I have a memory buffer allocated with cudaMallocManaged; this buffer is used as input to the AI model as a binding. I do the image preprocessing with the OpenCV as follows: I create and OpenCV matrix pointing to that buffer on GPU and preprocess images inplace. Like: cv::Size inputSize = _modelConf…

Hi, Sorry for the late. Please see the sample below: #include <iostream> #include <fstream> #include <sstream> #define CHECK_STATUS(STMT) \ do \ { …

Hi, VPI can wrap the GPU buffer. Which VPI version do you use? 1.2 or 2.x? Thanks.

I use vpi 2. How can I wrap the GPU buffer? As I see it, the code should look like: cudaMallocManaged(&GPU_buffer, buffer_size); VPIIMage img_vpi; VPIImageData img_data; img_data.bufferType = ?; img_data.buffer.? = GPU_buffer; VPIStatus err_vpi = vpiImageCreateWrapper(&img_data, nullptr, VPI_…

Could you please help me with my question?

Hi, Sorry for the late update. Here is an example to wrap CUDA buffer with VPI 2.x for your reference: // Given width, height, d_ptr(GPU buffer pointer) VPIImage img; VPIImageData data = {}; data.bufferType = VPI_IMAGE_BUFFER_CUDA_PITCH_LINEAR; data.buffer.pitch.numPlanes = 1; data.buffer.pitch.…

Thank you very much. I tried your code on Nvidia DevKit with Jetson AGX Xavier as follows: void* buff; int width = 100; int height = 100; cudaMalloc(&buff, width * height * 4 * sizeof(float)); VPIImage img_vpi; VPIImageData img_data = {}; img_data.bufferType = VPI_IMAGE_BUFFER_CUDA_PITCH_LINE…

Hi, We want to check the invalid argument error in our environment. Could you wrap the code into a runnable source and share it with us? Thanks.

include include <opencv2/cudaimgproc.hpp> include <opencv2/imgcodecs.hpp> include <opencv2/cudawarping.hpp> // for cv::cuda::resize include <cuda.h> include <cuda_runtime.h> include <vpi/Image.h> include <vpi/Status.h> include <vpi/ImageFormat.h> int main() { cuInit(0); int img_width_ou…

Thanks. Will get back to you after checking.

Hi, Below line is not correct: img_data.buffer.pitch.planes[0].pixelType = VPI_PIXEL_TYPE_3F32; Only below is supported in VPI Image: https://docs.nvidia.com/vpi/ImageFormat_8h.html For example, please try this instead: img_data.buffer.pitch.format = VPI_IMAGE_FORMAT_F32; Thanks.

I replaced the line ``` img_data.buffer.pitch.planes[0].pixelType = VPI_PIXEL_TYPE_3F32; with ``` img_data.buffer.pitch.format = VPI_IMAGE_FORMAT_F32; but still have the same output VPI_ERROR_INVALID_ARGUMENT

VPI image pointing to managed memory

Robotics & Edge Computing Jetson Systems Jetson AGX Xavier

system Closed December 5, 2023, 2:08am 19

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.

Topic		Replies	Views
VPI Image wraper around NvBufSurface on Jetson AGX Xavier Jetson AGX Xavier vpi	10	1093	December 26, 2023
Get a VPIIMage from NvBufferSurface Jetson AGX Xavier vpi	6	1054	October 2, 2023
VPI CUDA interop with managed memory Jetson AGX Xavier cuda , vpi	16	2024	October 18, 2021
Wrap cv::cuda::GpuMat with VPIImage Jetson AGX Xavier opencv , cuda , vpi	3	1296	October 18, 2021
VPI 3.2 Image Wrapper Performance Problems when using CudaMallocManaged Jetson AGX Orin vpi	6	170	February 17, 2025
Convert VPIImage to cv::cuda::GpuMat Jetson AGX Xavier vpi	5	993	October 18, 2021
Performance issues using vpiImageCreate*Wrapper Jetson Xavier NX vpi	8	2200	February 9, 2023
Convert frame from NvBufSurface (Deepstream 6.4) to VPIImage (VPI3.0) DeepStream SDK vpi	5	477	May 21, 2024
VPI CUDA, opencv GPU Mat Jetson AGX Orin vpi	2	136	November 11, 2024
Deepstream VPI 3.0 Wrapper Compatibility dGPU DeepStream SDK deepstream	3	179	January 14, 2025

VPI image pointing to managed memory

Related topics