- 🍨 本文为🔗365天深度学习训练营 内部限免文章（版权归 K同学啊 所有）
- 🍦 参考文章地址： 🔗第P1周：实现mnist手写数字识别 | 365天深度学习训练营
- 🍖 作者：K同学啊 | 接辅导、程序定制
文章目录
- 我的环境：
- 一、前期工作
- 1. 设置 GPU
- 2. 导入数据
- 3. 数据可视化
- 二、构建简单的CNN网络
- 三、训练模型
- 1. 设置超参数
- 2. 编写训练函数
- 3. 编写测试函数
- 4. 正式训练
- 四、结果可视化
- 五、用自己制作的图片进行预测
我的环境：
- 语言环境：Python 3.7.13
- 编译器：jupyter notebook
- 深度学习环境：
- torch==1.12.1+cu113、cuda==11.3.1
- torchvision==0.13.1+cu113、cuda==11.3.1
一、前期工作
1. 设置 GPU
import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvisiondevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")device
device(type='cuda')
2. 导入数据
train_ds = torchvision.datasets.MNIST('data', train=True, transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensordownload=True)test_ds = torchvision.datasets.MNIST('data', train=False, transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensordownload=True)
batch_size = 32train_dl = torch.utils.data.DataLoader(train_ds, batch_size=batch_size, shuffle=True)test_dl = torch.utils.data.DataLoader(test_ds, batch_size=batch_size)
# 取一个批次查看数据格式
# 数据的shape为：[batch_size, channel, height, weight]
# 其中batch_size为自己设定，channel，height和weight分别是图片的通道数，高度和宽度。
imgs, labels = next(iter(train_dl))
imgs.shape
torch.Size([32, 1, 28, 28])
3. 数据可视化
import numpy as np# 指定图片大小，图像大小为20宽、5高的绘图(单位为英寸inch)
plt.figure(figsize=(20, 5))
for i, imgs in enumerate(imgs[:20]):# 维度缩减npimg = np.squeeze(imgs.numpy())# 将整个figure分成2行10列，绘制第i+1个子图。plt.subplot(2, 10, i+1)plt.imshow(npimg, cmap=plt.cm.binary)plt.axis('off')
二、构建简单的CNN网络
使用 image_dataset_from_directory 方法将磁盘中的数据加载到 tf.data.Dataset 中
import torch.nn.functional as Fnum_classes = 10 # 图片的类别数class Model(nn.Module):def __init__(self):super().__init__()# 特征提取网络self.conv1 = nn.Conv2d(1, 32, kernel_size=3) # 第一层卷积,卷积核大小为3*3self.pool1 = nn.MaxPool2d(2) # 设置池化层，池化核大小为2*2self.conv2 = nn.Conv2d(32, 64, kernel_size=3) # 第二层卷积,卷积核大小为3*3 self.pool2 = nn.MaxPool2d(2) # 分类网络self.fc1 = nn.Linear(1600, 64) self.fc2 = nn.Linear(64, num_classes)# 前向传播def forward(self, x):x = self.pool1(F.relu(self.conv1(x))) x = self.pool2(F.relu(self.conv2(x)))x = torch.flatten(x, start_dim=1)x = F.relu(self.fc1(x))x = self.fc2(x)return x
from torchinfo import summary
# 将模型转移到GPU中（我们模型运行均在GPU中进行）
model = Model().to(device)summary(model)
=================================================================
Layer (type:depth-idx) Param #
=================================================================
Model --
├─Conv2d: 1-1 320
├─MaxPool2d: 1-2 --
├─Conv2d: 1-3 18,496
├─MaxPool2d: 1-4 --
├─Linear: 1-5 102,464
├─Linear: 1-6 650
=================================================================
Total params: 121,930
Trainable params: 121,930
Non-trainable params: 0
=================================================================
三、训练模型
1. 设置超参数
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-2 # 学习率
opt = torch.optim.SGD(model.parameters(),lr=learn_rate)
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losstrain_acc += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc /= sizetrain_loss /= num_batchesreturn train_acc, train_loss
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losstarget_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 /= sizetest_loss /= num_batchesreturn test_acc, test_loss
4. 正式训练
epochs = 5
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:77.6%, Train_loss:0.744, Test_acc:91.1%，Test_loss:0.284
Epoch: 2, Train_acc:94.1%, Train_loss:0.196, Test_acc:96.2%，Test_loss:0.128
Epoch: 3, Train_acc:96.2%, Train_loss:0.123, Test_acc:97.5%，Test_loss:0.089
Epoch: 4, Train_acc:97.1%, Train_loss:0.094, Test_acc:97.4%，Test_loss:0.078
Epoch: 5, Train_acc:97.5%, Train_loss:0.078, Test_acc:98.0%，Test_loss:0.062
Done
四、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()
五、用自己制作的图片进行预测
for i in range(10):img_path = 'imgs/no' + str(i) + '.png'img = Image.open(img_path)img = img.convert('L')img = data_transform(img)img = torch.unsqueeze(img, dim=0)img = img.to(device)model.eval()with torch.no_grad():output = model(img)print(output.argmax(1).item())
预测结果：
0
1
2
3
4
5
6
7
8
9
