 1, 1, 3))
targets = torch.reshape(targets, (1, 1, 1, 3))
loss = L1Loss()# reduction='sum'
result = loss(inputs, targets)
print(result)tensor(0.6667)
[*]交叉熵loss
x = torch.tensor()
y = torch.tensor()
x = torch.reshape(x, (1, 3))
loss_cross = nn.CrossEntropyLoss()
result_cross = loss_cross(x, y)
print(f"The result_cross of CrossEntropyLoss: {result_cross}")The result_cross of CrossEntropyLoss: 1.1019428968429565
[*]测试
import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriter
from torch.utils.data import DataLoader
dataset = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(),
download=True)
dataloader = DataLoader(dataset, batch_size=1)
class Nn_LossNetworkModel(nn.Module):
def __init__(self):
super().__init__()
self.model1 = Sequential(
Conv2d(3, 32, 5, padding=2),
MaxPool2d(2),
Conv2d(32, 32, 5, padding=2),
MaxPool2d(2),
Conv2d(32, 64, 5, padding=2),
MaxPool2d(2),
Flatten(),
Linear(1024, 64),
Linear(64, 10)
)
def forward(self, x):
x = self.model1(x)
return x
loss = nn.CrossEntropyLoss()
if __name__ == '__main__':
nn_lossmodel = Nn_LossNetworkModel()
for data in dataloader:
imgs, targets = data
outputs = nn_lossmodel(imgs)
result_loss = loss(outputs, targets)
print(f"the result_loss is : {result_loss}")
[*]梯度下降 进行反向传播
[*]debug测试查看 grad
if __name__ == '__main__':
nn_lossmodel = Nn_LossNetworkModel()
for data in dataloader:
imgs, targets = data
outputs = nn_lossmodel(imgs)
result_loss = loss(outputs, targets)
# print(f"the result_loss is : {result_loss}")
result_loss.backward()
print("ok")优化器
import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriter
from torch.utils.data import DataLoader
# 加载数据集转换为tensor类型
dataset = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(),
download=True)
# 使用DataLoader将数据集进行加载
dataloader = DataLoader(dataset, batch_size=1)
# 创建网络
class Nn_LossNetworkModel(nn.Module):
def __init__(self):
super().__init__()
self.model1 = Sequential(
Conv2d(3, 32, 5, padding=2),
MaxPool2d(2),
Conv2d(32, 32, 5, padding=2),
MaxPool2d(2),
Conv2d(32, 64, 5, padding=2),
MaxPool2d(2),
Flatten(),
Linear(1024, 64),
Linear(64, 10)
)
def forward(self, x):
x = self.model1(x)
return x
if __name__ == '__main__':
loss = nn.CrossEntropyLoss()
nn_lossmodel = Nn_LossNetworkModel()
optim = torch.optim.SGD(nn_lossmodel.parameters(), lr=0.01)
for data in dataloader:
imgs, targets = data
outputs = nn_lossmodel(imgs)
result_loss = loss(outputs, targets)
optim.zero_grad()
result_loss.backward()
optim.step()
if __name__ == '__main__':
loss = nn.CrossEntropyLoss()
nn_lossmodel = Nn_LossNetworkModel()
optim = torch.optim.SGD(nn_lossmodel.parameters(), lr=0.01)
for epoch in range(20):
running_loss = 0.0
for data in dataloader:
imgs, targets = data
outputs = nn_lossmodel(imgs)
result_loss = loss(outputs, targets)
optim.zero_grad()
result_loss.backward()
optim.step()
running_loss = running_loss + result_loss
print("running_loss: ", running_loss)Files already downloaded and verified
running_loss:tensor(18788.4355, grad_fn=)
running_loss:tensor(16221.9961, grad_fn=)
........
现有网络模型的使用以及修改
import torchvision
import torch
from torch import nn
# train_data = torchvision.datasets.ImageNet("./data_image_net", split="train",
# transform=torchvision.transforms.ToTensor(), download=True)
vgg16_false = torchvision.models.vgg16(pretrained=False)
vgg16_true = torchvision.models.vgg16(pretrained=True)
print('ok')
print(vgg16_true)
train_data = torchvision.datasets.CIFAR10('./dataset', train=True, transform=torchvision.transforms.ToTensor(),
download=True)
# vgg16_true.add_module('add_linear', nn.Linear(1000, 10))
vgg16_true.classifier.add_module('add_linear', nn.Linear(1000, 10))
print(vgg16_true)
print(vgg16_false)
vgg16_false.classifier = nn.Linear(4096, 10)
print(vgg16_false)网络模型的保存与读取
[*]save
import torch
import torchvision
from torch import nn
vgg16 = torchvision.models.vgg16(pretrained=False)
# 保存方式1: 模型结构+模型参数
torch.save(vgg16, "vgg16_method1.pth")
# 保存方式2： 模型参数（官方推荐）
torch.save(vgg16.state_dict(), "vgg16_method2.pth")
# 陷阱
class Nn_Model(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(3, 64, 3)
def forward(self, x):
x = self.conv1(x)
return x
nn_model = Nn_Model()
torch.save(nn_model, "nnModel_method1.pth")
[*]load
import torch
import torchvision
from torch import nn
from p19_model_save import *
# 加载方式1 ---> 对应保存方式1 ，加载模型
model = torch.load("vgg16_method1.pth")
# print(model)
# 加载方式2
model2 = torch.load("vgg16_method2.pth")
print(model2)
# 方式2 的回复网络模型结构
vgg16 = torchvision.models.vgg16(pretrained=False)
vgg16.load_state_dict(torch.load("vgg16_method2.pth"))
print(vgg16)
# 陷阱1
# class Nn_Model(nn.Module):
# def __init__(self):
# super().__init__()
# self.conv1 = nn.Conv2d(3, 64, 3)
#
# def forward(self, x):
# x = self.conv1(x)
# return x
model1 = torch.load("nnModel_method1.pth")
print(model1)完成的模型训练套路（一）
[*]建包 train.py 和 model.py
[*]model.py
import torch
from torch import nn
# 搭建神经网络
class Nn_Neural_NetWork(nn.Module):
def __init__(self):
super().__init__()
self.model = nn.Sequential(
nn.Conv2d(3, 32, 5, 1, 2),
nn.MaxPool2d(2),
nn.Conv2d(32, 32, 5, 1, 2),
nn.MaxPool2d(2),
nn.Conv2d(32, 64, 5, 1, 2),
nn.MaxPool2d(2),
nn.Flatten(),
nn.Linear(64 * 4 * 4, 64),
nn.Linear(64, 10)
)
def forward(self, x):
x = self.model(x)
return x
if __name__ == '__main__':
# 测试一下模型准确性
nn_model = Nn_Neural_NetWork()
input = torch.ones((64, 3, 32, 32))
output = nn_model(input)
print(output.shape)
[*]train.py
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from model import *
# 准备数据集
train_data = torchvision.datasets.CIFAR10(root='./data', train=True, transform=torchvision.transforms.ToTensor(),
download=True)
test_data = torchvision.datasets.CIFAR10(root='./data', train=False, transform=torchvision.transforms.ToTensor(),
download=True)
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为:{}".format(train_data_size))
print("测试数据集的长度为:{}".format(test_data_size))
# 利用DataLoader 来加载数据集
train_loader = DataLoader(train_data, batch_size=64)
test_loader = DataLoader(test_data, batch_size=64)
# 创建网络模型
nn_model = Nn_Neural_NetWork()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
# 优化器
# 1e-2 = 1 x (10)^(-2) = 1/100 = 0.01
learning_rate = 0.01
optimizer = torch.optim.SGD(nn_model.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 10
for i in range(epoch):
print("--------第{}轮训练开始-------".format(i + 1))
# 训练步骤开始
for data in train_loader:
imgs, targets = data
output = nn_model(imgs)
loss = loss_fn(output, targets)
# 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_step += 1
print("训练次数: {}, Loss: {}".format(total_train_step, loss.item()))完成的模型训练套路（二）
[*]train.py
[*]增加了tenorboard
[*]增加了精确度Accuracy
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriterfrom p20_model import *# 准备数据集train_data = torchvision.datasets.CIFAR10(root='./data', train=True, transform=torchvision.transforms.ToTensor(), download=True)test_data = torchvision.datasets.CIFAR10(root='./data', train=False, transform=torchvision.transforms.ToTensor(), download=True)train_data_size = len(train_data)test_data_size = len(test_data)print("训练数据集的长度为:{}".format(train_data_size))print("测试数据集的长度为:{}".format(test_data_size))# 利用DataLoader 来加载数据集train_loader = DataLoader(train_data, batch_size=64)test_loader = DataLoader(test_data, batch_size=64)# 创建网络模型nn_model = Nn_Neural_NetWork()# 损失函数loss_fn = nn.CrossEntropyLoss()# 优化器# 1e-2 = 1 x (10)^(-2) = 1/100 = 0.01learning_rate = 0.01optimizer = torch.optim.SGD(nn_model.parameters(), lr=learning_rate)# 设置训练网络的一些参数# 记录训练的次数total_train_step = 0# 记录测试的次数total_test_step = 0# 训练的轮数epoch = 10# （可加可不加） 添加tensorboardwriter = SummaryWriter('./logs_train')for i in range(epoch): print("--------第{}轮训练开始-------".format(i + 1)) # 训练步骤开始 for data in train_loader: imgs, targets = data output = nn_model(imgs) loss = loss_fn(output, targets) # 优化器优化模型 optimizer.zero_grad() loss.backward() optimizer.step() total_train_step += 1 if total_train_step % 100 == 0: print("训练次数: {}, Loss: {}".format(total_train_step, loss.item())) writer.add_scalar("train_loss", loss.item(), total_train_step) # 测试步骤开始 total_test_loss = 0 # 精确度 total_accuracy = 0 with torch.no_grad(): for data in test_loader: imgs, targets = data outputs = nn_model(imgs) loss = loss_fn(outputs, targets) total_test_loss += loss accuracy = (outputs.argmax(1) == targets).sum() total_accuracy += accuracy print("整体测试集上的Loss: {}".format(total_test_loss)) print("整体测试集上的正确率Accuracy: {}".format(total_accuracy / test_data_size)) writer.add_scalar("test_loss", total_test_loss, total_test_step) writer.add_scalar("test_accuracy", total_accuracy / test_data_size, total_test_step) total_test_step += 1 # 保存模型结果 torch.save(nn_model, "model_{}.pth".format(i)) print("模型保存")writer.close()
来源:https://www.cnblogs.com/Do1y/p/17819002.html
免责声明：由于采集信息均来自互联网，如果侵犯了您的权益，请联系我们【E-Mail:cb@itdo.tech】 我们会及时删除侵权内容，谢谢合作！
页:
[1]