How to Transfer Data Efficiently？

CVCUDA / CV-CUDA

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

https://cvcuda.github.io

Other

2.32k stars 212 forks source link

How to Transfer Data Efficiently？ #163

Open mizhitian-xiaomi opened 3 months ago

mizhitian-xiaomi commented 3 months ago

//: # ""

The data types of input image and the model inferencing input data are numpy.ndarray.
I have to perform many data type conversions when using cvcuda, which is very inefficient.
How can I solve this problem?

bhaefnerNV commented 1 month ago

Hi @mizhitian-xiaomi, Thanks for you interest in CV-CUDA! Could you provide more information to your use-case?

Is the workflow to go from a torch tensor -> cvcuda tensor -> numpy array, and while having the cvcuda tensor, do data type conversions? Then repeat this process for multiple tensors?