- 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
本次学习的首要目标是:了解并设置动态学习率
识别类别:adidas、nike(共两类)
要求:
- 了解如何设置动态学习率(重点)
- 调整代码使测试集accuracy到达84%。
拔高(可选):
- 保存训练过程中的最佳模型权重
- 调整代码使测试集accuracy到达86%。
# 1. 设置环境
import sys
from datetime import datetime
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib
print("---------------------1.配置环境------------------")
print("Start time: ", datetime.today())
print("Pytorch version: " + torch.__version__)
print("Python version: " + sys.version)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device
2.1 打印
classNames
列表,显示每个文件所属的类别名称
2.2 打印归一化后的类别名称,0
或1
2.3 划分数据集,划分为训练集&测试集,torch.utils.data.DataLoader()
参数详解
2.4 检查数据集的shape
'''
# 2.1 导入数据
● 第一步:使用pathlib.Path()函数将字符串类型的文件夹路径转换为pathlib.Path对象。
● 第二步:使用glob()方法获取data_dir路径下的所有文件路径,并以列表形式存储在data_paths中。
● 第三步:通过split()函数对data_paths中的每个文件路径执行分割操作,获得各个文件所属的类别名称,并存储在classNames中
● 第四步:打印classNames列表,显示每个文件所属的类别名称。(注意路径分割得到的索引值)
'''
print("---------------------2.1 导入数据------------------")
import os,PIL,random,pathlib
data_dir = 'D:/jupyter notebook/DL-100-days/datasets/SportShoes_data/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
for path in data_paths:
print("path: ", path)
'''
注意这里的[5],随文件路径改变,由上一行打印的path可知道这里取哪个索引值
'''
classNames = [str(path).split("\\")[5] for path in data_paths]
print("classNames: ",classNames)
print("---------------------2.2 数据可视化------------------")
import matplotlib.pyplot as plt
from PIL import Image
# 指定图像文件夹路径
image_folder = 'D:/jupyter notebook/DL-100-days/datasets/SportShoes_data/train/adidas/'
# 获取文件夹中的所有图像文件
image_files = [f for f in os.listdir(image_folder) if f.endswith((".jpg", ".png", ".jpeg"))]
# 创建Matplotlib图像
fig, axes = plt.subplots(3, 8, figsize=(16, 6))
# 使用列表推导式加载和显示图像
for ax, img_file in zip(axes.flat, image_files):
img_path = os.path.join(image_folder, img_file)
img = Image.open(img_path)
ax.imshow(img)
ax.axis('off')
# 显示图像
plt.tight_layout()
plt.show()
'''
划分数据集:
第一步:将训练数据集、测试数据集中的图片,分别定义一个归一化的函数,并打印各自归一化后的类别索引
第二步:设置batch size,训练集、测试集,并打印各自的shape信息
'''
print("---------------------2.3 定义train_transforms函数,完成图片尺寸归一化------------------")
traindata_path = 'D:/jupyter notebook/DL-100-days/datasets/SportShoes_data/train/'
testdata_path = 'D:/jupyter notebook/DL-100-days/datasets/SportShoes_data/test/'
# 关于transforms.Compose的更多介绍可以参考:https://blog.csdn.net/qq_38251616/article/details/124878863
train_transforms = transforms.Compose([
transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
# transforms.RandomHorizontalFlip(), # 随机水平翻转
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。
])
test_transform = transforms.Compose([
transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
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。
])
# 打印训练集、测试集的类别索引
train_dataset = datasets.ImageFolder(traindata_path,transform=train_transforms)
test_dataset = datasets.ImageFolder(testdata_path,transform=train_transforms)
print("train_dataset: ", train_dataset.class_to_idx)
print("test_dataset: ", test_dataset.class_to_idx)
print("---------------------2.4 划分数据集------------------")
# 设置batch size,打印test_dl的size
batch_size = 32
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)
print("---------------------2.4.1 检查训练集、测试集的size------------------")
for X, y in train_dl:
print("train_dl Shape of X [N, C, H, W]: ", X.shape)
print("train_dl Shape of y: ", y.shape, y.dtype)
break
for X, y in test_dl:
print("test_dl Shape of X [N, C, H, W]: ", X.shape)
print("test_dl Shape of y: ", y.shape, y.dtype)
break
'''
简单的CNN网络:
conv1层: Conv2d + BatchNorm2d + ReLU
conv2层: Conv2d + BatchNorm2d + ReLU
pool3层:MaxPool2d
conv4层: Conv2d + BatchNorm2d + ReLU
conv5层: Conv2d + BatchNorm2d + ReLU
pool6层:MaxPool2d
dropout层:DropOut
fc层:Linear
'''
print("---------------------3. 创建简单的CNN网络------------------")
import torch.nn.functional as F
class Model(nn.Module):
def __init__(self):
super(Model, self).__init__()
self.conv1=nn.Sequential(
nn.Conv2d(3, 12, kernel_size=5, padding=0), # 12*220*220
nn.BatchNorm2d(12),
nn.ReLU())
self.conv2=nn.Sequential(
nn.Conv2d(12, 12, kernel_size=5, padding=0), # 12*216*216
nn.BatchNorm2d(12),
nn.ReLU())
self.pool3=nn.Sequential(
nn.MaxPool2d(2)) # 12*108*108
self.conv4=nn.Sequential(
nn.Conv2d(12, 24, kernel_size=5, padding=0), # 24*104*104
nn.BatchNorm2d(24),
nn.ReLU())
self.conv5=nn.Sequential(
nn.Conv2d(24, 24, kernel_size=5, padding=0), # 24*100*100
nn.BatchNorm2d(24),
nn.ReLU())
self.pool6=nn.Sequential(
nn.MaxPool2d(2)) # 24*50*50
self.dropout = nn.Sequential(
nn.Dropout(0.2))
self.fc=nn.Sequential(
nn.Linear(24*50*50, len(classNames)))
def forward(self, x):
batch_size = x.size(0)
x = self.conv1(x) # 卷积-BN-激活
x = self.conv2(x) # 卷积-BN-激活
x = self.pool3(x) # 池化
x = self.conv4(x) # 卷积-BN-激活
x = self.conv5(x) # 卷积-BN-激活
x = self.pool6(x) # 池化
x = self.dropout(x)
x = x.view(batch_size, -1) # flatten 变成全连接网络需要的输入 (batch, 24*50*50) ==> (batch, -1), -1 此处自动算出的是24*50*50
x = self.fc(x)
return x
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = Model().to(device)
model
4.1 编写训练函数
4.2 编写测试函数
4.3 设置动态学习率
4.4 开始正式训练,epochs==40
'''
训练:
第一步:编写训练函数
第二步:编写测试函数
第三步:设置动态学习率(与P4的不同,P4使用固定学习率,本文使用动态学习率)
第四步:开启训练
'''
print("---------------------4.1 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
print("---------------------4.2 编写测试函数------------------")
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
'''
设置动态学习率,两种方式:(1)自定义;(2)调用官方接口
下文使用方式(1),后续尝试方式(2)
'''
print("---------------------4.3 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)
print("---------------------4.4 开启训练,epoch=40------------------")
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
epochs = 40
train_loss = []
train_acc = []
test_loss = []
test_acc = []
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)
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))
print('Done')
'''
训练结果图表表示
'''
print("---------------------5.1 查看训练结果-----------------")
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()
print("---------------------5.2 指定一张图片进行预测-----------------")
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='D:/jupyter notebook/DL-100-days/datasets/SportShoes-data/test/adidas/17.jpg',
model=model,
transform=train_transforms,
classes=classes)
print("---------------------5.3 模型保存-----------------")
# 模型保存
PATH = './P5-model.pth' # 保存的参数文件名
torch.save(model.state_dict(), PATH)
# 将参数加载到model当中
model.load_state_dict(torch.load(PATH, map_location=device))
print("End time: ", datetime.today())
torch.optim.lr_scheduler.StepLR
等间隔动态调整说明:等间隔动态调整方法,每经过step_size个epoch,做一次学习率decay,以gamma值为缩小倍数。
函数原型:torch.optim.lr_scheduler.StepLR(optimizer, step_size, gamma=0.1, last_epoch=-1)
关键参数详解:
optimizer(Optimizer)
:是之前定义好的需要优化的优化器的实例名
step_size(int)
:是学习率衰减的周期,每经过每个epoch
,做一次学习率衰减(decay
)
gamma(float)
:学习率衰减的乘法因子。Default:0.1
用法示例:
optimizer = torch.optim.SGD(net.parameters(), lr=0.001 )
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.1)
lr_scheduler.LambdaLR
自定义学习率更新函数torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda, last_epoch=-1, verbose=False)
optimizer(Optimizer)
:是之前定义好的需要优化的优化器的实例名称lr_lambda(function)
:更新学习率的函数lambda1 = lambda epoch: (0.92 ** (epoch // 2) # 第二组参数的调整方法
optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda1) #选定调整方法
替换4.3节的自定义学习率,也是每两个epoch衰减到原来的0.98,初始学习率learn_rate = 1e-4:
训练情况如下:
lr_scheduler.MultiStepLR
特定epoch中调整学习率torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones, gamma=0.1, last_epoch=-1, verbose=False)
optimizer(Optimizer)
:是之前定义好的需要优化的优化器的实例名milestones(list)
:是一个关于epoch数值的list,表示在达到哪个epoch范围内开始变化,必须是升序排列gamma(float)
:学习率衰减的乘法因子。Default:0.1
optimizer = torch.optim.SGD(net.parameters(), lr=0.001 )
scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer,
milestones=[2,6,15], #调整学习率的epoch数
gamma=0.1)
学习率方式 | test_accuracy |
---|---|
自定义函数 | 81.6% |
torch.optim.lr_scheduler.StepLR | 81.6% |
lr_scheduler.LambdaLR | 85.5% |
lr_scheduler.MultiStepLR | 75.0% |
针对本文,动态学习率lr_scheduler.LambdaLR
表现优秀。