Inference pytorch C++ with alexnet and cv::imread image

本文关键字：cv imread image and alexnet pytorch C++ with Inference 更新时间：2023-10-16

我正在尝试使用C++应用程序推断使用alexnet预训练网络的图像分类任务。
我已经成功地推断出一个用python加载网络的狗图像：

alexnet = torchvision.models.alexnet(pretrained=True)
img = Image.open("dog.jpg")
transform = transforms.Compose([
transforms.Resize(256),                
transforms.CenterCrop(224),        
transforms.ToTensor(),                  
transforms.Normalize(                   
mean=[0.485, 0.456, 0.406],         
std=[0.229, 0.224, 0.225]              
)])
img_t = transform(img)
batch_t = torch.unsqueeze(img_t, 0)
alexnet.forward(batch_t)
_, index = torch.max(out, 1)

结果index是 208，Labrador_retriever，看起来不错。
然后我保存要从C++应用程序加载的网络

example = torch.rand(1, 3, 224, 224)
traced_script_module_alex = torch.jit.trace(alexnet, example)
traced_script_module.save("alexnet.pt")

当我加载到C++时，我得到错误的结果：

cv::Mat img = cv::imread("dog.jpg");
cv::resize(img, img, cv::Size(224, 224), cv::INTER_CUBIC);
// Convert the image and label to a tensor.
torch::Tensor img_tensor = torch::from_blob(img.data, { 1, img.rows, img.cols, 3 }, torch::kByte);
img_tensor = img_tensor.permute({ 0, 3, 1, 2 }); // convert to CxHxW
img_tensor = img_tensor.to(torch::kFloat);
std::vector<torch::jit::IValue> input;
input.push_back(img_tensor);
torch::jit::script::Module  module = torch::jit::load("alexnet.pt");
at::Tensor output = module.forward(input).toTensor();
std::cout << output.argmax(1) << 'n';

argmax是463，桶。我想我不是在看同一个图像;我错过了什么...？

你的C++代码缺少这部分Python代码：

transform = transforms.Compose([
transforms.Resize(256),                
transforms.CenterCrop(224),        
transforms.ToTensor(),                  
transforms.Normalize(                   
mean=[0.485, 0.456, 0.406],         
std=[0.229, 0.224, 0.225]              
)])
img_t = transform(img)