Maaike's profile - activity

I am trying to copy GpuMat data to the Triton Inference Server shared memory. However, a GpuMat is not continuous, but the Inference Server expects continuous data. Downloading the gpuMat to a cv::Mat and then do a cudaMemcpy of the cv::Mat into the shared memory of the Inference server works, but I want to copy it to the gpu shared memory of the inference server without downloading it. But I'm struggling to find out how I should do that.

My input GpuMat is a 600x600 color image (3 layers) converted to float.

What is the data structure of the GpuMat and / or how to make it continuous or copy it so it becomes continuous?

I tried with cudaMemcpy2D, I tried just a cudaMemcpy but row by row, I tried to create a continuous gpumat with cv::cuda::createContinuous and then copyTo from the input to the continuous array.

It turns out that it works perfectly with cudaMemcpy2D, as long as you don't make the image contiguous where you expect

Thanks. Yes, well, I searched for continuous but if I search for contiguous I do not get other results. But indeed, tha

Make GpuMat continuous / copy to continuous memory. I am trying to copy GpuMat data to the Triton Inference Server share