【Pytorch NOTE】P1 实现mnist手写数字识别

DL学习笔记 P1
【Pytorch NOTE】实现mnist手写数字识别

---

---

前言

• 🍨 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、设置GPU

import torch
# noinspection PyUnresolvedReferences
import torch.nn as nn
# noinspection PyUnresolvedReferences
import matplotlib.pyplot as plt
# noinspection PyUnresolvedReferences
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")

print(device)

二、正式开始

1.导入数据

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)

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))
print(imgs.shape)

2.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()

3.构建网络

#构建网络
import torch.nn.functional as F
num_classes = 10
class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1,32,kernel_size = 3)
        self.pool1 = nn.MaxPool2d(2)
        self.conv2 = nn.Conv2d(32,64,kernel_size = 3)
        self.pool2 = nn.MaxPool2d(2)

        self.fc1 = nn.Linear(1600,64)
        self.fc2 = nn.Linear(64,num_classes)
    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)

输出

=================================================================
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
=================================================================

4.设置参数

#设置超参数
loss_fn = nn.CrossEntropyLoss()
learn_rate = 1e-2
opt = torch.optim.SGD(model.parameters(),lr= learn_rate)

5.编写训练函数和测试函数

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    num_batches =  len(dataloader)

    train_loss, train_acc = 0,0

    for X, y in dataloader:
        X, y = X.to(device), y.to(device)

        pred = model(X)
        loss = loss_fn(pred, y)

        #反向传播
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        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

def test (dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    test_loss, test_acc = 0,0

    with torch.no_grad():
        for imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)

            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

6.训练模型

#训练模型
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')

7.结果可视化

#将结果可视化
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings("ignore")
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

plt.rcParams['figure.dpi'] = 100

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()

---

总结

本文首次利用Pytorch环境搭建训练模型实现mnist数据集的手写数字识别