- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍖 原作者:K同学啊 | 接辅导、项目定制
一、前期准备
1.设置GPU
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warnings
warnings.filterwarnings("ignore") #忽略警告信息
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device
2. 导入数据
data_dir = 'F:/host/Data/好莱坞明星人脸识别识别数据/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*/*'))
classeNames = sorted(item.name for item in data_dir.glob('*/') if item.is_dir())
classeNames
train_transforms = transforms.Compose([
transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
transforms.RandomRotation(45), # 随机旋转,-45°到45°之间的随机值
transforms.RandomHorizontalFlip(0.5), # 随机水平翻转
transforms.RandomVerticalFlip(0.5), # 随机垂直翻转,选择一个概率
transforms.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.2, hue=0.2), # 颜色扭曲,brightness为亮度,contrast为对比度,saturation为饱和度,hue为色相
transforms.RandomGrayscale(0.025), # 概率转为灰度率,3通道就是R=G=B
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor,并归一化到[0,1]之间
transforms.Normalize( # 标准化处理-->转换为标准正太分布(高斯分布),使模型更容易收敛
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的,mean为均值,std为标准差
])
total_data = datasets.ImageFolder("F:/host/Data/好莱坞明星人脸识别识别数据/",transform=train_transforms)
total_data
total_data.class_to_idx
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])
train_dataset, test_dataset
batch_size = 64
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1)
for X, y in test_dl:
print("Shape of X [N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape, y.dtype)
break
二、调用官方的VGG-16模型
VGG-16结构说明:
- 13个卷积层(Convolutional Layer),分别用blockX_convX表示;
- 3个全连接层(Fully connected Layer),用classifier表示;
- 5个池化层(Pool layer)。
VGG-16
包含了16个隐藏层(13个卷积层和3个全连接层),故称为VGG-16
VGG-16网络结构图:
二、调用官方的VGG-16模型
VGG-16结构说明:
- 13个卷积层(Convolutional Layer),分别用blockX_convX表示;
- 3个全连接层(Fully connected Layer),用classifier表示;
- 5个池化层(Pool layer)。
VGG-16
包含了16个隐藏层(13个卷积层和3个全连接层),故称为VGG-16
VGG-16网络结构图:
from torchvision.models import vgg16
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
# 加载预训练模型,并且对模型进行微调
model = vgg16(pretrained = True).to(device) # 加载预训练的vgg16模型
for param in model.parameters():
param.requires_grad = False # 冻结模型的参数,这样子在训练的时候只训练最后一层的参数
# 修改classifier模块的第6层(即:(6): Linear(in_features=4096, out_features=2, bias=True))
# 注意查看我们下方打印出来的模型
model.classifier._modules['6'] = nn.Linear(4096,len(classeNames)) # 修改vgg16模型中最后一层全连接层,输出目标类别个数
model.to(device)
model
三、 训练模型
1. 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
num_batches = len(dataloader) # 批次数目, (size/batch_size,向上取整)
train_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loss
train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
train_loss += loss.item()
train_acc /= size
train_loss /= num_batches
return train_acc, train_loss
```
## 2. 编写测试函数
测试函数和训练函数大致相同,但是由于不进行梯度下降对网络权重进行更新,所以不需要传入优化器
```python
def test (dataloader, model, loss_fn):
size = len(dataloader.dataset) # 测试集的大小
num_batches = len(dataloader) # 批次数目, (size/batch_size,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loss
target_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 /= size
test_loss /= num_batches
return test_acc, test_loss
3. 设置动态学习率
def adjust_learning_rate(optimizer, epoch, start_lr):
# 每 2 个epoch衰减到原来的 0.98
lr = start_lr * (0.92 ** (epoch // 2))
for param_group in optimizer.param_groups:
param_group['lr'] = lr
learn_rate = 1e-4 # 初始学习率
# optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
# 调整优化器
# SGD即梯度下降易得到局部最优,而Adam可得到全局最优
optimizer = torch.optim.Adam(model.parameters(), lr=learn_rate)
更多的官方动态学习率设置方式可参考:https://pytorch.org/docs/stable/optim.html
4. 正式训练
model.train()
、model.eval()
训练营往期文章中有详细的介绍。请注意观察我是如何保存最佳模型,与TensorFlow2的保存方式有何异同。
import copy
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
epochs = 40
train_loss = []
train_acc = []
test_loss = []
test_acc = []
best_acc = 0 # 设置一个最佳准确率,作为最佳模型的判别指标
for epoch in range(epochs):
# 更新学习率(使用自定义学习率时使用)
adjust_learning_rate(optimizer, epoch, learn_rate)
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
# scheduler.step() # 更新学习率(调用官方动态学习率接口时使用)
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
# 保存最佳模型到 best_model
if epoch_test_acc > best_acc:
best_acc = epoch_test_acc
best_model = copy.deepcopy(model)
train_acc.append(epoch_train_acc)
train_loss.append(epoch_train_loss)
test_acc.append(epoch_test_acc)
test_loss.append(epoch_test_loss)
# 获取当前的学习率
lr = optimizer.state_dict()['param_groups'][0]['lr']
template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')
print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss,
epoch_test_acc*100, epoch_test_loss, lr))
# 保存最佳模型到文件中
PATH = './model/starFace_best_model_2.pth' # 保存的参数文件名
torch.save(model.state_dict(), PATH)
print('Done')
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, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
2. 指定图片进行预测
from PIL import Image
classes = list(total_data.class_to_idx)
def predict_one_image(image_path, model, transform, classes):
test_img = Image.open(image_path).convert('RGB')
plt.imshow(test_img) # 展示预测的图片
test_img = transform(test_img)
img = test_img.to(device).unsqueeze(0)
model.eval()
output = model(img)
_,pred = torch.max(output,1)
pred_class = classes[pred]
print(f'预测结果是:{pred_class}')
# 预测训练集中的某张照片
predict_one_image(image_path='F:/host/Data/好莱坞明星人脸识别识别数据/Jennifer Lawrence/027_3290d1bc.jpg',
model=model,
transform=train_transforms,
classes=classes)
3. 模型评估
best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)
epoch_test_acc, epoch_test_loss
# 查看是否与我们记录的最高准确率一致
epoch_test_acc
五、个人收获
通过transforms对数据进行增强,使准确度提高到33.4%