目录
一、前言
- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍦 参考文章：Pytorch实战 | 第P4周：猴痘病识别
- 🍖 原作者：K同学啊|接辅导、项目定制
二、我的环境
-
电脑系统：Windows 10
-
语言环境：Python 3.7
-
编译器：pycharm
-
深度学习环境：Pytorch
二、分析步骤
1.导入所需要的库
# 1.导入所需要的库
import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(torch.__version__)
print(torch.cuda.is_available())
print(torch.cuda.get_device_name(0))
# 1.7.0+cu110
# True
# 'NVIDIA GeForce GT 730'
device = torch.device("cpu")
2.导入数据
# 2.导入数据
# 定义数据增强和预处理
transform = transforms.Compose([
transforms.Resize((224, 224)),
transforms.RandomHorizontalFlip(),
transforms.RandomRotation(20),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
data_dir = './data/mpox_hou_dou/' # 本地文件数据集存放路径读取
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[2] for path in data_paths]
#print(data_paths)
#print(classeNames)
#exit()
total_datadir = './data/mpox_hou_dou/'
# 关于transforms.Compose的更多介绍可以参考：
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)
# exit()3.划分数据集
# 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])
#print(train_dataset,'\n',test_dataset)
#print(train_size,test_size)
# exit()
batch_size = 32
# num_workers不为零,多线程来读数据，多线程必须加 if __name__ == '__main__':
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
)
#print(train_dl)
#print(test_dl)
# exit()
# 为什么直接跑不能跑，必须要定义一个函数，然后调用才能跑,因为多线程的问题
# [N, C, H, W] 分别代表什么：[batch_size, channel, height, weight]
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
# exit()4.构建简单的CNN网络
import torch.nn.functional as F
class Network_bn(nn.Module):
def __init__(self):
super(Network_bn, self).__init__()
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().to(device)
#print(model)5.训练模型
5.1. 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)
opt = torch.optim.Adam(model.parameters(), lr=learn_rate)5.2.编写训练函数
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset) # 训练集的大小，一共900张图片
num_batches = len(dataloader) # 批次数目，28.125,不够一张的按一张算29（900/32）
# print(size)
# print(num_batches)
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()
#test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()
train_loss += loss.item()
#print(train_acc,'\n',train_loss)
#exit()
train_acc /= size
train_loss /= num_batches
return train_acc, train_loss5.3.编写测试函数
def test(dataloader, model, loss_fn):
size = len(dataloader.dataset) # 训练集的大小，一共900张图片
num_batches = len(dataloader) # 批次数目，28.125,不够一张的按一张算29（900/32）
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()
#print(test_acc,'\n',test_acc)
test_acc /= size
test_loss /= num_batches
return test_acc, test_loss5.4.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')6.模型评估，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()优化算法SGD下的模型效果
优化算法Adam下的模型效果
7.保存模型
# 保存
model_path = './model.pth'
torch.save(model.state_dict(),model_path)
# 将参数加载到model当中
model.load_state_dict(torch.load(model_path,map_location=device))8. 预测一张本地图片
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)
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}')
predict_one_image(image_path = r'E:\cnn\data\mpox_hou_dou\11.png',
model = model,
transform = train_transforms,
classes = classes)9. 总结
在检测本地图片时，已经加载模型了，但是检测时还是会将模型重新训练一次，尝试了一些方法都不行，也不知道问题是出在哪里。
2054
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
