- 🍨 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
- 🚀 文章来源:K同学的学习圈子
我的环境:
-
语言环境:python 3.8
-
编译器:jupyter notebook
-
深度学习环境:Pytorch
torch == 2.1.0+cpu
torchvision == 0.16.0+cpu
一、准备工作
1. 导入库函数
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,random
2.加载数据
● 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。
data_dir = "D:\BaiduNetdiskDownload\datasets\weather_photos"
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*/'))
classNames = [str(path).split("\\")[4] for path in data_paths]
classNames
['cloudy', 'rain', 'shine', 'sunrise']
3.图片可视化
import matplotlib.pyplot as plt
from PIL import Image
# 指定图像文件夹路径
image_folder = "D:\BaiduNetdiskDownload\datasets\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()
4. 数据加载(设置batchsize和取样等功能)
# 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(data_dir,transform=train_transforms)
total_data
Dataset ImageFolder
Number of datapoints: 1125
Root location: D:\BaiduNetdiskDownload\datasets\weather_photos
StandardTransform
Transform: Compose(
Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=warn)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)
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
(<torch.utils.data.dataset.Subset at 0x2a1fa06af40>,
<torch.utils.data.dataset.Subset at 0x2a1ffec1b50>)
train_size, test_size
(900, 225)
-
使用torch.utils.data.DataLoader进行数据加载
torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=None,sampler=None, batch_sampler=None, num_workers=0, collate_fn=None, pin_memory=False, drop_last=False, timeout=0, worker_init_fn=None, multiprocessing_context=None, generator=None, *, prefetch_factor=2, persistent_workers=False, pin_memory_device=‘’)
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)
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
Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y: torch.Size([32]) torch.int64
二、CNN网络配置、编译、训练
1. 模型建立
-
卷积层:nn.Conv2d(inputsize,outputsize,kernel_size)
-
池化层:nn.MaxPool2d(kernel_size)
-
nn.Linear(inputsize,outputsize)
-
torch.flatten()/torch.nn.flatten()/x.view(),将二维数据拉伸为一维,连接卷积层和全连接层。但x.view()是直接在元数据上操作,其它的是返回一个新的张量。
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
model = Network_bn()
model
Network_bn(
(conv1): Conv2d(3, 12, kernel_size=(5, 5), stride=(1, 1))
(bn1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(12, 12, kernel_size=(5, 5), stride=(1, 1))
(bn2): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(conv4): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1))
(bn4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv5): Conv2d(24, 24, kernel_size=(5, 5), stride=(1, 1))
(bn5): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(fc1): Linear(in_features=60000, out_features=1129, bias=True)
)
import torchinfo
torchinfo.summary(model) #显示模型信息
=================================================================
Layer (type:depth-idx) Param #
=================================================================
Network_bn --
├─Conv2d: 1-1 912
├─BatchNorm2d: 1-2 24
├─Conv2d: 1-3 3,612
├─BatchNorm2d: 1-4 24
├─MaxPool2d: 1-5 --
├─Conv2d: 1-6 7,224
├─BatchNorm2d: 1-7 48
├─Conv2d: 1-8 14,424
├─BatchNorm2d: 1-9 48
├─Linear: 1-10 67,741,129
=================================================================
Total params: 67,767,445
Trainable params: 67,767,445
Non-trainable params: 0
=================================================================
2. 训练函数
2.1 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)
2.2 训练函数
- optimizer.zero_grad(),梯度清零。
- loss.backward(),反向传播计算每个w的梯度值。
- optimizer.step(),梯度下降法更新参数值。
# 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
train_acc和loss的计算原理:
- pred.argmax(1)返回预测结果pred行最大值的索引,每行是表示一个样本的预测概率分布。==y表示判断预测是否正确。
- .type(torch.float)将判断结果转为浮点类型可以进行求和。
- .sum()对预测结果的正误进行求和。
- .item()将求和结果转为标量值便于输出。
2.3 测试函数
去掉了训练函数中梯度下降和权重更新的步骤。
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
2.4 模型训练
- model.train(),用于训练,启用BN层和dropout。
- model.eval(),用于测试,不启用BN层和dropout。
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')
Epoch: 1, Train_acc:57.7%, Train_loss:2.587, Test_acc:52.9%,Test_loss:3.022
Epoch: 2, Train_acc:77.1%, Train_loss:0.784, Test_acc:82.7%,Test_loss:0.637
Epoch: 3, Train_acc:82.3%, Train_loss:0.574, Test_acc:80.4%,Test_loss:0.561
Epoch: 4, Train_acc:85.2%, Train_loss:0.514, Test_acc:82.7%,Test_loss:0.504
Epoch: 5, Train_acc:85.6%, Train_loss:0.476, Test_acc:85.3%,Test_loss:0.484
Epoch: 6, Train_acc:87.9%, Train_loss:0.420, Test_acc:86.2%,Test_loss:0.383
Epoch: 7, Train_acc:88.3%, Train_loss:0.379, Test_acc:90.7%,Test_loss:0.420
Epoch: 8, Train_acc:90.0%, Train_loss:0.346, Test_acc:89.3%,Test_loss:0.374
Epoch: 9, Train_acc:89.9%, Train_loss:0.331, Test_acc:88.0%,Test_loss:0.386
Epoch:10, Train_acc:90.0%, Train_loss:0.298, Test_acc:89.8%,Test_loss:0.342
Epoch:11, Train_acc:91.9%, Train_loss:0.296, Test_acc:91.1%,Test_loss:0.339
Epoch:12, Train_acc:91.6%, Train_loss:0.309, Test_acc:92.0%,Test_loss:0.321
Epoch:13, Train_acc:92.7%, Train_loss:0.261, Test_acc:90.7%,Test_loss:0.329
Epoch:14, Train_acc:92.7%, Train_loss:0.268, Test_acc:90.7%,Test_loss:0.326
Epoch:15, Train_acc:92.7%, Train_loss:0.274, Test_acc:89.8%,Test_loss:0.393
Epoch:16, Train_acc:94.0%, Train_loss:0.223, Test_acc:90.7%,Test_loss:0.294
Epoch:17, Train_acc:93.6%, Train_loss:0.277, Test_acc:89.8%,Test_loss:0.363
Epoch:18, Train_acc:93.7%, Train_loss:0.221, Test_acc:90.7%,Test_loss:0.289
Epoch:19, Train_acc:94.0%, Train_loss:0.275, Test_acc:84.4%,Test_loss:0.338
Epoch:20, Train_acc:95.2%, Train_loss:0.205, Test_acc:91.6%,Test_loss:0.270
Done
三、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()
四、总结
- 本周内容进一步熟悉了pytorch框架。在模型中加入了BN层,作用:
- 加快网络的训练和收敛速度
- 防止梯度爆炸和梯度消失
- 防止过拟合