Pytorch学习
目录
- Pytorch环境配置及安装
- Dataset类代码实战
- TensorBoard的使用
-
- TensorBoard的安装
- add_scalar()的使用
- Transforms的使用
- 常见的Transforms
-
- 全部代码
- ToTensor类
- Normalize的使用
- Compose的用法
- RandomCrop()用法
- torchvision中的数据集使用
- DataLoader的使用
- 神经网络的基本骨架-nn.Module的使用
- 土堆说卷积操作（选看）
- 神经网络-卷积层
- 神经网络-最大池化的使用
- 神经网络-非线性激活
- 神经网络-线性层及其他层介绍
-
- 线性层
- 神经网络——搭建小实战和Sequential的使用
- 损失函数与反向传播
- 优化器
- 现有网络模型的使用及修改
- 网络模型的保存与读取
-
- 保存
- 读取
- 完整的模型训练套路
- 利用GPU训练
-
- 方式一
- 方式二
- 完整的模型验证套路
Pytorch环境配置及安装
点击链接跳转
Pytorch环境配置及安装
Dataset类代码实战
文件路径
#根据路径读取图片
from PIL import Image
img_path = "dataset/train/ants/0013035.jpg"
img = Image.open(img_path)
img.size #Out: (768, 512)
img.show() #显示图片
os.listdir()返回指定路径下的文件和文件夹列表
os.path.join()连接两个或更多的路径名组件
import os #os模块用于和系统进行交互
dir_path = "dataset/train/ants"
img_path_list = os.listdir(dir_path)
img_path_list[0] #Out: '0013035.jpg'
root_dir = "dataset/train"
label_dir = "ants"
path = os.path.join(root_dir,label_dir)
from torch.utils.data import Dateset
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)
self.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)
#实例化
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)
train_dataset = ants_dataset + bees_dataset #两个数据集相加
TensorBoard的使用
TensorBoard的安装
在anaconda prompt或者pytorch的terminal输入
pip install tensorboard
add_scalar()的使用
常用来绘制train/val loss
writer.add_scalar("y=x", i, i)
from torch.utils.tensorboard import SummaryWriter
writer = SummaryWriter("logs")
# y = x
for i in range(100):
writer.add_scalar("y=x", i, i)
writer.close()
tensorboard --logdir=logs
#logdir=事件文件所在文件夹名
为了防止端口和别人冲突
tensorboard --logdir=logs --logs=6007
writer.add_image()
image_path = "data/train/ants_image/0013035.jpg"
from PIL import Image
img = Image.open(image_path)
或者直接打印图片类型
print(type(img))
# Out:不满足要求
利用Opencv读取图片，获得numpy型图片数据，或者利用numpy.array()，对PIL图片进行转换
import cv2
cv_img = cv2.imread(img_path)
import numpy as np
img_array = np.array(img)
print(type(img_array))
# Out:
转化成功
from torch.utils.tensorboard import SummaryWriter
import numpy as np
from PIL import Image
writer = SummaryWriter("logs")
image_path = "data/train/ants_image/0013035.jpg"
img_PIL = Image.open(image_path)
img_array = np.array(img_PIL)
writer.add_image("test", img_array, 1, dataformats='HWC')# 1表示step1 因为通道数在最后，所以要指定dataformats
writer.close()
从PIL到numpy，需要在add_image()中指定shape中每一个数字/维表示的含义
Transforms的使用
from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
image_path = "data/train/ants_image/0013035.jpg"
img = Image.open(image_path)
writer = SummaryWriter("logs")
tensor_trans = transforms.ToTensor()
tensor_img = tensor_trans(img)
writer.add_image("Tensor_img", tensor_img)
writer.close()
常见的Transforms
_ _call_ _的作用
class Person:
def __call__(self, name):
print("__call__"+"Hello"+name)
def hello(self, name):
print("hello"+name)
person = Person()
person("Zhangsan")
person.hello("lisi")
全部代码
from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
writer = SummaryWriter("logs")
img = Image.open("data/train/ants_image/0013035.jpg")
print(img)
# ToTensor
trans_totensor = transforms.ToTensor()
img_tensor = trans_totensor(img)
writer.add_image("ToTensor", img_tensor)
# Normalize
print(img_tensor[0][0][0])
trans_norm = transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
img_norm = trans_norm(img_tensor)
print(img_norm[0][0][0])
writer.add_image("Normalize", img_norm)
# Resize
print(img.size)
trans_resize = transforms.Resize((512,512)) # 按指定大小
img_resize = trans_resize(img) # img PIL -> resize img_resize PIL
img_resize = trans_totensor(img_resize) # img_resize PIL -> totensor ->img_resize tenser
writer.add_image("Resize", img_resize, 0)
#Compose - resize - 2
trans_resize_2 = transforms.Resize(300) # 按比例
# PIL -> PIL -> tensor
trans_compose = transforms.Compose([trans_resize_2, trans_totensor])
img_resize_2 = trans_compose(img)
writer.add_image("Resize", img_resize_2, 1)
# RandomCrop
trans_random = transforms.RandomCrop(512) #或者指定h,w transforms.RandomCrop((500, 1000))
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()
ToTensor类
Normalize的使用
Resize()的使用
Compose的用法
（768×512）-> (450×300)
RandomCrop()用法
torchvision中的数据集使用
此节讲解如何将数据集和transform结合到一起
CIFAR10数据集
import torchvision
from torch.utils.tensorboard import SummaryWriter
dataset_transform = torchvision.transforms.Compose([
torchvision.transforms.ToTensor()#此处先只做一个操作
])
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)
img, target = test_set[0]
print(img)
print(target)
print(test_set.classes[target])
img.show()
print(test_set[0])
import torchvision
from torch.utils.tensorboard import SummaryWriter
dataset_transform = torchvision.transforms.Compose([
torchvision.transforms.ToTensor()#此处先只做一个操作
])
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):# 显示前10张照片
img, target = test_set[i]
writer.add_image("test_set", img, i)
writer.close()
DataLoader的使用
dataloader从dataset取数据
dataloader
import torchvision
# 准备的测试数据集
from torch.utils.data import DataLoader
test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor())
test_loader = DataLoader(dataset=test_data, batch_size=4, shuffle=True, num_workers=0, drop_last=False)
# 测试数据集中第一张图片及target
img, target = test_data[0]
print(img.shape)
print(target)
for data in test_loader:
imgs, targets = data
print(imgs.shape)
print(targets)
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=False)
# 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")
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为Ture的话，第一轮和第二轮会进行打乱
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=False)
# 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()
神经网络的基本骨架-nn.Module的使用
nn.Module
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()
x = torch.tensor(1.0)
output = tudui(x)
print(output)
土堆说卷积操作（选看）
nn.Conv2d
import torch
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]])
input = torch.reshape(input, (1, 1, 5, 5))#batchsize=1 channel=1
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)
output3 = F.conv2d(input, kernel, stride=1, padding=1)
print(output3)
神经网络-卷积层
torch.nn.Conv2d
import torch
import torchvision
from torch import nn
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 Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__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
tudui = Tudui()
# print(tudui)
writer = SummaryWriter("./logs")
step = 0
for data in dataloader:
imgs, targets =data
output = tudui(imgs)
# print(output.shape)
# print(imgs.shape)
# print(output.shape)
# torch.Size([64, 3, 32, 32])
writer.add_images("input", imgs, step)
# torch.Size([64, 6, 30, 30])
output = torch.reshape(output, (-1, 3, 30, 30)) # 为了可视化，需要reshape，但是这种处理不好
writer.add_images("output", output, step)
step = step + 1
vgg16 model
神经网络-最大池化的使用
torch.nn.MaxPool2d
import torch
from torch import nn
from torch.nn import MaxPool2d
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))
print(input.shape)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=True)
def forward(self, input):
output = self.maxpool1(input)
return output
tudui = Tudui()
output = tudui(input)
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, transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=64)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=True)
def forward(self, input):
output = self.maxpool1(input)
return output
tudui = Tudui()
writer = SummaryWriter("logs_maxpool")
step = 0
for data in dataloader:
imgs, targets = data
writer.add_images("inputs", imgs, step)
output = tudui(imgs)
writer.add_images("outputs", output, step)
step = step + 1
writer.close()
神经网络-非线性激活
ReLU
Sigmoid
import torch
from torch import nn
from torch.nn import ReLU
input = torch.tensor([[1, -0.5],
[-1, 3]])
input = torch.reshape(input, (-1, 1, 2, 2))
print(input.shape)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.relu1 = ReLU() # 默认inplace是False，所以要返回output
def forward(self, input):
output = self.relu1(input)
return output
tudui = Tudui()
output = tudui(input)
print(output)
import torch
import torchvision.datasets
from torch import nn
from torch.nn import ReLU, Sigmoid
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
input = torch.tensor([[1, -0.5],
[-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 Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.sigmoid1 = Sigmoid()
def forward(self, input):
output = self.sigmoid1(input)
return output
tudui = Tudui()
writer = SummaryWriter("./logs_sigmoid")
step = 0
for data in dataloader:
imgs, targets = data
writer.add_images("input", imgs, global_step=step)
output = tudui(imgs)
writer.add_images("output", output, step)
step += 1
writer.close()
神经网络-线性层及其他层介绍
正则化层
用的比较少
recurrent层
文字识别，特定的网络结构，用的不是很多
transformer层
特定的网络结构，用的不是很多
线性层
用的比较多
dropout层
防止过拟合
sparse层
特定的网络结构，自然语言处理
线性层
import torch
import torchvision
from torch import nn
from torch.nn import Linear
from torch.utils.data import DataLoader
dataset = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(), download=True)
dataloader = DataLoader(dataset, batch_size=64, drop_last=True)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.linear1 = Linear(196608, 10)
def forward(self, input):
output = self.linear1(input)
return output
tudui = Tudui()
for data in dataloader:
imgs, targets = data
print(imgs.shape)
output = torch.flatten(imgs)
print(output.shape)
output = tudui(output)
print(output.shape)
神经网络——搭建小实战和Sequential的使用
torch.nn.Sequential
import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriter
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__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
tudui = Tudui()
print(tudui)
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
print(output.shape)
writer = SummaryWriter("../logs_seq")
writer.add_graph(tudui, input)
writer.close()
损失函数与反向传播
loss function
import torch
from torch.nn import L1Loss
from torch import nn
inputs = torch.tensor([1, 2, 3], dtype=torch.float32)
targets = torch.tensor([1, 2, 5], 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)
loss_mse = nn.MSELoss()
result_mse = loss_mse(inputs, targets)
print(result)
print(result_mse)
x = torch.tensor([0.1, 0.2, 0.3])
y = torch.tensor([1])
x = torch.reshape(x, (1, 3))
loss_cross = nn.CrossEntropyLoss()
result_cross = loss_cross(x, y)
print(result_cross)
import torchvision
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
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 Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__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()
tudui = Tudui()
for data in dataloader:
imgs, targets = data
outputs = tudui(imgs)
result_loss = loss(outputs, targets)
print("ok")
优化器
import torch
import torchvision
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
from torch.optim.lr_scheduler import StepLR
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 Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__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()
tudui = Tudui()
optim = torch.optim.SGD(tudui.parameters(), lr=0.01)
for epoch in range(20):
running_loss = 0.0
for data in dataloader:
imgs, targets = data
outputs = tudui(imgs)
result_loss = loss(outputs, targets)
optim.zero_grad()
result_loss.backward()
optim.step()
running_loss = running_loss + result_loss
print(running_loss)
现有网络模型的使用及修改
import torchvision
# train_data = torchvision.datasets.ImageNet("./data_image_net", split='train', download=True,
# transform=torchvision.transforms.ToTensor())
from torch import nn
vgg16_false = torchvision.models.vgg16(pretrained=False)
vgg16_true = torchvision.models.vgg16(pretrained=True)
print(vgg16_true)
train_data = torchvision.datasets.CIFAR10('../data', train=True, transform=torchvision.transforms.ToTensor(),
download=True)
vgg16_true.classifier.add_module('add_linear', nn.Linear(1000, 10))
print(vgg16_true)
print(vgg16_false)
vgg16_false.classifier[6] = nn.Linear(4096, 10)
print(vgg16_false)
网络模型的保存与读取
保存
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 Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=3)
def forward(self, x):
x = self.conv1(x)
return x
tudui = Tudui()
torch.save(tudui, "tudui_method1.pth")
读取
import torch
from model_save import *
# 方式1-》保存方式1，加载模型
import torchvision
from torch import nn
model = torch.load("vgg16_method1.pth")
# print(model)
# 方式2，加载模型
vgg16 = torchvision.models.vgg16(pretrained=False)
vgg16.load_state_dict(torch.load("vgg16_method2.pth"))
# model = torch.load("vgg16_method2.pth")
# print(vgg16)
# 陷阱1
# class Tudui(nn.Module):
# def __init__(self):
# super(Tudui, self).__init__()
# self.conv1 = nn.Conv2d(3, 64, kernel_size=3)
#
# def forward(self, x):
# x = self.conv1(x)
# return x
model = torch.load('tudui_method1.pth')
print(model)
完整的模型训练套路
import torch
from torch import nn
# 搭建神经网络
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__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__':
tudui = Tudui()
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
print(output.shape)
import torchvision
from torch.utils.tensorboard import SummaryWriter
from model import *
# 准备数据集
from torch import nn
from torch.utils.data import DataLoader
train_data = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=torchvision.transforms.ToTensor(), download=True)
test_data = torchvision.datasets.CIFAR10(root="./dataset", train=False, transform=torchvision.transforms.ToTensor(), download=True)
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 如果train_data_size=10, 训练数据集的长度为：10
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_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 创建网络模型
tudui = Tudui()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
# 优化器
# learning_rate = 0.01
# 1e-2=1 x (10)^(-2) = 1 /100 = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.parameters(), lr=learning_rate)# SGD随机梯度下降
# 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
# 添加tensorboard
writer = SummaryWriter("./logs_train")
for i in range(epoch):
print("-------第 {} 轮训练开始-------".format(i+1))
# 训练步骤开始
tudui.train()
for data in train_dataloader:
imgs, targets = data
outputs = tudui(imgs)
loss = loss_fn(outputs, targets)
# 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_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
tudui.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
outputs = tudui(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = total_test_loss + loss.item()
accuracy = (outputs.argmax(1) == targets).sum()
total_accuracy = 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: {}".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 = total_test_step + 1
torch.save(tudui, "tudui_{}.pth".format(i))
# torch.save(tudui.state_dict(), "tudui_{}.pth".format(i))
print("模型已保存")
writer.close()
利用GPU训练
方式一
import torch
import torchvision
from torch.utils.tensorboard import SummaryWriter
# from model import *
# 准备数据集
from torch import nn
from torch.utils.data import DataLoader
train_data = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=torchvision.transforms.ToTensor(),
download=True)
test_data = torchvision.datasets.CIFAR10(root="./dataset", train=False, transform=torchvision.transforms.ToTensor(),
download=True)
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 如果train_data_size=10, 训练数据集的长度为：10
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_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 创建网络模型
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__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
tudui = Tudui()
if torch.cuda.is_available():
tudui = tudui.cuda()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():
loss_fn = loss_fn.cuda()
# 优化器
# learning_rate = 0.01
# 1e-2=1 x (10)^(-2) = 1 /100 = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.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
# 添加tensorboard
writer = SummaryWriter("./logs_train")
for i in range(epoch):
print("-------第 {} 轮训练开始-------".format(i+1))
# 训练步骤开始
tudui.train()
for data in train_dataloader:
imgs, targets = data
if torch.cuda.is_available():
imgs = imgs.cuda()
targets = targets.cuda()
outputs = tudui(imgs)
loss = loss_fn(outputs, targets)
# 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_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
tudui.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
if torch.cuda.is_available():
imgs = imgs.cuda()
targets = targets.cuda()
outputs = tudui(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = total_test_loss + loss.item()
accuracy = (outputs.argmax(1) == targets).sum()
total_accuracy = 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: {}".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 = total_test_step + 1
torch.save(tudui, "tudui_{}.pth".format(i))
print("模型已保存")
writer.close()
import torch
import torchvision
from torch.utils.tensorboard import SummaryWriter
# from model import *
# 准备数据集
from torch import nn
from torch.utils.data import DataLoader
# 定义训练的设备
device = torch.device("cuda")
train_data = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=torchvision.transforms.ToTensor(),
download=True)
test_data = torchvision.datasets.CIFAR10(root="./dataset", train=False, transform=torchvision.transforms.ToTensor(),
download=True)
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 如果train_data_size=10, 训练数据集的长度为：10
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_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 创建网络模型
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__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
tudui = Tudui()
tudui = tudui.to(device)
# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)
# 优化器
# learning_rate = 0.01
# 1e-2=1 x (10)^(-2) = 1 /100 = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.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
# 添加tensorboard
writer = SummaryWriter("./logs_train")
for i in range(epoch):
print("-------第 {} 轮训练开始-------".format(i+1))
# 训练步骤开始
tudui.train()
for data in train_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = tudui(imgs)
loss = loss_fn(outputs, targets)
# 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_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
tudui.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = tudui(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = total_test_loss + loss.item()
accuracy = (outputs.argmax(1) == targets).sum()
total_accuracy = 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: {}".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 = total_test_step + 1
torch.save(tudui, "tudui_{}.pth".format(i))
print("模型已保存")
writer.close()
方式二
import torch
import torchvision
from torch.utils.tensorboard import SummaryWriter
# from model import *
# 准备数据集
from torch import nn
from torch.utils.data import DataLoader
# 定义训练的设备
device = torch.device("cuda")
train_data = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=torchvision.transforms.ToTensor(),
download=True)
test_data = torchvision.datasets.CIFAR10(root="./dataset", train=False, transform=torchvision.transforms.ToTensor(),
download=True)
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 如果train_data_size=10, 训练数据集的长度为：10
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_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 创建网络模型
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__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
tudui = Tudui()
tudui = tudui.to(device)
# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)
# 优化器
# learning_rate = 0.01
# 1e-2=1 x (10)^(-2) = 1 /100 = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.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
# 添加tensorboard
writer = SummaryWriter("./logs_train")
for i in range(epoch):
print("-------第 {} 轮训练开始-------".format(i+1))
# 训练步骤开始
tudui.train()
for data in train_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = tudui(imgs)
loss = loss_fn(outputs, targets)
# 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_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
tudui.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = tudui(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = total_test_loss + loss.item()
accuracy = (outputs.argmax(1) == targets).sum()
total_accuracy = 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: {}".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 = total_test_step + 1
torch.save(tudui, "tudui_{}.pth".format(i))
print("模型已保存")
writer.close()
完整的模型验证套路
import torch
import torchvision
from PIL import Image
from torch import nn
image_path = "./imgs/airplane.png"
image = Image.open(image_path)
print(image)
image = image.convert('RGB')
transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32, 32)),
torchvision.transforms.ToTensor()])
image = transform(image)
print(image.shape)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__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
model = torch.load("tudui_29_gpu.pth", map_location=torch.device('cpu'))
print(model)
image = torch.reshape(image, (1, 3, 32, 32))
model.eval()
with torch.no_grad():
output = model(image)
print(output)
print(output.argmax(1))