# C++/pytorch How to convert tensor to image array?

**URL:** <https://discuss.pytorch.org/t/c-pytorch-how-to-convert-tensor-to-image-array/43896>\
**Category:** C++\
**Created:** [April 29, 2019, 7:52am UTC](https://discuss.pytorch.org/t/c-pytorch-how-to-convert-tensor-to-image-array/43896 "2019-04-29T07:52:58Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![JingLiRaysightmed](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/j/ea666f/32.png) [@JingLiRaysightmed](https://discuss.pytorch.org/u/JingLiRaysightmed)\
**Post date:** [April 29, 2019, 7:52am UTC](https://discuss.pytorch.org/t/c-pytorch-how-to-convert-tensor-to-image-array/43896/1 "2019-04-29T07:52:58Z")

</div>

I would like to convert a tensor to image array and use tensor.data() method. But it doesn’t work.

My function is showed below:

```auto
#include <torch/script.h> // One-stop header.

#include <iostream>
#include <memory>
#include <sstream>
#include <string>
#include <vector>

#include "itkImage.h"
#include "itkImageFileReader.h"
#include "itkImageFileWriter.h"
#include "itkImageRegionIterator.h"

//////////////////////////////////////////////////////
//Goal: load jit script model and segment myocardium
//Step: 1. load jit script model
// 2. load input image
// 3. predict by model
// 4. save the result to file
//////////////////////////////////////////////////////
typedef short PixelType;
const unsigned int Dimension = 3;
typedef itk::Image<PixelType, Dimension> ImageType;
typedef itk::ImageFileReader<ImageType> ReaderType;
typedef itk::ImageRegionIterator<ImageType> IteratorType;

bool itk2tensor(ImageType::Pointer itk_img, torch::Tensor &tensor_img) {
	
	typename ImageType::RegionType region = itk_img->GetLargestPossibleRegion();
	const typename ImageType::SizeType size = region.GetSize();
	std::cout << "Input size: " << size[0] << ", " << size[1]<< ", " << size[2] << std::endl;

	int len = size[0] * size[1] * size[2];
	short rowdata[len];
	int count = 0;
	IteratorType iter(itk_img, itk_img->GetRequestedRegion());
	
	// convert itk to array
	for (iter.GoToBegin(); !iter.IsAtEnd(); ++iter) {
		rowdata[count] = iter.Get();
		count++;
	}
	std::cout << "Convert itk to array DONE!" << std::endl;

	// convert array to tensor
	tensor_img = torch::from_blob(rowdata, {1, 1, (int)size[0], (int)size[1], (int)size[2]}, torch::kShort).clone();
	tensor_img = tensor_img.toType(torch::kFloat);
	tensor_img = tensor_img.to(torch::kCUDA);
	tensor_img.set_requires_grad(0);

	return true;
}

bool tensor2itk(torch::Tensor &t, ImageType::Pointer itk_img) {

	std::cout << "tensor dtype = " << t.dtype() << std::endl;
	std::cout << "tensor size = " << t.sizes() << std::endl;
	t = t.toType(torch::kShort);
	short * array = t.data<short>();

	ImageType::IndexType start;
	start[0] = 0; // first index on X
	start[1] = 0; // first index on Y
	start[2] = 0; // first index on Z

	ImageType::SizeType size;
	size[0] = t.size(2);
	size[1] = t.size(3);
	size[2] = t.size(4);

	ImageType::RegionType region;
	region.SetSize( size );
	region.SetIndex( start );

	itk_img->SetRegions( region );
	itk_img->Allocate();

	int len = size[0] * size[1] * size[2];

	IteratorType iter(itk_img, itk_img->GetRequestedRegion());
	int count = 0;
	// convert array to itk
	std::cout << "start!" << std::endl;
	for (iter.GoToBegin(); !iter.IsAtEnd(); ++iter) {
		short temp = *array++; // ERROR!
		std::cout << temp << " ";
		iter.Set(temp);
		count++;
	}
	std::cout << "end!" << std::endl;

	return true;
}

int main(int argc, const char* argv[]) {
	int a, b, c;
	if (argc != 4) {
		std::cerr << "usage: automyo input jitmodel output\n";
		return -1;
	}

	std::cout << "========= jit start =========\n";
	// 1. load jit script model
	std::cout << "Load script module: " << argv[2] << std::endl;
	std::shared_ptr<torch::jit::script::Module> module = torch::jit::load(argv[2]);
	module->to(at::kCUDA);

	// assert(module != nullptr);
	std::cout << "Load script module DONE" << std::endl;

	// 2. load input image
	const char* img_path = argv[1];
	std::cout << "Load image: " << img_path << std::endl;

	ReaderType::Pointer reader = ReaderType::New();

	if (!img_path) {
		std::cout << "Load input file error!" << std::endl;
		return false;
	}

	reader->SetFileName(img_path);
	reader->Update();

	std::cout << "Load image DONE!" << std::endl;

	ImageType::Pointer itk_img = reader->GetOutput();

	torch::Tensor tensor_img;
	if (!itk2tensor(itk_img, tensor_img)) {
		std::cerr << "itk2tensor ERROR!" << std::endl;
	}
	else {
		std::cout << "Convert array to tensor DONE!" << std::endl;
	}

	std::vector<torch::jit::IValue> inputs;
	inputs.push_back(tensor_img);

	// 3. predict by model
	torch::Tensor y = module->forward(inputs).toTensor();
	std::cout << "Inference DONE!" << std::endl;

	// 4. save the result to file
	torch::Tensor seg = y.gt(0.5);
	// std::cout << seg << std::endl;

	ImageType::Pointer out_itk_img = ImageType::New();
	if (!tensor2itk(seg, out_itk_img)) {
		std::cerr << "tensor2itk ERROR!" << std::endl;
	}
	else {
		std::cout << "Convert tensor to itk DONE!" << std::endl;
	}

	std::cout << out_itk_img << std::endl;

	return true;
}

```

The runtime log is showed below:

> Load script module: model\_myo\_jit.pt  
> Load script module DONE  
> Load image: patch\_6.nii.gz  
> Load image DONE!  
> Input size: 128, 128, 128  
> Convert itk to array DONE!  
> Convert array to tensor DONE!  
> Inference DONE!  
> tensor dtype = unsigned char  
> tensor size = [1, 1, 96, 96, 96]  
> start!  
> Segmentation fault (core dumped)

Why and how to convert?

---

<div class="post-metadata">

**Author:** ![JingLiRaysightmed](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/j/ea666f/32.png) [@JingLiRaysightmed](https://discuss.pytorch.org/u/JingLiRaysightmed)\
**Post date:** [April 29, 2019, 9:58am UTC](https://discuss.pytorch.org/t/c-pytorch-how-to-convert-tensor-to-image-array/43896/2 "2019-04-29T09:58:12Z")

</div>

I have found the solution. When I convert the y to kCPU, it works. Because it in CUDA before.