- 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
本文基础要求:
(1)本地读取并加载数据。
(2)测试集accuracy到达93%
拔高:
(1)测试集accuracy到达95%
(2)调用模型识别一张本地图片
# 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,random
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
导入数据分四步:
● 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。
'''
D:\jupyter notebook\DL-100-days\datasets\P3-天气识别\weather_photos\
'''
print("---------------------2.1 导入本地数据------------------")
data_dir = 'D:/jupyter notebook/DL-100-days/datasets/P3-天气识别/weather_photos/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classNames = [str(path).split("\\")[1] for path in data_paths]
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/P3-天气识别/weather_photos/cloudy/'
# 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()
print("---------------------2.3 定义train_transforms函数,完成图片尺寸归一化------------------")
total_datadir = 'D:\jupyter notebook\DL-100-days\datasets\P3-天气识别\weather_photos'
# 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.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。
])
total_data = datasets.ImageFolder(total_datadir,transform=train_transforms)
total_data
print("---------------------2.4 划分数据集------------------")
# 使用torch.utils.data.random_split()方法进行数据集划分。
# 该方法将总体数据total_data按照指定的大小比例([train_size, test_size])随机划分为训练集和测试集,并将划分结果分别赋值给train_dataset和test_dataset两个变量。
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
print("---------------------2.4.1 检查训练集、测试集的size------------------")
# ● train_size表示训练集大小,通过将总体数据长度的80%转换为整数得到;
# ● test_size表示测试集大小,是总体数据长度减去训练集大小。
train_size,test_size
print("---------------------2.4.1 检查训练集、测试集的size------------------")
batch_size = 32
# ⭐torch.utils.data.DataLoader()参数详解
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
print("---------------------3. 定义简单CNN网络------------------")
import torch.nn.functional as F
class Network_bn(nn.Module):
def __init__(self):
super(Network_bn, self).__init__()
"""
nn.Conv2d()函数:
第一个参数(in_channels)是输入的channel数量
第二个参数(out_channels)是输出的channel数量
第三个参数(kernel_size)是卷积核大小
第四个参数(stride)是步长,默认为1
第五个参数(padding)是填充大小,默认为0
"""
self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=0)
self.bn1 = nn.BatchNorm2d(12)
self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=0)
self.bn2 = nn.BatchNorm2d(12)
self.pool = nn.MaxPool2d(2,2)
self.conv4 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=0)
self.bn4 = nn.BatchNorm2d(24)
self.conv5 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=0)
self.bn5 = nn.BatchNorm2d(24)
self.fc1 = nn.Linear(24*50*50, len(classeNames))
def forward(self, x):
x = F.relu(self.bn1(self.conv1(x)))
x = F.relu(self.bn2(self.conv2(x)))
x = self.pool(x)
x = F.relu(self.bn4(self.conv4(x)))
x = F.relu(self.bn5(self.conv5(x)))
x = self.pool(x)
x = x.view(-1, 24*50*50)
x = self.fc1(x)
return x
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = Network_bn().to(device)
model
print("---------------------4. 训练模型------------------")
print("---------------------4.1 设置超参数------------------")
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-4 # 学习率
opt = torch.optim.SGD(model.parameters(),lr=learn_rate)
print("---------------------4.2 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60000张图片
num_batches = len(dataloader) # 批次数目,1875(60000/32)
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("---------------------4.3 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,313(10000/32=312.5,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
print("---------------------4.4 正式训练------------------")
epochs = 20
train_loss = []
train_acc = []
test_loss = []
test_acc = []
for epoch in range(epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
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)
template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%,Test_loss:{:.3f}')
print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')
print("---------------------5. 训练结果可视化------------------")
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()
尝试提高test_accuracy的值。
【提高准确率方法总结】
不同epoch次数得到的test_accuracy的结果如下表:
epoch | test_accuracy |
---|---|
epoch = 50 | 92.4% |
epoch = 60 | 93.3% |
epoch = 70 | 92.4% |
epoch = 80 | 94.2% |
epoch = 90 | 90.2% |
得到训练情况如下:
结论:50个epoch训练完,test_accuracy = 92.4%。在学习率不变的情况下,增加epoch次数是能够增加test_accuracy的值的。
【参考这里】
使用pytorch提供的学习率,在
torch.optim.lr_scheduler
内部,基于当前epoch的数值,封装了几种相应的动态学习率调整方法,该部分的官方手册传送门——optim.lr_scheduler官方文档。需要注意的是学习率的调整需要应用在优化器参数更新之后,也就是说:
optimizer = torch.optim.XXXXXXX()#具体optimizer的初始化
scheduler = torch.optim.lr_scheduler.XXXXXXXXXX()#具体学习率变更策略的初始化
for i in range(epoch):
for data,label in dataloader:
out = net(data)
output_loss = loss(out,label)
optimizer.zero_grad()
loss.backward()
optimizer.step()
scheduler.step()
设置动态学习率,不同epoch次数的test_accuracy值如下表所示:
epoch | test_accuracy |
---|---|
epoch = 50 | 92.0% |
epoch = 60 | 93.3% |
epoch = 70 | 92.4% |
epoch = 80 | 93.3% |
epoch = 90 | 87.6% |
训练情况如下:test_accuracy最高能达到92.9%,然后又降下来,等50个epoch都训练完,最终的test_accuracy = 92.0%。