InceptionV4 Pytorch 实现图片分类

liuhenghui52012024-09-02 10:23

一、目录结构

训练过程：

  1. 在训练集和测试集分类目录中放好待训练的分类图片（f1,f2,f3）
  2. 运行模型训练代码，生成模型参数文件
  3. 运行分类测试文件，设置待验证的图片路径，调用模型文件得出分类结果

二、模型构建代码

python 复制代码 
import torch
import torch.nn as nn
import torch.nn.functional as F

class BasicConv2d(nn.Module):
    def __init__(self, in_channels, out_channels, **kwargs):
        super(BasicConv2d, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, **kwargs)
        self.bn = nn.BatchNorm2d(out_channels)

    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        return F.relu(x)


class InceptionA(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(InceptionA, self).__init__()
        # branch1: avgpool --> conv1*1(96)
        self.b1_1 = nn.AvgPool2d(kernel_size=3, padding=1, stride=1)
        self.b1_2 = BasicConv2d(in_channels, 96, kernel_size=1)

        # branch2: conv1*1(96)
        self.b2 = BasicConv2d(in_channels, 96, kernel_size=1)

        # branch3: conv1*1(64) --> conv3*3(96)
        self.b3_1 = BasicConv2d(in_channels, 64, kernel_size=1)
        self.b3_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)

        # branch4: conv1*1(64) --> conv3*3(96) --> conv3*3(96)
        self.b4_1 = BasicConv2d(in_channels, 64, kernel_size=1)
        self.b4_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)
        self.b4_3 = BasicConv2d(96, 96, kernel_size=3, padding=1)

    def forward(self, x):
        y1 = self.b1_2(self.b1_1(x))
        y2 = self.b2(x)
        y3 = self.b3_2(self.b3_1(x))
        y4 = self.b4_3(self.b4_2(self.b4_1(x)))

        outputsA = [y1, y2, y3, y4]
        return torch.cat(outputsA, 1)


class InceptionB(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(InceptionB, self).__init__()
        # branch1: avgpool --> conv1*1(128)
        self.b1_1 = nn.AvgPool2d(kernel_size=3, padding=1, stride=1)
        self.b1_2 = BasicConv2d(in_channels, 128, kernel_size=1)

        # branch2: conv1*1(384)
        self.b2 = BasicConv2d(in_channels, 384, kernel_size=1)

        # branch3: conv1*1(192) --> conv1*7(224) --> conv1*7(256)
        self.b3_1 = BasicConv2d(in_channels, 192, kernel_size=1)
        self.b3_2 = BasicConv2d(192, 224, kernel_size=(1, 7), padding=(0, 3))
        self.b3_3 = BasicConv2d(224, 256, kernel_size=(1, 7), padding=(0, 3))

        # branch4: conv1*1(192) --> conv1*7(192) --> conv7*1(224) --> conv1*7(224) --> conv7*1(256)
        self.b4_1 = BasicConv2d(in_channels, 192, kernel_size=1, stride=1)
        self.b4_2 = BasicConv2d(192, 192, kernel_size=(1, 7), padding=(0, 3))
        self.b4_3 = BasicConv2d(192, 224, kernel_size=(7, 1), padding=(3, 0))
        self.b4_4 = BasicConv2d(224, 224, kernel_size=(1, 7), padding=(0, 3))
        self.b4_5 = BasicConv2d(224, 256, kernel_size=(7, 1), padding=(3, 0))

    def forward(self, x):
        y1 = self.b1_2(self.b1_1(x))
        y2 = self.b2(x)
        y3 = self.b3_3(self.b3_2(self.b3_1(x)))
        y4 = self.b4_5(self.b4_4(self.b4_3(self.b4_2(self.b4_1(x)))))

        outputsB = [y1, y2, y3, y4]
        return torch.cat(outputsB, 1)


class InceptionC(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(InceptionC, self).__init__()
        # branch1: avgpool --> conv1*1(256)
        self.b1_1 = nn.AvgPool2d(kernel_size=3, padding=1, stride=1)
        self.b1_2 = BasicConv2d(in_channels, 256, kernel_size=1)

        # branch2: conv1*1(256)
        self.b2 = BasicConv2d(in_channels, 256, kernel_size=1)

        # branch3: conv1*1(384) --> conv1*3(256) & conv3*1(256)
        self.b3_1 = BasicConv2d(in_channels, 384, kernel_size=1)
        self.b3_2_1 = BasicConv2d(384, 256, kernel_size=(1, 3), padding=(0, 1))
        self.b3_2_2 = BasicConv2d(384, 256, kernel_size=(3, 1), padding=(1, 0))

        # branch4: conv1*1(384) --> conv1*3(448) --> conv3*1(512) --> conv3*1(256) & conv7*1(256)
        self.b4_1 = BasicConv2d(in_channels, 384, kernel_size=1, stride=1)
        self.b4_2 = BasicConv2d(384, 448, kernel_size=(1, 3), padding=(0, 1))
        self.b4_3 = BasicConv2d(448, 512, kernel_size=(3, 1), padding=(1, 0))
        self.b4_4_1 = BasicConv2d(512, 256, kernel_size=(3, 1), padding=(1, 0))
        self.b4_4_2 = BasicConv2d(512, 256, kernel_size=(1, 3), padding=(0, 1))

    def forward(self, x):
        y1 = self.b1_2(self.b1_1(x))
        y2 = self.b2(x)
        y3_1 = self.b3_2_1(self.b3_1(x))
        y3_2 = self.b3_2_2(self.b3_1(x))
        y4_1 = self.b4_4_1(self.b4_3(self.b4_2(self.b4_1(x))))
        y4_2 = self.b4_4_2(self.b4_3(self.b4_2(self.b4_1(x))))

        outputsC = [y1, y2, y3_1, y3_2, y4_1, y4_2]
        return torch.cat(outputsC, 1)


class ReductionA(nn.Module):
    def __init__(self, in_channels, out_channels, k, l, m, n):
        super(ReductionA, self).__init__()
        # branch1: maxpool3*3(stride2 valid)
        self.b1 = nn.MaxPool2d(kernel_size=3, stride=2)

        # branch2: conv3*3(n stride2 valid)
        self.b2 = BasicConv2d(in_channels, n, kernel_size=3, stride=2)

        # branch3: conv1*1(k) --> conv3*3(l) --> conv3*3(m stride2 valid)
        self.b3_1 = BasicConv2d(in_channels, k, kernel_size=1)
        self.b3_2 = BasicConv2d(k, l, kernel_size=3, padding=1)
        self.b3_3 = BasicConv2d(l, m, kernel_size=3, stride=2)

    def forward(self, x):
        y1 = self.b1(x)
        y2 = self.b2(x)
        y3 = self.b3_3(self.b3_2(self.b3_1(x)))

        outputsRedA = [y1, y2, y3]
        return torch.cat(outputsRedA, 1)


class ReductionB(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(ReductionB, self).__init__()
        # branch1: maxpool3*3(stride2 valid)
        self.b1 = nn.MaxPool2d(kernel_size=3, stride=2)

        # branch2: conv1*1(192) --> conv3*3(192 stride2 valid)
        self.b2_1 = BasicConv2d(in_channels, 192, kernel_size=1)
        self.b2_2 = BasicConv2d(192, 192, kernel_size=3, stride=2)

        # branch3: conv1*1(256) --> conv1*7(256) --> conv7*1(320) --> conv3*3(320 stride2 valid)
        self.b3_1 = BasicConv2d(in_channels, 256, kernel_size=1)
        self.b3_2 = BasicConv2d(256, 256, kernel_size=(1, 7), padding=(0, 3))
        self.b3_3 = BasicConv2d(256, 320, kernel_size=(7, 1), padding=(3, 0))
        self.b3_4 = BasicConv2d(320, 320, kernel_size=3, stride=2)

    def forward(self, x):
        y1 = self.b1(x)
        y2 = self.b2_2(self.b2_1((x)))
        y3 = self.b3_4(self.b3_3(self.b3_2(self.b3_1(x))))

        outputsRedB = [y1, y2, y3]
        return torch.cat(outputsRedB, 1)


class Stem(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(Stem, self).__init__()
        # conv3*3(32 stride2 valid)
        self.conv1 = BasicConv2d(in_channels, 32, kernel_size=3, stride=2)
        # conv3*3(32 valid)
        self.conv2 = BasicConv2d(32, 32, kernel_size=3)
        # conv3*3(64)
        self.conv3 = BasicConv2d(32, 64, kernel_size=3, padding=1)
        # maxpool3*3(stride2 valid) & conv3*3(96 stride2 valid)
        self.maxpool4 = nn.MaxPool2d(kernel_size=3, stride=2)
        self.conv4 = BasicConv2d(64, 96, kernel_size=3, stride=2)

        # conv1*1(64) --> conv3*3(96 valid)
        self.conv5_1_1 = BasicConv2d(160, 64, kernel_size=1)
        self.conv5_1_2 = BasicConv2d(64, 96, kernel_size=3)
        # conv1*1(64) --> conv7*1(64) --> conv1*7(64) --> conv3*3(96 valid)
        self.conv5_2_1 = BasicConv2d(160, 64, kernel_size=1)
        self.conv5_2_2 = BasicConv2d(64, 64, kernel_size=(7, 1), padding=(3, 0))
        self.conv5_2_3 = BasicConv2d(64, 64, kernel_size=(1, 7), padding=(0, 3))
        self.conv5_2_4 = BasicConv2d(64, 96, kernel_size=3)

        # conv3*3(192 valid)
        self.conv6 = BasicConv2d(192, 192, kernel_size=3, stride=2)
        # maxpool3*3(stride2 valid)
        self.maxpool6 = nn.MaxPool2d(kernel_size=3, stride=2)

    def forward(self, x):
        y1_1 = self.maxpool4(self.conv3(self.conv2(self.conv1(x))))
        y1_2 = self.conv4(self.conv3(self.conv2(self.conv1(x))))
        y1 = torch.cat([y1_1, y1_2], 1)

        y2_1 = self.conv5_1_2(self.conv5_1_1(y1))
        y2_2 = self.conv5_2_4(self.conv5_2_3(self.conv5_2_2(self.conv5_2_1(y1))))
        y2 = torch.cat([y2_1, y2_2], 1)

        y3_1 = self.conv6(y2)
        y3_2 = self.maxpool6(y2)
        y3 = torch.cat([y3_1, y3_2], 1)

        return y3


class MyInceptionV4(nn.Module):
    def __init__(self, num_classes):
        super(MyInceptionV4, self).__init__()
        self.stem = Stem(3, 384)
        self.icpA = InceptionA(384, 384)
        self.redA = ReductionA(384, 1024, 192, 224, 256, 384)
        self.icpB = InceptionB(1024, 1024)
        self.redB = ReductionB(1024, 1536)
        self.icpC = InceptionC(1536, 1536)
        self.avgpool = nn.AvgPool2d(kernel_size=8)
        self.dropout = nn.Dropout(p=0.8)
        self.linear = nn.Linear(1536, out_features=num_classes)

    def forward(self, x):
        # Stem Module
        out = self.stem(x)
        # InceptionA Module * 4
        out = self.icpA(self.icpA(self.icpA(self.icpA(out))))
        # ReductionA Module
        out = self.redA(out)
        # InceptionB Module * 7
        out = self.icpB(self.icpB(self.icpB(self.icpB(self.icpB(self.icpB(self.icpB(out)))))))
        # ReductionB Module
        out = self.redB(out)
        # InceptionC Module * 3
        out = self.icpC(self.icpC(self.icpC(out)))
        # Average Pooling
        out = self.avgpool(out)
        out = out.view(out.size(0), -1)
        # Dropout
        out = self.dropout(out)
        # Linear(Softmax)
        out = self.linear(out)

        return out

# def test():
#     x = torch.randn(20, 3, 299, 299)
#     net = MyInceptionV4(num_classes=5)
#     y = net(x)
#     print(y.size())
# test()

三、模型训练代码

python 复制代码 
import time
import torch
from torch import nn
import os
from MyInceptionV4 import MyInceptionV4 as Model
from torchvision.datasets import ImageFolder
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
from tqdm import tqdm



os.environ["PYTORCH_CUDA_ALLOC_CONF"]="expandable_segments:True,max_split_size_mb:64"


def WriteData(fname, *args):
    with open(fname, 'a+') as f:
        for data in args:
            f.write(str(data)+"\t")
        f.write("\n")

def train(dataloader, model, loss_fn, optimizer, device):
    model.train()
    size = len(dataloader.dataset)
    avg_loss = 0

    # 从数据加载器中读取batch(一次读取多少张，即批次数)，X(图片数据)，y(图片真实标签)
    time_start = time.time()
    for batch,(X, y) in enumerate(dataloader): #固定格式：batchL第几批数据，不是批次大小，（X,y）:数值用括号
        # 将数据存储到显卡
        X, y = X.to(device), y.to(device)
        # 得到预测的结果pred
        out = model(X)
        loss = loss_fn(out, y)
        avg_loss += loss # 一个batch的数据
        #反向传播，更新模型参数
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        # 每次训练10次，输出一次当前信息
        if batch % 10 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"Current Batch Training Loss：{loss:>5f} [{current:>5d}/{size:>5d}]")

    # 当一个epoth玩了后返回平均 loss
    avg_loss /= size
    avg_loss = avg_loss.detach().cpu().numpy()

    time_end = time.time()
    print(f"train time:{(time_end - time_start):>0.2f} Avg Loss ={avg_loss:>5f}")
    return avg_loss

def validate(dataloader, model, loss_fn, device):
    size = len(dataloader.dataset)
    # 将模型转为验证模式
    model.eval()
    # 初始化 test_loss 和 correct 用来统计每次的误差
    test_loss, correct = 0, 0
    # 测试时模型参数不用跟新，所以 no_gard()
    # 非训练，推理期用到
    with torch.no_grad():
        # 加载数据加载器，得到里面的X(图片数据) 和 y(真实标签)
        for X, y in tqdm(dataloader):
            # 将数据转到GPU
            X, y = X.to(device), y.to(device)
            # 将图片传入到模型当中就得到预测的值pred
            pred = model(X)
            # 计算预测值pred和真实值y的差距
            test_loss += loss_fn(pred, y).item()
            # 统计预测正确的个数（针对分类）
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()
    test_loss /= size
    correct /= size
    print(f"correct = {correct}, Test Error: \n Accuracy: {(100 * correct):>0.5f}%, Avg loss:{test_loss:>0.5f} \n")
    return correct, test_loss

if __name__=='__main__':
    '''
    加载数据集
    '''
    train_root = "dataset/dataset_train"
    test_root = "dataset/dataset_test"

    train_tf = transforms.Compose([
        transforms.Resize((299, 299)),
        transforms.RandomVerticalFlip(), #对图片进行随机的水平翻转
        transforms.ToTensor() # 把图片改为Tenser格式
    ])

    test_tf = transforms.Compose([
        transforms.Resize((299, 299)),
        transforms.ToTensor()  # 把图片改为Tenser格式
    ])

    batch_size = 32
    train_data = ImageFolder(root=train_root, transform=train_tf)
    train_loader = DataLoader(dataset=train_data, batch_size=batch_size, pin_memory=True, num_workers=4, shuffle=True)

    test_data = ImageFolder(root=test_root, transform=test_tf)
    test_loader = DataLoader(dataset=test_data, batch_size=batch_size, pin_memory=True, num_workers=4, shuffle=True)

    # 如果显卡可用，则用显卡训练
    device = "cuda" if torch.cuda.is_available() else "cpu"
    # device = "cpu"
    print(f"Using {device} device")

    if hasattr(torch.cuda, 'empty_cache'):
        torch.cuda.empty_cache()
    model = Model(num_classes=5)
    model = model.to(device)

    # 定义损失函数，计算相差多少，交叉熵
    loss_fn = nn.CrossEntropyLoss()

    # 定义优化器，用来训练时候优化模型参数，随机梯度下降法
    learning_rate = 1e-4
    optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

    epochs = 40
    loss_ = 10
    save_root = "Model_result/My_Inception_v4/"

    if not os.path.exists(save_root):
        os.makedirs(save_root)

    for t in range(epochs):
        print(f"Epoth {t+1}\n--------------------------------")
        avg_loss = train(train_loader, model, loss_fn, optimizer, device)

        val_accuracy, val_loss = validate(test_loader, model, loss_fn, device)
        # 写入数据
        WriteData(save_root + "My_Inception_v4.txt",
                  "epoch", t,
                  "train_loss", avg_loss,
                  "val_loss", val_loss,
                  "val_accuracy", val_accuracy)
        if t % 5 == 0:
            torch.save(model.state_dict(), save_root+"My_Inception_v4_epoch" + str(t) + "_loss_" + str(avg_loss) + ".pth")

        torch.save(model.state_dict(), save_root + "My_Inception_v4_last.pth")

        if val_loss < loss_:
            loss_ = val_loss
            torch.save(model.state_dict(), save_root + "My_Inception_v4_best.pth")

四、分类测试代码

python 复制代码 
'''
单图测试
'''

import torch
from MyInceptionV4 import MyInceptionV4
from PIL import Image
import torchvision.transforms as transforms
import os


if __name__=='__main__':
    img_path = r"dataset/dataset_train/f3/image_00581.jpg"

    test_tf = transforms.Compose([
        transforms.Resize(((299, 299))),
        transforms.ToTensor()
    ])

    # 如果显卡可用，则用显卡训练
    device = "cuda" if torch.cuda.is_available() else "cpu"
    print(f"Using {device} device")

    model = MyInceptionV4(num_classes=5)
    model = model.to(device)
    state_dict = torch.load(r"Model_result/My_Inception_v4/My_Inception_v4_best.pth")

    model.load_state_dict(state_dict)
    model.eval()
    with torch.no_grad():
        img = Image.open(img_path) #打开图片
        img = img.convert('RGB') #转换为RGB格式
        img = test_tf(img)
        img_tensor = torch.unsqueeze(img, 0) # C,H,W（通道，高，宽） 转为 N,C,H,W
        img_tensor = img_tensor.to(device)
        result = model(img_tensor)

        id = result.argmax(1).item()

        file_list = []
        for a, b, c in os.walk("dataset/dataset_train"):
            if len(b) != 0:
                file_list = b
                print("InveptionV4 对输入的图片预测的结果为：", file_list[id])
相关推荐
咚咚王者几秒前
人工智能之核心技术 深度学习 第四章 循环神经网络（RNN）与序列模型
人工智能·rnn·深度学习
蘑菇物联3 分钟前
蘑菇物联入选“预见·2026”年度双榜，以AI技术赋能制造业绿色转型！
大数据·人工智能
无忧智库7 分钟前
智慧城市核心标准全景解析：从顶层设计到落地实践的深度解读（PPT）
人工智能·智慧城市
2501_9421917719 分钟前
【YOLOv26实战】健身器材物体检测与识别：从模型优化到实际应用
人工智能·yolo·目标跟踪
m0_4665252931 分钟前
东软与葫芦岛市民政局签约 共建智慧养老服务平台
大数据·人工智能
乐居生活官37 分钟前
2026五大功能全面的电商软件测评：打造全链路智能运营体系
大数据·人工智能
百***354839 分钟前
2026年GEO服务商选择指南：从信息过载中构建品牌清晰度
人工智能
audyxiao0011 小时前
会议热点扫描｜智慧教育顶级会议AIED 2025的研究热点可视化分析
人工智能·智慧教育·会议热点·aied
执笔论英雄1 小时前
【梯度检查点】
人工智能
虫小宝1 小时前
电商AI导购系统工程化实践：模型训练、部署与在线推理的架构设计
人工智能
热门推荐
01GitHub 镜像站点02OpenCode 入门教程：介绍 · 安装 · 配置第三方 API (如 Claude)03【网络安全测试】Burp Suite工具使用说明、配置及常见问题（有关必回）04Claude Code Skills 实用使用手册05Clawdbot 中文汉化版 接入微信、飞书06在Trae中使用Pencil MCP07struts2 XML外部实体注入漏洞复现（CVE-2025-68493）08UV安装并设置国内源09零门槛部署本地 AI 助手：Clawdbot/Meltbot 部署深度保姆级教程10AI 规范驱动开发“三剑客”深度对比：Spec-Kit、Kiro 与 OpenSpec 实战指南