简介

本篇文章利用pytorch搭建CNN卷积神经网络实现简单花卉分类的任务

一、CNN卷积神经网络基础知识

关于CNN卷积神经网络的基础知识以下文章有详细讲解，可供参考：
CNN笔记：通俗理解卷积神经网络

二、数据集介绍

本文使用花卉数据集，该数据集包含了4317张图片，包含雏菊、蒲公英、玫瑰、向日葵、郁金香五种花卉，我已将数据集拆分为训练集和测试集两部分，以下是数据集目录：

数据集已放于以下链接，有需要可自行下载
花卉数据集

三、代码实现

读取数据

step1.读取train\test文件夹，得到其中的五个子文件夹名称（即五种花卉名称）
step2.读取每一种花卉数量，相加得到总图片数目
step3.创建矩阵存放所有图片数据以及其对应标签
step4.返回数据及其标签

def read_file(path):  # 读取数据，文件夹中包含五个子文件夹data_list = os.listdir(path)  # 得到5个子文件夹名称data_len = 0  # 存放总图片数目for flower_type in data_list:data_len += len(os.listdir(os.path.join(path, flower_type)))data = np.zeros((data_len, 128, 128, 3))data_label = np.zeros(data_len)i = 0for j, flower_type in enumerate(data_list):  # 读出所有图片flower_list = os.listdir(os.path.join(path, flower_type))for img in flower_list:data[i, :, :, :] = cv2.resize(cv2.imread(os.path.join(path, flower_type, img)), (128, 128))data_label[i] = ji += 1return data, data_label
train_data, train_label = read_file('C:/Users/superjw/Desktop/flowers/train')
test_data, test_label = read_file('C:/Users/superjw/Desktop/flowers/test')
print("already get data...")

数据处理

step1.将数据转换为tensor（张量）形式并归一化处理
step2.准备Dataset与Dataloader

class ImgDataset(Dataset):def __init__(self, x=None, y=None, transform=None):self.x = xself.y = yself.transform = transformdef __len__(self):return len(self.x)def __getitem__(self, index):X = self.x[index]if self.transform is not None:X = self.transform(X)if self.y is not None:Y = self.y[index]return X, Yelse:return X
train_transform = transforms.Compose([  # 数据处理transforms.ToTensor(),  # 转换为张量transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),  # 归一化处理])test_transform = transforms.Compose([  # 数据处理transforms.ToTensor(),  # 转换为张量transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),  # 归一化处理])train_dataset = ImgDataset(train_data, train_label, train_transform)train_loader = DataLoader(train_dataset, batch_size=20, shuffle=True)test_dataset = ImgDataset(test_data, test_label, test_transform)test_loader = DataLoader(test_dataset, batch_size=20, shuffle=False)print("already process data...")

搭建网络

step1.搭建卷积神经网络
step2.定义损失函数与优化器
step2.查询GPU是否可用
step3.将模型置于GPU上等待训练

class Model(nn.Module):def __init__(self):super(Model, self).__init__()self.cnn = nn.Sequential(nn.Conv2d(3, 64, 3, 1, 1),  # 输入3*128*128，输出64*128*128nn.ReLU(),nn.MaxPool2d(2),  # 输出64*64*64nn.Conv2d(64, 128, 3, 1, 1),  # 输出128*64*64nn.ReLU(),nn.MaxPool2d(2),  # 输出128*32*32nn.Conv2d(128, 256, 3, 1, 1),  # 输出256*32*32nn.ReLU(),nn.MaxPool2d(2),  # 输出256*16*16nn.Conv2d(256, 512, 3, 1, 1),  # 输出512*16*16nn.ReLU(),nn.MaxPool2d(2),  # 输出512*8*8nn.Conv2d(512, 512, 3, 1, 1),  # 输出512*8*8nn.ReLU(),nn.MaxPool2d(2),  # 输出512*4*4)self.fc = nn.Sequential(nn.Linear(512 * 4 * 4, 1024),  # 输入8192，输出1024nn.ReLU(),nn.Linear(1024, 512),  # 输入1024，输出512nn.ReLU(),nn.Linear(512, 5)  # 输入512，输出5)
loss = nn.CrossEntropyLoss()  # 定义损失函数
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)  # 定义优化器
print("if GPU can be used?:", torch.cuda.is_available())  # true 查看GPU是否可用
model = Model().cuda()  # 利用GPU加速
print("already prepared model...")

训练网络

step1.设置训练次数
step2.将模型置于训练状态
step3.利用训练集不断更新网络参数
step4.输出每一次训练后网络的准确度

num_epoch = 30print("start training...")for epoch in range(num_epoch):train_loss = 0train_acc = 0model.train()  # 模型置于训练状态for i, data in enumerate(train_loader):  # train_loader = (inputs, label)data[0] = data[0].type(torch.FloatTensor)data[1] = data[1].type(torch.FloatTensor)optimizer.zero_grad()  # 梯度清零pred_label = model(data[0].cuda())  # 实际输出batch_loss = loss(pred_label, data[1].cuda().long())  # 计算误差batch_loss.backward()  # 反向传播optimizer.step()  # 更新参数train_acc += np.sum(np.argmax(pred_label.cpu().data.numpy(), axis=1) == data[1].numpy())  # 计算准确度train_loss += batch_loss.item()  # 计算误差print("epoch:{}" .format(epoch+1))print("model's accuracy in train_data is:{}".format(train_acc/len(train_label)))print("model's loss in train_data is:{}".format(train_loss/len(train_label)))print("finish training...")

测试网络

step1.将网络置于评估模式
step2.计算网络在测试集上的准确度

print("start testing...")model.eval()test_acc = 0with torch.no_grad():for i, data in enumerate(test_loader):data[0] = data[0].type(torch.FloatTensor)data[1] = data[1].type(torch.FloatTensor)pred_label = model(data[0].cuda())  # 实际输出test_acc += np.sum(np.argmax(pred_label.cpu().data.numpy(), axis=1) == data[1].numpy())  # 计算准确度print("model's accuracy in test_data is:{}".format(test_acc / len(test_label)))

保存网络

torch.save(model.state_dict(), "C:/CodeProject/python/cnn/cnn.pt")
print("already save model")

结果展示

epoch:30
model's accuracy in train_data is:0.976594027441485
model's loss in train_data is:0.0043283372970561425
finish training...
start testing...
model's accuracy in test_data is:0.6483333333333333
already save model

总结

以上就是利用卷积神经网络实现图像分类的介绍，完整代码如下：

import os
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import cv2
import numpy as np
from torch.utils.data import DataLoader, Datasetdef read_file(path):  # 读取数据，文件夹中包含五个子文件夹data_list = os.listdir(path)  # 得到5个子文件夹名称data_len = 0  # 存放总图片数目for flower_type in data_list:data_len += len(os.listdir(os.path.join(path, flower_type)))data = np.zeros((data_len, 128, 128, 3))data_label = np.zeros(data_len)i = 0for j, flower_type in enumerate(data_list):  # 读出所有图片flower_list = os.listdir(os.path.join(path, flower_type))for img in flower_list:data[i, :, :, :] = cv2.resize(cv2.imread(os.path.join(path, flower_type, img)), (128, 128))data_label[i] = ji += 1return data, data_labelclass ImgDataset(Dataset):def __init__(self, x=None, y=None, transform=None):self.x = xself.y = yself.transform = transformdef __len__(self):return len(self.x)def __getitem__(self, index):X = self.x[index]if self.transform is not None:X = self.transform(X)if self.y is not None:Y = self.y[index]return X, Yelse:return Xclass Model(nn.Module):def __init__(self):super(Model, self).__init__()self.cnn = nn.Sequential(nn.Conv2d(3, 64, 3, 1, 1),  # 输入3*128*128，输出64*128*128nn.ReLU(),nn.MaxPool2d(2),  # 输出64*64*64nn.Conv2d(64, 128, 3, 1, 1),  # 输出128*64*64nn.ReLU(),nn.MaxPool2d(2),  # 输出128*32*32nn.Conv2d(128, 256, 3, 1, 1),  # 输出256*32*32nn.ReLU(),nn.MaxPool2d(2),  # 输出256*16*16nn.Conv2d(256, 512, 3, 1, 1),  # 输出512*16*16nn.ReLU(),nn.MaxPool2d(2),  # 输出512*8*8nn.Conv2d(512, 512, 3, 1, 1),  # 输出512*8*8nn.ReLU(),nn.MaxPool2d(2),  # 输出512*4*4)self.fc = nn.Sequential(nn.Linear(512 * 4 * 4, 1024),  # 输入8192，输出1024nn.ReLU(),nn.Linear(1024, 512),  # 输入1024，输出512nn.ReLU(),nn.Linear(512, 5)  # 输入512，输出5)def forward(self, x):out = self.cnn(x)out = out.view(out.size()[0], -1)  # batch_size*8192return self.fc(out)if __name__ == '__main__':train_data, train_label = read_file('C:/Users/superjw/Desktop/flowers/train')test_data, test_label = read_file('C:/Users/superjw/Desktop/flowers/test')print("already get data...")train_transform = transforms.Compose([  # 数据处理transforms.ToTensor(),  # 转换为张量transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),  # 归一化处理])test_transform = transforms.Compose([  # 数据处理transforms.ToTensor(),  # 转换为张量transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),  # 归一化处理])train_dataset = ImgDataset(train_data, train_label, train_transform)train_loader = DataLoader(train_dataset, batch_size=20, shuffle=True)test_dataset = ImgDataset(test_data, test_label, test_transform)test_loader = DataLoader(test_dataset, batch_size=20, shuffle=False)print("already process data...")print("if GPU can be used?:", torch.cuda.is_available())  # true 查看GPU是否可用model = Model().cuda()  # 利用GPU加速print("already prepared model...")loss = nn.CrossEntropyLoss()  # 定义损失函数optimizer = torch.optim.Adam(model.parameters(), lr=0.001)  # 定义优化器num_epoch = 30print("start training...")for epoch in range(num_epoch):train_loss = 0train_acc = 0model.train()  # 模型置于训练状态for i, data in enumerate(train_loader):  # train_loader = (inputs, label)data[0] = data[0].type(torch.FloatTensor)data[1] = data[1].type(torch.FloatTensor)optimizer.zero_grad()  # 梯度清零pred_label = model(data[0].cuda())  # 实际输出batch_loss = loss(pred_label, data[1].cuda().long())  # 计算误差batch_loss.backward()  # 反向传播optimizer.step()  # 更新参数train_acc += np.sum(np.argmax(pred_label.cpu().data.numpy(), axis=1) == data[1].numpy())  # 计算准确度train_loss += batch_loss.item()  # 计算误差print("epoch:{}" .format(epoch+1))print("model's accuracy in train_data is:{}".format(train_acc/len(train_label)))print("model's loss in train_data is:{}".format(train_loss/len(train_label)))print("finish training...")print("start testing...")model.eval()test_acc = 0with torch.no_grad():for i, data in enumerate(test_loader):data[0] = data[0].type(torch.FloatTensor)data[1] = data[1].type(torch.FloatTensor)pred_label = model(data[0].cuda())  # 实际输出test_acc += np.sum(np.argmax(pred_label.cpu().data.numpy(), axis=1) == data[1].numpy())  # 计算准确度print("model's accuracy in test_data is:{}".format(test_acc / len(test_label)))torch.save(model.state_dict(), "C:/CodeProject/python/cnn/cnn.pt")print("already save model")

CNN卷积神经网络：花卉分类相关推荐

基于TensorFlow的CNN卷积网络模型花卉分类GUI版（2）
一.项目描述 10类花的图片1100张,按{牡丹,月季,百合,菊花,荷花,紫荆花,梅花,-}标注,其中1000张作为训练样本,100张作为测试样本,设计一个CNN卷积神经网络花卉分类器进行花卉的分类, ...
CNN卷积神经网络(数字分类)
CNN卷积神经网络--手写数字识别 import torch import torch.nn as nn from torch.autograd import Variable import torc ...
基于TensorFlow的CNN卷积网络模型花卉分类（1）
一.项目描述使用TensorFlow进行卷积神经网络实现花卉分类的项目,加载十种花分类,建立模型后进行预测分类图片环境:win10 +TensorFlow gpu 1.12.0+pycharm 训 ...
cnn 预测过程代码_代码实践 | CNN卷积神经网络之文本分类
学习目录阿力阿哩哩:深度学习 | 学习目录zhuanlan.zhihu.com 前面我们介绍了:阿力阿哩哩:一文掌握CNN卷积神经网络zhuanlan.zhihu.com阿力阿哩哩:代码实践|全连 ...
Tensorflow使用CNN卷积神经网络以及RNN(Lstm、Gru)循环神经网络进行中文文本分类
Tensorflow使用CNN卷积神经网络以及RNN(Lstm.Gru)循环神经网络进行中文文本分类本案例采用清华大学NLP组提供的THUCNews新闻文本分类数据集的一个子集进行训练和测试http ...
分类预测 | MATLAB实现CNN卷积神经网络数据分类预测
分类预测 | MATLAB实现CNN卷积神经网络数据分类预测目录分类预测 | MATLAB实现CNN卷积神经网络数据分类预测基本介绍模型设计学习总结参考资料基本介绍使用卷积网络的潜在好 ...
TensorFlow CNN卷积神经网络实现工况图分类识别（一）
1. Tensorflow知识点 1.1. 张量在Tensorflow程序中,所有的数据都是通过张量的形式来表示.从功能的角度上看,张量可以简单的理解为多维数组. (1)占位符Placeholder ...
CV之IC之AlexNet：基于tensorflow框架采用CNN卷积神经网络算法(改进的AlexNet,训练/评估/推理)实现猫狗分类识别案例应用
CV之IC之AlexNet:基于tensorflow框架采用CNN卷积神经网络算法(改进的AlexNet,训练/评估/推理)实现猫狗分类识别案例应用目录基于tensorflow框架采用CNN(改进 ...
Top2：CNN 卷积神经网络实现猫狗图片识别二分类
Top2:CNN 卷积神经网络实现猫狗图片识别二分类系统:Windows10 Professional 环境:python=3.6 tensorflow-gpu=1.14 ```python &qu ...

CNN卷积神经网络：花卉分类

文章目录

简介