- 🍨 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
一、思维导图总结
二、代码实现
1、设置GPU
若设备支持GPU就使用GPU,否则使用CPU
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
devicedevice(type='cuda')2、数据准备
2.1、识别数据路径
# 查看当前工作路径（确认路径是否正确）
print("当前工作路径：", os.getcwd())
# 定义数据目录（建议用绝对路径更稳妥，相对路径依赖当前工作路径）
data_dir = './data/猴痘数据集/'
data_dir = pathlib.Path(data_dir)
# 获取数据目录下的所有子路径（文件夹或文件）
data_paths = list(data_dir.glob('*'))
# 提取每个子路径的名称（即类别名，自动适配系统分隔符）
classeNames = [path.name for path in data_paths]
classeNames当前工作路径： /root/365天训练营/Pytorch实战
['Monkeypox', 'Others']2.2、获取数据
import torchvision
from torchvision import transforms, datasets
total_datadir = './data/猴痘数据集/'
# 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_dataDataset ImageFolder
Number of datapoints: 1777
Root location: ./data/猴痘数据集/
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])
)total_data.class_to_idx{'Monkeypox': 0, 'Others': 1}2.3、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])
train_dataset, test_dataset(<torch.utils.data.dataset.Subset at 0x7f0c95efe140>,
<torch.utils.data.dataset.Subset at 0x7f0c95efe0e0>)train_size,test_size(1421, 356)batch_size = 32
# torch.utils.data.DataLoader 是 PyTorch 中用于加载和管理数据的一个实用工具类
# 它允许你以小批次的方式迭代你的数据集，这对于训练神经网络和其他机器学习任务非常有用
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)
breakShape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y: torch.Size([32]) torch.int643、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__()
"""
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)
modelUsing 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)
)4、模型训练
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)4.2、训练函数
# 训练循环函数
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
# 测试函数和训练函数大致相同，但是由于不进行梯度下降对网络权重进行更新，所以不需要传入优化器
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
# 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')Epoch: 1, Train_acc:66.4%, Train_loss:0.631, Test_acc:66.0%，Test_loss:0.663
Epoch: 2, Train_acc:74.1%, Train_loss:0.543, Test_acc:70.2%，Test_loss:0.553
Epoch: 3, Train_acc:76.8%, Train_loss:0.492, Test_acc:73.0%，Test_loss:0.539
Epoch: 4, Train_acc:80.2%, Train_loss:0.451, Test_acc:73.6%，Test_loss:0.517
Epoch: 5, Train_acc:81.4%, Train_loss:0.431, Test_acc:74.7%，Test_loss:0.603
Epoch: 6, Train_acc:82.4%, Train_loss:0.417, Test_acc:76.4%，Test_loss:0.527
Epoch: 7, Train_acc:84.5%, Train_loss:0.387, Test_acc:77.5%，Test_loss:0.477
Epoch: 8, Train_acc:85.1%, Train_loss:0.373, Test_acc:77.2%，Test_loss:0.482
Epoch: 9, Train_acc:86.3%, Train_loss:0.358, Test_acc:77.8%，Test_loss:0.448
Epoch:10, Train_acc:86.5%, Train_loss:0.348, Test_acc:78.7%，Test_loss:0.452
Epoch:11, Train_acc:87.7%, Train_loss:0.332, Test_acc:78.4%，Test_loss:0.472
Epoch:12, Train_acc:87.8%, Train_loss:0.324, Test_acc:79.5%，Test_loss:0.442
Epoch:13, Train_acc:88.6%, Train_loss:0.314, Test_acc:78.9%，Test_loss:0.462
Epoch:14, Train_acc:89.5%, Train_loss:0.304, Test_acc:80.6%，Test_loss:0.425
Epoch:15, Train_acc:89.3%, Train_loss:0.294, Test_acc:82.6%，Test_loss:0.423
Epoch:16, Train_acc:90.1%, Train_loss:0.288, Test_acc:80.6%，Test_loss:0.415
Epoch:17, Train_acc:90.9%, Train_loss:0.277, Test_acc:80.9%，Test_loss:0.409
Epoch:18, Train_acc:90.6%, Train_loss:0.264, Test_acc:81.2%，Test_loss:0.411
Epoch:19, Train_acc:91.3%, Train_loss:0.261, Test_acc:84.0%，Test_loss:0.411
Epoch:20, Train_acc:91.8%, Train_loss:0.250, Test_acc:82.0%，Test_loss:0.436
Done5、结果可视化
5.1、Loss与Accuracy图
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
from datetime import datetime
current_time = datetime.now() # 获取当前时间
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.xlabel(current_time) # 打卡请带上时间戳，否则代码截图无效
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()
5.2、图片预测
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='./data/猴痘数据集/Monkeypox/M01_01_10.jpg',
model=model,
transform=train_transforms,
classes=classes)预测结果是：Monkeypox5.3、模型保存
# 模型保存
print("当前工作路径：", os.getcwd())
PATH = './model/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))当前工作路径： /root/365天训练营/Pytorch实战
<All keys matched successfully>
扫一扫
2964
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
