郑州商城网站建设,网站后台无法编辑文字,天津智能网站建设哪里有,国内怎么打开WordPress网站#x1f368; 本文为#x1f517;365天深度学习训练营 内部限免文章#xff08;版权归 K同学啊 所有#xff09;#x1f366; 参考文章地址#xff1a; #x1f517;第P6周#xff1a;好莱坞明星识别 | 365天深度学习训练营#x1f356; 作者#xff1a;K同学啊 | 接… 本文为365天深度学习训练营 内部限免文章版权归 K同学啊 所有 参考文章地址 第P6周好莱坞明星识别 | 365天深度学习训练营 作者K同学啊 | 接辅导、程序定制 文章目录我的环境一、前期工作1. 设置 GPU2. 导入数据3. 划分数据集二、调用vgg-16模型三、训练模型1. 设置超参数2. 编写训练函数3. 编写测试函数4. 正式训练四、结果可视化1.Loss 与 Accuracy 图我的环境
语言环境Python 3.6.8编译器jupyter notebook深度学习环境 torch0.13.1、cuda11.3torchvision1.12.1、cuda11.3
一、前期工作
1. 设置 GPU
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
from torchvision import transforms, datasetsif __name____main__: 设置GPU device torch.device(cuda if torch.cuda.is_available() else cpu)print(Using {} device\n.format(device))Using cuda device2. 导入数据
import os, PIL, pathlib
data_dir D:/jupyter notebook/DL-100-days/datasets/48-data/
data_dir pathlib.Path(data_dir)
data_paths list(data_dir.glob(*))
classeNames [str(path).split(\\)[5] for path in data_paths]
print(classeNames)[Angelina Jolie,Brad Pitt,Denzel Washington,Hugh Jackman,Jennifer Lawrence,Johnny Depp,Kate Winslet,Leonardo DiCaprio,Megan Fox,Natalie Portman,Nicole Kidman,Robert Downey Jr,Sandra Bullock,Scarlett Johansson,Tom Cruise,Tom Hanks,Will Smith]train_transforms transforms.Compose([transforms.Resize([224,224]),# resize输入图片transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换成tensortransforms.Normalize(mean [0.485, 0.456, 0.406],std [0.229,0.224,0.225]) # 从数据集中随机抽样计算得到
])total_data datasets.ImageFolder(data_dir,transformtrain_transforms)
total_dataDataset ImageFolderNumber of datapoints: 1800Root location: hlwStandardTransform
Transform: Compose(Resize(size[224, 224], interpolationPIL.Image.BILINEAR)ToTensor()Normalize(mean[0.485, 0.456, 0.406], std[0.229, 0.224, 0.225]))3. 划分数据集
train_size int(0.8*len(total_data))
test_size len(total_data) - train_size
train_dataset, test_dataset torch.utils.data.random_split(total_data,[train_size,test_size])batch_size 32
train_dl torch.utils.data.DataLoader(train_dataset,batch_sizebatch_size,shuffleTrue,num_workers1)
test_dl torch.utils.data.DataLoader(test_dataset,batch_sizebatch_size,shuffleTrue,num_workers1)二、调用vgg-16模型
from torchvision.models import vgg16model vgg16(pretrained True).to(device)
for param in model.parameters():param.requires_grad Falsemodel.classifier._modules[6] nn.Linear(4096,len(classNames))model.to(device)# 查看要训练的层
params_to_update model.parameters()
# params_to_update []
for name,param in model.named_parameters():if param.requires_grad True:
# params_to_update.append(param)print(\t,name)三、训练模型
1. 设置超参数
# 优化器设置
optimizer torch.optim.Adam(params_to_update, lr1e-4)#要训练什么参数/
scheduler torch.optim.lr_scheduler.StepLR(optimizer, step_size5, gamma0.92)#学习率每5个epoch衰减成原来的1/10
loss_fn nn.CrossEntropyLoss()2. 编写训练函数
# 训练循环
def train(dataloader, model, loss_fn, optimizer):size len(dataloader.dataset) # 训练集的大小一共900张图片num_batches len(dataloader) # 批次数目29900/32train_loss, train_acc 0, 0 # 初始化训练损失和正确率for X, y in dataloader: # 获取图片及其标签X, y X.to(device), y.to(device)# 计算预测误差pred model(X) # 网络输出loss loss_fn(pred, y) # 计算网络输出和真实值之间的差距targets为真实值计算二者差值即为损失# 反向传播optimizer.zero_grad() # grad属性归零loss.backward() # 反向传播optimizer.step() # 每一步自动更新# 记录acc与losstrain_acc (pred.argmax(1) y).type(torch.float).sum().item()train_loss loss.item()train_acc / sizetrain_loss / num_batchesreturn train_acc, train_loss3. 编写测试函数
def test (dataloader, model, loss_fn):size len(dataloader.dataset) # 测试集的大小一共10000张图片num_batches len(dataloader) # 批次数目8255/328向上取整test_loss, test_acc 0, 0# 当不进行训练时停止梯度更新节省计算内存消耗with torch.no_grad():for imgs, target in dataloader:imgs, target imgs.to(device), target.to(device)# 计算losstarget_pred model(imgs)loss loss_fn(target_pred, target)test_loss loss.item()test_acc (target_pred.argmax(1) target).type(torch.float).sum().item()test_acc / sizetest_loss / num_batchesreturn test_acc, test_loss4. 正式训练
epochs 20
train_loss []
train_acc []
test_loss []
test_acc []
best_acc 0
filenamecheckpoint.pthfor epoch in range(epochs):model.train()epoch_train_acc, epoch_train_loss train(train_dl, model, loss_fn, optimizer)scheduler.step()#学习率衰减model.eval()epoch_test_acc, epoch_test_loss test(test_dl, model, loss_fn)# 保存最优模型if epoch_test_acc best_acc:best_acc epoch_train_accstate {state_dict: model.state_dict(),#字典里key就是各层的名字值就是训练好的权重best_acc: best_acc,optimizer : optimizer.state_dict(),}torch.save(state, filename)train_acc.append(epoch_train_acc)train_loss.append(epoch_train_loss)test_acc.append(epoch_test_acc)test_loss.append(epoch_test_loss)template (Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%Test_loss:{:.3f})print(template.format(epoch1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print(Done)
print(best_acc,best_acc)Epoch: 1, Train_acc:12.2%, Train_loss:2.701, Test_acc:13.9%Test_loss:2.544 Epoch: 2, Train_acc:20.8%, Train_loss:2.386, Test_acc:20.6%Test_loss:2.377 Epoch: 3, Train_acc:26.1%, Train_loss:2.228, Test_acc:22.5%Test_loss:2.274 … Epoch:19, Train_acc:51.6%, Train_loss:1.528, Test_acc:35.8%Test_loss:1.864 Epoch:20, Train_acc:53.9%, Train_loss:1.499, Test_acc:35.3%Test_loss:1.852 Done best_acc 0.37430555555555556
四、结果可视化
1.Loss 与 Accuracy 图
import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings(ignore) #忽略警告信息
plt.rcParams[font.sans-serif] [SimHei] # 用来正常显示中文标签
plt.rcParams[axes.unicode_minus] False # 用来正常显示负号
plt.rcParams[figure.dpi] 100 #分辨率epochs_range range(epochs)plt.figure(figsize(12, 3))
plt.subplot(1, 2, 1)plt.plot(epochs_range, train_acc, labelTraining Accuracy)
plt.plot(epochs_range, test_acc, labelTest Accuracy)
plt.legend(loclower right)
plt.title(Training and Validation Accuracy)plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, labelTraining Loss)
plt.plot(epochs_range, test_loss, labelTest Loss)
plt.legend(locupper right)
plt.title(Training and Validation Loss)
plt.show()
