Pytorch实战 | P2 彩色图片识别(深度学习实践pytorch)

一、我的环境：

● 语言环境：Python3.8
● 编译器：pycharm
● 深度学习环境：Pytorch

二、主要代码实现

1、main.py

import matplotlib.pyplot as plt
import torch
import numpy as np
from model import *
from torchinfo import summary

# 一、 数据准备

# --- 1、设置GPU ---
import torchvision.datasets

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# --- 2、导入数据 ---
train_ds = torchvision.datasets.CIFAR10('data',
                                        train=True,
                                        transform=torchvision.transforms.ToTensor(),  # 将数据类型转化为Tensor
                                        download=True)

test_ds = torchvision.datasets.CIFAR10('data',
                                       train=False,
                                       transform=torchvision.transforms.ToTensor(),  # 将数据类型转化为Tensor
                                       download=False)

batch_size = 32

train_dl = torch.utils.data.DataLoader(train_ds,
                                       batch_size=batch_size,
                                       shuffle=False)
test_dl = torch.utils.data.DataLoader(test_ds, batch_size=batch_size)

# --- 3、数据可视化 ---
imgs, labels = next(iter(train_dl))
plt.figure(figsize=(32, 5))
for i, imgs in enumerate(imgs):
    npimg = imgs.numpy().transpose((1, 2, 0))
    plt.subplot(2, 16, i + 1)
    plt.imshow(npimg, cmap=plt.cm.binary)
    plt.axis('off')
plt.show()

# 二、构建网络
# model.py  __init__() forward()
# 加载并打印模型
model = Model().to(device)

summary(model)

# 三、模型训练

# --- 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)  # 定义优化器，随机梯度下降算法

# --- 2、编写训练函数 ---
# model.py train(dataloader, model, loss_fn, optimizer, device)

# --- 3、编写测试函数 ---
# model.py test(dataloader, model, loss_fn, optimizer, device)

# --- 4、正式训练 ---
epochs = 10
train_loss = []
train_acc = []
test_loss = []
test_acc = []

for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = model.train1(train_dl, model, loss_fn, opt, device)

    model.eval()
    epoch_test_acc, epoch_test_loss = model.test1(test_dl, model, loss_fn, opt, device)

    train_loss.append(epoch_train_loss)
    train_acc.append(epoch_train_acc)
    test_loss.append(epoch_test_loss)
    test_acc.append(epoch_test_acc)

    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')

# 四、结果可视化
import matplotlib.pyplot as plt
import warnings

warnings.filterwarnings("ignore")
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

epoch_range = range(epochs)

plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)

plt.plot(epoch_range, train_acc, label='Training Accuracy')
plt.plot(epoch_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epoch_range, train_loss, label='Training loss')
plt.plot(epoch_range, test_loss, label='Test loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

2、 model.py

# _*_coding:utf-8_*_
import torch
import torch.nn as nn
import torch.nn.functional as F

num_class = 10  # 图片的分类数


class Model(nn.Module):
    def __init__(self):
        super().__init__()
        # 特征提取网络
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3)
        self.pool1 = nn.MaxPool2d(kernel_size=2)
        self.conv2 = nn.Conv2d(64, 64, kernel_size=3)
        self.pool2 = nn.MaxPool2d(kernel_size=2)
        self.conv3 = nn.Conv2d(64, 128, kernel_size=3)
        self.pool3 = nn.MaxPool2d(kernel_size=2)

        # 分类网络
        self.fc1 = nn.Linear(512, 256)
        self.fc2 = nn.Linear(256, num_class)

    # 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 = self.pool3(F.relu(self.conv3(x)))

        x = torch.flatten(x, start_dim=1)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)

        return x

    def train1(self, dataloader, model, loss_fn, optimizer, device):
        size = len(dataloader.dataset)  # 6000张图片
        num_batch = len(dataloader)  # 批次的数目

        train_loss, train_acc = 0, 0  # 初始化训练损失 和 正确率

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

            pred = model(X)  # 计算网络输出
            loss = loss_fn(pred, y)  # 计算网络输出和预测的loss

            # 反向传播
            optimizer.zero_grad()  # 梯度归零
            loss.backward()  # 反向传播
            optimizer.step()  # 自动更新参数

            train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
            train_loss += loss.item()

        train_acc /= size
        train_loss /= num_batch

        return train_acc, train_loss

    def test1(self, dataloader, model, loss_fn, optimizer, device):
        size = len(dataloader.dataset)
        number_batch = len(dataloader)

        test_loss, test_acc = 0, 0  # 验证数据的损失和准确率

        # 停止更新梯度
        with torch.no_grad():
            for imgs, target in dataloader:
                imgs, target = imgs.to(device), target.to(device)

                target_pred = model(imgs)  # 网络预测结果

                loss = loss_fn(target_pred, target)  # 计算loss

                test_loss += loss.item()
                test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()

        test_loss /= number_batch
        test_acc /= size

        return test_acc, test_loss

三、遇到的疑问

为什么model(x)可以直接调用forward（x）?

forward是自动调用的

    model = Net()
    y = model(x)

如上则调用网络模型定义的forward方法。

即，当把定义的网络模型model当作函数调用的时候就自动调用定义的网络模型的forward方法。

是通过nn.Module 的__call__方法调用的

就相当于调用了模型就是直接调用它的forward函数，y=model(x)，这个x就是直接传入到forward函数的x参数
————————————————
版权声明：本文为CSDN博主「hxxjxw」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/hxxjxw/article/details/107707471