深度学习学习笔记01-Pytorch实现mnist手写数字识别
我的环境
电脑系统:Windows 11
显卡:NVIDIA RTX4060
语言环境:Python 3.8.10
开发工具:Jupyter notebook
深度学习环境:Pytorch 1.9.0 + cu111
一、前期准备
设置GPU
若输出cuda则使用了GPU,否则使用的是CPU
import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision
# 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")
device
device(type='cuda') 我的电脑使用的是gpu加速
代码输出
device(type=‘cuda’)
导入数据
从dataset下载MNIST数据集,划分训练集与测试集
函数原型:
torchvision.datasets.MNIST(root, train=True, transform=None, target_transform=None, download=False)
train_ds = torchvision.datasets.MNIST('data',
train=True,
transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
download=True)
test_ds = torchvision.datasets.MNIST('data',
train=False,
transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
download=True)
torch.utils.data.DataLoader函数
torch.utils.data.DataLoader是Pytorch自带的一个数据加载器,结合了数据集和取样器,并且可以提供多个线程处理数据集。
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_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])
代码输出
torch.Size([32, 1, 28, 28])
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')
#plt.show() 如果你使用的是Pycharm编译器,请加上这行代码
二、CNN网络
import torch.nn.functional as F
num_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*3
self.pool1 = nn.MaxPool2d(2) # 设置池化层,池化核大小为2*2
self.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
加载并打印模型
import torchinfo
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
=================================================================
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
超参数的设定
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)
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
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
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')
d:\python38\lib\site-packages\torch\nn\functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at ..\c10/core/TensorImpl.h:1156.)
return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
Epoch: 1, Train_acc:80.9%, Train_loss:0.673, Test_acc:93.3%,Test_loss:0.221
Epoch: 2, Train_acc:94.5%, Train_loss:0.181, Test_acc:96.6%,Test_loss:0.112
Epoch: 3, Train_acc:96.5%, Train_loss:0.118, Test_acc:97.3%,Test_loss:0.089
Epoch: 4, Train_acc:97.2%, Train_loss:0.092, Test_acc:97.9%,Test_loss:0.066
Epoch: 5, Train_acc:97.7%, Train_loss:0.077, Test_acc:98.0%,Test_loss:0.065
Done
代码输出
Epoch: 1, Train_acc:80.0%, Train_loss:0.689, Test_acc:94.1%,Test_loss:0.198
Epoch: 2, Train_acc:94.9%, Train_loss:0.169, Test_acc:96.5%,Test_loss:0.117
Epoch: 3, Train_acc:96.6%, Train_loss:0.111, Test_acc:97.1%,Test_loss:0.091
Epoch: 4, Train_acc:97.3%, Train_loss:0.087, Test_acc:97.6%,Test_loss:0.073
Epoch: 5, Train_acc:97.7%, Train_loss:0.075, Test_acc:98.0%,Test_loss:0.063
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()