第一周(20240630-20240705)打卡~
医工交叉太难了,一切都要从头开始。。。
去学医吧,学不被定义的医。。。
小五加油!(某医学博士的日常碎碎念)
>- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/0dvHCaOoFnW8SCp3JpzKxg) 中的学习记录博客**
>- **🍖 原作者:[K同学啊](https://mtyjkh.blog.csdn.net/)**
555系统环境:
● 语言环境:Python3
● 编译器:Jupyter
● 深度学习环境:
○ torch==2.2.2
○ torchvision==0.17.2
# 背景知识
# MNIST手写数字数据集来源于是美国国家标准与技术研究所,是著名的公开数据集之一。
# 数据集中的数字图片是由250个不同职业的人纯手写绘制,数据集获取的网址为:http://yann.lecun.com/exdb/mnist/(下载后需解压)。
# 我们一般会采用(train_images, train_labels), (test_images, test_labels) = datasets.mnist.load_data()这行代码直接调用,这样就比较简单
# MNIST手写数字数据集中包含了70000张图片,其中60000张为训练数据,10000为测试数据,70000张图片均是28*28。
# 一、前期准备
# 1.1 设置环境
import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision
# torchvision.datasets是Pytorch自带的一个数据库,我们可以通过代码在线下载数据,这里使用的是torchvision.datasets中的MNIST数据集。
# 使用dataset下载MNIST数据集,并划分好训练集与测试集
# 使用dataloader加载数据,并设置好基本的batch_size
# 1.2 导入数据
# 参数说明:
# ● root (string) :数据地址 ● train (string) :True-训练集,False-测试集
# ● download (bool,optional) : 如果为True,从互联网上下载数据集,并把数据集放在root目录下。
# ● transform (callable, optional ):这里的参数选择一个你想要的数据转化函数,直接完成数据转化
# ● target_transform (callable,optional) :接受目标并对其进行转换的函数/转换。
train_ds = torchvision.datasets.MNIST('data',
train=True,
transform=torchvision.transforms.ToTensor(),
download=True)
test_ds = torchvision.datasets.MNIST('data',
train=False,
transform=torchvision.transforms.ToTensor(),
download=True)
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)
imgs, labels = next(iter(train_dl))
imgs.shape
[out]: torch.Size([32, 1, 28, 28])
# 3.数据可视化
import numpy as np
imgs, labels = next(iter(train_dl))
# 指定图片大小,图像大小为宽20、高5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()
# 二、简易cnn网络
# 2.1 构建模型
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,输入通道为 1,输出通道为 32,卷积核大小为3*3
self.pool1 = nn.MaxPool2d(2) #设置池化层,池化核为2*2
self.conv2 = nn.Conv2d(32, 64, kernel_size=3)#第二层卷积,输入通道为 32,输出通道为 64,卷积核大小为3*3
self.pool2 = nn.MaxPool2d(2)
# 分类网络
self.fc1 = nn.Linear(1600, 64) #定义了第一个全连接层,输入维度为 1600,输出维度为 64。
self.fc2 = nn.Linear(64, num_classes) #定义了第二个全连接层,输入维度为 64,输出维度为 num_classes,num_classes 表示分类的类别数。
# 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
pip install torchinfo
# 2.2 加载并打印模型
from torchinfo import summary
model = Model()
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
# 3.1 设置超参数
loss_fn = nn.CrossEntropyLoss() # 创建交叉熵损失函数
learn_rate = 1e-2 # 学习率
opt = torch.optim.SGD(model.parameters(),lr=learn_rate) #随机梯度下降优化器
# 3.2 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
# 3.3 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
# 3.4 正式训练
device = torch.device("cpu")
epochs = 10
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:80.1%, Train_loss:0.684, Test_acc:93.2%,Test_loss:0.231 Epoch: 2, Train_acc:94.4%, Train_loss:0.184, Test_acc:96.2%,Test_loss:0.120 Epoch: 3, Train_acc:96.5%, Train_loss:0.115, Test_acc:97.5%,Test_loss:0.087 Epoch: 4, Train_acc:97.2%, Train_loss:0.090, Test_acc:97.6%,Test_loss:0.078 Epoch: 5, Train_acc:97.7%, Train_loss:0.075, Test_acc:98.0%,Test_loss:0.063 Epoch: 6, Train_acc:98.0%, Train_loss:0.066, Test_acc:97.9%,Test_loss:0.060 Epoch: 7, Train_acc:98.2%, Train_loss:0.059, Test_acc:98.4%,Test_loss:0.050 Epoch: 8, Train_acc:98.4%, Train_loss:0.053, Test_acc:98.5%,Test_loss:0.048 Epoch: 9, Train_acc:98.6%, Train_loss:0.048, Test_acc:98.6%,Test_loss:0.042 Epoch:10, Train_acc:98.7%, Train_loss:0.044, Test_acc:98.6%,Test_loss:0.042 Done
# 四、结果可视化
plt.rcParams['font.sans-serif'] = ['SimHei', 'path/to/SimHei.ttf'] #增加字体
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()