一、完整的模型训练套路
以CIFAR10为例
1、创建数据集
# 准备数据集
import torchvision
# 训练数据集
train_data = torchvision.datasets.CIFAR10("../dataset",train=True,
transform=torchvision.transforms.ToTensor(),download=True)
# 测试数据集
test_data = torchvision.datasets.CIFAR10("../dataset",train=False,
transform=torchvision.transforms.ToTensor(),download=True)可以查看数据集长度
# length 长度
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)) #训练数据集的长度为:50000
print("测试数据集的长度为:{}".format(test_data_size)) #测试数据集的长度为:100002、加载数据集(DataLoader)
# 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)
3、搭建神经网络
最好新建一个model.py
# 搭建神经网络 class ExamModuel(nn.Module): def __init__(self): super(ExamModuel, 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
测试网络模型的正确性(可省略)
if __name__ == '__main__': # 创造网络模型 ex_model = ExamModuel() input = torch.ones((64,3,32,32)) output = ex_model(input) print(output.shape)
4、创建网络模型
# 创建网络模型 ex_model = ExamModule()
5、损失函数
# 损失函数 loss_fn = nn.CrossEntropyLoss()
6、优化器
# 优化器 # SGD:随机梯度下降 # learning_rate = 0.01 # 学习率 learning_rate = 1e-2 # 学习率 optimizer = torch.optim.SGD(ex_model.parameters(),lr=learning_rate)
7、设置训练网络的一些参数
# 设置训练网络的一些参数 total_train_step = 0 # 记录训练的次数 total_test_step = 0 # 记录测试的次数 epoch = 10 # 训练的轮数
8、开始训练、测试训练效果
循环定义训练轮数epoch
for i in range(epoch):
print("-------------第{}轮训练开始-------------".format(i+1))训练
#训练步骤开始
ex_model.train() #对一些特殊的层有作用
for data in train_dataloader:
imgs,targets = data
outputs = ex_model(imgs)
loss = loss_fn(outputs,targets) # 和真实值targets相比,损失值为loss
# 优化器优化模型
optimizer.zero_grad() # 梯度清零
loss.backward() # 反向传播,得到每一个参数节点的梯度
optimizer.step() # 进行优化
total_train_step += 1
if total_train_step % 100 == 0:
print("训练次数:{},Loss:{}".format(total_train_step,loss.item()))每一轮都可以测试训练效果
# 测试开始
my_nn.eval()
total_test_loss = 0
train_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
img,target = data
output = my_nn(img)
accuracy = (target == output.argmax(1)).sum()
train_accuracy += accuracy
loss = loss_fn(output,target)
total_test_loss += loss
print("整体测试集上的Loss:{},ACC:{}".format(total_test_loss.item(),train_accuracy.item()/test_data_size))9、添加tensorboard
print("整体测试集上的loss:{}".format(total_test_loss))
print("整体测试集上的accracy:{}".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 torch.save(ex_model,"ex_model_{}.pth".format(i))
print("模型已保存...")
writer.close()①让模型在GPU上训练(一)
只需添加一些代码(ex_model、loss_fn、imgs、targets部分)
模型、损失函数、数据 需要添加.cuda()
模型-->cuda
ex_model = ExamModule()
if torch.cuda.is_available():
ex_model = ex_model.cuda() #网络模型可以转移到cuda上# 损失函数
loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():
loss_fn = loss_fn.cuda() #损失函数-->cudaimgs,targets = data
if torch.cuda.is_available():
imgs = imgs.cuda()
targets = targets.cuda()
# 注意:训练数据和测试数据都要添加该段代码在GPU上速度快了很多
CPU上:

GPU上:

②让模型在GPU上训练(二)
device = torch.device("cpu")
device = torch.device("cuda") 或者(等同于) device = torch.device("cuda:0")
device = torch.device("cuda:1")
模型/损失函数/imgs/targets.to(device)
# 有GPU则在GPU上训练,无GPU则在CPU上训练
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")# 定义训练的设备
device = torch.device("cuda")
# device = torch.device("cpu")模型-->设备 ex_model = ExamModule() ex_model = ex_model.to(device) #把网络转移到设备上 # ex_model.to(device) #这样写即可
# 损失函数-->设备 loss_fn = nn.CrossEntropyLoss() loss_fn = loss_fn.to(device) #把损失函数转移到设备上 # loss_fn.to(device) #这样写即可
imgs,targets = data imgs = imgs.to(device) targets = targets.to(device)
二、完整的模型验证(测试、demo)套路
利用已经训练好的模型,然后给它提供输入
测试OK的模型,就可以对外应用了
import torch import torchvision from PIL import Image from torch import nn
输入
device = torch.device("cuda")
img_path = "../imgs/003.png"
img = Image.open(img_path)
img = img.convert("RGB") #png格式是四个通道,除了RGB三通道外,还有一个透明度通道
transfrom = torchvision.transforms.Compose([torchvision.transforms.Resize((32,32)),
torchvision.transforms.ToTensor()])
img = transfrom(img)
img = img.to(device)
# print(img.shape)补充知识点:png格式是四个通道,除了RGB三通道外,还有一个透明度通道
搭建模型
class ExamModule(nn.Module):
def __init__(self):
super(ExamModule, 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
ex_model = torch.load("ex_model_29.pth")
# ex_model = torch.load("ex_model_29.pth",map_location=torch.device("cpu"))
# 在GPU中训练的模型,要将其映射到cpu上,使用map_location=torch.device("cpu")
print(ex_model)测试输出
img = torch.reshape(img,(1,3,32,32)) # print(img.shape) ex_model.eval() with torch.no_grad(): output = ex_model(img) print(output) print(output.argmax(1))
版权声明:本文为weixin_44334635原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处链接和本声明。