- 🍨 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
前言
要求:
- 训练过程中保存效果最好的模型参数。
- 加载最佳模型参数识别本地的一张图片。
- 调整网络结构使测试集accuracy到达88%(重点)。
拔高:
- 调整模型参数并观察测试集的准确率变化。
- 尝试设置动态学习率。
- 测试集accuracy到达90%。
实验环境:
- 语言环境:Python3.10
- 编译器:Pycharm
- 深度学习环境:Pytorch
1.torch == 2.2.2
2.torchvision == 0.16.0
一、前期准备
1.设置GPU
import os
import pathlib
import warnings
import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.nn.functional as F
from PIL import Image
from torchvision import transforms, datasets
#-------------设置GPU---------------
# 设置硬件设备,如果有GPU则使用,没有则使用cpu
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
代码输出:
cuda
2.导入数据
输入代码:
#---------------------------导入数据----------------------
data_dir = 'F:/lsydata/houdoudata/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[3] for path in data_paths]
print(classeNames)
代码输出:
['Monkeypox', 'Others']
关于导入数据步骤:
● 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classeNames中
● 第四步:打印classeNames列表,显示每个文件所属的类别名称。
代码输入:
# 指定图像文件夹路径
image_folder = ('F:/lsydata/houdoudata/Monkeypox/')
# 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", ".npg", ".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()
代码输出:
代码输入:
total_datadir = 'F:/lsydata/houdoudata/'
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)
print(total_data)
代码输出:
Dataset ImageFolder
Number of datapoints: 2142
Root location: F:/lsydata/houdoudata/
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])
)
代码输入:
A = total_data.class_to_idx
print(A)
代码输出:
{'Monkeypox': 0, 'Others': 1}
总结:关于total_data.class_to_idx是一个存储了数据集类别和对应索引的字典。
3.划分数据集
代码输入:
#----------------------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])
print(train_dataset)
print(test_dataset)
代码输出:
<torch.utils.data.dataset.Subset object at 0x000002440C23B910>
<torch.utils.data.dataset.Subset object at 0x000002440C23B8B0>
代码输入:
print(train_size, test_size)
代码输出:
1713 429
代码输入:
batch_size = 32
train_dl = torch.utils.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1)
test_dl = torch.utils.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
代码输出:
Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y: torch.Size([32]) torch.int64
二、构建简单的CNN网络
代码输入:
#-------------------------------构建简单的cnn网络----------------------------
class Network_bn(nn.Module):
def __init__(self):
super(Network_bn, self).__init__() #特征提取网络
self.conv1 = nn.Conv2d(3, 12, kernel_size=5, stride=1, padding=0)
self.bn1 = nn.BatchNorm2d(12)
self.conv2 = nn.Conv2d(12, 12, kernel_size=5, stride=1, padding=0)
self.bn2 = nn.BatchNorm2d(12)
self.pool = nn.MaxPool2d(2, 2)
self.conv4 = nn.Conv2d(12, 24, kernel_size=5, stride=1, padding=0)
self.bn4 = nn.BatchNorm2d(24)
self.conv5 = nn.Conv2d(24, 24, kernel_size=5, stride=1, padding=0)
self.bn5 = nn.BatchNorm2d(24)
# 分类网络
self.fc1 = nn.Linear(24*50*50, len(classeNames))
# 向前传播
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)
print(model)
代码输出:
Using cuda device
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=2, bias=True)
)
三、训练模型
1.设置超参数
#-----------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.编写训练函数
#-------------------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
3.编写测试函数
#--------------------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
4.正式训练
#---------------------------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')
代码输出:
Epoch: 1, Train_acc:58.9%, Train_loss:0.700, Test_acc:65.3%, Test_loss:0.642
Epoch: 2, Train_acc:66.3%, Train_loss:0.634, Test_acc:68.8%, Test_loss:0.585
Epoch: 3, Train_acc:71.0%, Train_loss:0.579, Test_acc:73.9%, Test_loss:0.527
Epoch: 4, Train_acc:73.0%, Train_loss:0.528, Test_acc:73.9%, Test_loss:0.548
Epoch: 5, Train_acc:76.5%, Train_loss:0.499, Test_acc:69.5%, Test_loss:0.649
Epoch: 6, Train_acc:78.1%, Train_loss:0.476, Test_acc:76.2%, Test_loss:0.499
Epoch: 7, Train_acc:80.7%, Train_loss:0.451, Test_acc:79.0%, Test_loss:0.475
Epoch: 8, Train_acc:82.2%, Train_loss:0.429, Test_acc:78.6%, Test_loss:0.471
Epoch: 9, Train_acc:84.0%, Train_loss:0.407, Test_acc:78.3%, Test_loss:0.450
Epoch:10, Train_acc:84.5%, Train_loss:0.393, Test_acc:80.2%, Test_loss:0.466
Epoch:11, Train_acc:85.5%, Train_loss:0.379, Test_acc:81.4%, Test_loss:0.423
Epoch:12, Train_acc:86.2%, Train_loss:0.368, Test_acc:79.5%, Test_loss:0.441
Epoch:13, Train_acc:87.9%, Train_loss:0.350, Test_acc:82.1%, Test_loss:0.428
Epoch:14, Train_acc:88.5%, Train_loss:0.334, Test_acc:81.6%, Test_loss:0.414
Epoch:15, Train_acc:89.7%, Train_loss:0.325, Test_acc:81.1%, Test_loss:0.410
Epoch:16, Train_acc:89.0%, Train_loss:0.317, Test_acc:81.6%, Test_loss:0.412
Epoch:17, Train_acc:90.3%, Train_loss:0.308, Test_acc:81.8%, Test_loss:0.422
Epoch:18, Train_acc:90.9%, Train_loss:0.297, Test_acc:83.9%, Test_loss:0.391
Epoch:19, Train_acc:90.8%, Train_loss:0.291, Test_acc:83.4%, Test_loss:0.399
Epoch:20, Train_acc:91.9%, Train_loss:0.275, Test_acc:83.9%, Test_loss:0.382
四、结果可视化
1. Loss与Accuracy图
#--------------------------------结果可视化------------------------
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()
代码输出:
2. 指定图片进行预测
输入代码:
#-------------指定图片进行预测---------------------
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:/lsydata/houdoudata/Monkeypox/M01_01_00.jpg',
model=model,
transform=train_transforms,
classes=classes)
输出代码:
预测结果是:Monkeypox
五、保存并加载模型
代码输入:
# 模型保存
PATH = './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))
代码输出:
<All keys matched successfully>
六、总结
本周练习过程中,运行代码有些不顺利,但一件件的解决了。
首先,学习了如何找到文件夹路径的数据集。
其次也学习了关于total_data.class_to_idx是一个存储了数据集类别和对应索引的字典
最后,学习了相对于上周增加指定图片预测与保存并加载模型这个两个模块。