C++利用opencv调用pytorch训练好的分类模型

pytorch保存模型


import torch.onnxd = torch.rand(1, 3, 224, 224,dtype=torch.float,device = 'cuda')
m = model_ft
o = model_ft(d)onnx_path = "onnx_model_name.onnx"
torch.onnx.export(m, d, onnx_path)

C++调用

#include "opencv2/dnn/dnn.hpp"using namespace cv;
using namespace cv::dnn;
using namespace std;void Classification_good()
{// 装载模型，设置参数clock_t  st = clock();string model = "C:\\Users\\Ring\\Desktop\\A_jupyter\\pytorch\\test\\onnx_model_name.onnx";ClassificationModel dnn_model(model);dnn_model.setPreferableBackend(DNN_BACKEND_CUDA);dnn_model.setPreferableTarget(DNN_TARGET_CUDA);float scale = 1.0 / 255;int inpWidth = 224, inpHeight = 224;Scalar mean(0, 0, 0);dnn_model.setInputParams(scale, Size(inpWidth, inpHeight), mean, true, false);clock_t  end = clock();cout << end - st << endl;// 图像文件夹遍历检测String folder = "C:\\Users\\Ring\\Desktop\\A_jupyter\\pytorch\\test\\Neu\\val\\Rs/";vector<String> imagePathList;glob(folder, imagePathList);cout << "test In C++!" << endl;for (int i = 0; i < imagePathList.size(); i++){Mat img = imread(imagePathList[i]);resize(img, img, Size(224, 224), 0, 0, INTER_LANCZOS4);Mat img_t = Mat::zeros(img.size(), CV_32FC1);for (int ii = 0; ii < img.cols; ii++){for (int jj = 0; jj < img.rows; jj++){img_t.at<float>(ii, jj) = img.at<uchar>(ii, jj);}}int classIds;float confs;double time1 = static_cast<double>(getTickCount());dnn_model.classify(img, classIds, confs);  // 前向推理，classIds是类别索引,classIds=0是划痕，classIds=1是颗粒double time2 = (static_cast<double>(getTickCount()) - time1) / getTickFrequency();cout << classIds << endl;cout << "time: " << time2 << endl;}
}

训练模型

import numpy as np
import torchvision
from torchvision import datasets, transforms, models
import torchimport matplotlib.pyplot as plt
import time
import os
import copy
print("Torchvision Version: ",torchvision.__version__)
print('pytorch Version: ',torch.__version__)data_dir = "./Neu"
batch_size = 32
input_size = 224all_imgs = datasets.ImageFolder(os.path.join(data_dir, "train"),transforms.Compose([transforms.RandomResizedCrop(input_size), #把每张图片变成resnet需要输入的维度224transforms.RandomHorizontalFlip(),transforms.ToTensor(),]))
loader = torch.utils.data.DataLoader(all_imgs, batch_size=batch_size, shuffle=True, num_workers=4)img = next(iter(loader))[0]img[0][1].dtype#plt展示torch的图片
unloader = transforms.ToPILImage()
plt.imshow(unloader(img[1].squeeze(0)))data_transforms = {"train": transforms.Compose([transforms.RandomResizedCrop(input_size),transforms.RandomHorizontalFlip(),transforms.ToTensor(),#transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),"val": transforms.Compose([transforms.Resize(input_size),transforms.CenterCrop(input_size),transforms.ToTensor(),#transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
}# Create training and validation datasets
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'val']}
# Create training and validation dataloaders
dataloaders_dict = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size, shuffle=True, num_workers=4) for x in ['train', 'val']}
#把迭代器存放到字典里作为value，key是train和val，后面调用key即可。# Detect if we have a GPU available
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")inputs, labels=next(iter(dataloaders_dict["train"])) #一个batch
print(inputs.shape)
print(labels)for inputs, labels in dataloaders_dict["train"]:print(labels.size()) #最后一个batch不足32model_name = "resnet"
num_classes = 6
num_epochs = 10
feature_extract = True  #只更新修改的层def set_parameter_requires_grad(model, feature_extracting):if feature_extracting:for param in model.parameters():param.requires_grad = False #提取的参数梯度不更新#初始化model
def initialize_model(model_name, num_classes, feature_extract, use_pretrained=True):if model_name == "resnet":model_ft = models.resnet50(pretrained=use_pretrained) #如果True，从imagenet上返回预训练的模型和参数set_parameter_requires_grad(model_ft, feature_extract)#提取的参数梯度不更新num_ftrs = model_ft.fc.in_features #model_ft.fc是resnet的最后全连接层#(fc): Linear(in_features=512, out_features=1000, bias=True)#in_features 是全连接层的输入特征维度#print(num_ftrs)model_ft.fc = nn.Linear(num_ftrs, num_classes)#out_features=1000 改为 num_classes=2input_size = 224 #resnet18网络输入图片维度是224，resnet34，50，101，152也是return model_ft, input_size
model_ft, input_size = initialize_model(model_name, num_classes, feature_extract, use_pretrained=True)
print(model_ft)next(iter(model_ft.named_parameters()))len(next(iter(model_ft.named_parameters())))for name,param in model_ft.named_parameters():print(name) #看下都有哪些参数model_ft = model_ft.to(device)
params_to_update = model_ft.parameters() #需要更新的参数
print("Params to learn:")
if feature_extract:params_to_update = [] #需要更新的参数存放在此for name,param in model_ft.named_parameters(): #model_ft.named_parameters()有啥看上面cellif param.requires_grad == True:
#这里要知道全连接层之前的层param.requires_grad == Flase
#后面加的全连接层param.requires_grad == Trueparams_to_update.append(param)print("\t",name)
else: #否则，所有的参数都会更新for name,param in model_ft.named_parameters():if param.requires_grad == True:print("\t",name)# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(params_to_update, lr=0.001, momentum=0.9) #定义优化器
# Setup the loss fxn
criterion = nn.CrossEntropyLoss() #定义损失函数#训练测试合一起了
def train_model(model, dataloaders, criterion, optimizer, num_epochs=5):since = time.time()val_acc_history = [] best_model_wts = copy.deepcopy(model.state_dict())#深拷贝上面resnet模型参数
#.copy和.deepcopy区别看这个：https://blog.csdn.net/u011630575/article/details/78604226 best_acc = 0.for epoch in range(num_epochs):print("Epoch {}/{}".format(epoch, num_epochs-1))print("-"*10)for phase in ["train", "val"]:running_loss = 0.running_corrects = 0.if phase == "train":model.train()else: model.eval()for inputs, labels in dataloaders[phase]:inputs = inputs.to(device)labels = labels.to(device)with torch.autograd.set_grad_enabled(phase=="train"):#torch.autograd.set_grad_enabled梯度管理器，可设置为打开或关闭#phase=="train"是True和False，双等号要注意outputs = model(inputs)loss = criterion(outputs, labels)_, preds = torch.max(outputs, 1)#返回每一行最大的数和索引，prds的位置是索引的位置#也可以preds = outputs.argmax(dim=1)if phase == "train":optimizer.zero_grad()loss.backward()optimizer.step()running_loss += loss.item() * inputs.size(0) #交叉熵损失函数是平均过的running_corrects += torch.sum(preds.view(-1) == labels.view(-1)).item()#.view(-1)展开到一维，并自己计算epoch_loss = running_loss / len(dataloaders[phase].dataset)epoch_acc = running_corrects / len(dataloaders[phase].dataset)print("{} Loss: {} Acc: {}".format(phase, epoch_loss, epoch_acc))if phase == "val" and epoch_acc > best_acc:best_acc = epoch_accbest_model_wts = copy.deepcopy(model.state_dict())#模型变好，就拷贝更新后的模型参数if phase == "val":val_acc_history.append(epoch_acc) #记录每个epoch验证集的准确率print()time_elapsed = time.time() - sinceprint("Training compete in {}m {}s".format(time_elapsed // 60, time_elapsed % 60))print("Best val Acc: {}".format(best_acc))model.load_state_dict(best_model_wts) #把最新的参数复制到model中return model, val_acc_history# Train and evaluate
model_ft, ohist = train_model(model_ft, dataloaders_dict, criterion, optimizer_ft, num_epochs=num_epochs)# Initialize the non-pretrained version of the model used for this run    初始化用于此运行的模型的未预训练版本
scratch_model,_ = initialize_model(model_name, num_classes, feature_extract=False, #所有参数都训练use_pretrained=False)# 不要imagenet的参数
scratch_model = scratch_model.to(device)
scratch_optimizer = optim.SGD(scratch_model.parameters(), lr=0.001, momentum=0.9)
scratch_criterion = nn.CrossEntropyLoss()
_,scratch_hist = train_model(scratch_model, dataloaders_dict, scratch_criterion, scratch_optimizer, num_epochs=num_epochs)#保存模型——这个在opencv中可以被正确的读取和预测import torch.onnximport netrond = torch.rand(1, 3, 224, 224,dtype=torch.float,device = 'cuda')
m = model_ft
o = model_ft(d)onnx_path = "onnx_model_name.onnx"
torch.onnx.export(m, d, onnx_path)netron.start(onnx_path)

C++利用opencv调用pytorch训练好的分类模型相关推荐

搭建C++开发图像算法的环境——利用C++调用Pytorch训练后模型
本文主要介绍如何搭建C++开发图像算法的环境,使用到CMake + libtorch + OpenCV + ITK等.旨在构建一个可融合深度学习框架,可开发图像处理算法且易于跨平台编译的环境. 准备条 ...
opencv调用pytorch训练好的模型
根据官方文档知 cv2.dnn.readNetFromTorch() 中使用 torch.save() 方法保存的文件. 加载文件必须包含带有导入网络的序列化 nn.Module 对象,尝试从序列化数 ...
python caffe 训练自己的模型_python接口调用已训练好的caffe模型测试分类方法
训练好了model后,可以通过python调用caffe的模型,然后进行模型测试的输出. 本次测试主要依靠的模型是在caffe模型里面自带训练好的结构参数:~/caffe/models/bvlc_re ...
Pytorch实现一个简单分类模型
Pytorch实现一个简单分类模型在本小节主要带领大家学习分类任务的代码编写,另外,本人参考的学习资料为[莫烦Python],有兴趣观看视频的同学可以观看视频资料https://www.youtub ...
【图像分类】如何使用 mmclassification 训练自己的分类模型
文章目录一.数据准备二.模型修改三.模型训练四.模型效果可视化五.如何分别计算每个类别的精确率和召回率 MMclassification 是一个分类工具库,这篇文章是简单记录一下如何用该工具 ...
利用C++调用PyTorch的模型
背景 PyTorch的主要接口是Python语言.虽然Python是许多需要动态和易于迭代的场景的首选语言,但同样有很多情况下,Python的这些属性恰好是不利的.在生产环境中,需要保证低延迟和其它严 ...
计算机视觉——利用openCV调用本地摄像头采集图片并截图保存
提示:文章写完后,目录可以自动生成,如何生成可参考右边的帮助文档文章目录前言一.采集方式二.代码部分三.效果演示前言由于本人研究生课题是深度学习目标检测方向.因此需要大量的数据集.在本地 ...
opencv调用自己训练的yolo3模型
一实现流程 1.准备好自己的数据集,通过yolo3结构框架训练好自己的模型文件(loss值一般训练到10就OK)yolov3源码:https://github.com/qqwweee/keras-y ...
Windows下Caffe的学习与应用（三）——使用OpenCV3调用自己训练好的Caffe模型进行图像分类
前言前面的博文中,我试了如何使用caffe训练得到想要的模型与其如何使用别人成熟的模型微调优化自己训练的模型,那么得到训练好的模型之后如何在自己的项目中呢,我这里使用opencv的DNN模块调用ca ...

C++利用opencv调用pytorch训练好的分类模型

C++利用opencv调用pytorch训练好的分类模型相关推荐

最新文章

热门文章