CV-CUDA
CV-CUDA copied to clipboard
CVCUDA
CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.
I'm running on WSL2 ubuntu 20.04 with RTX 4080 and should meet all prerequisites from README. Here is the log: $ ci/build.sh -- Found CUDAToolkit: /usr/local/cuda/include (found suitable version "12.0.76",...
I want to use it on nvidia's xavier nx, but it seems that it is only support the x86 platform. The GPU of the jetson series is much stronger than...
I was pleasantly surprised to see such a good project. I know that nvidia also has another gpu image processing library: NVIDIA 2D Image And Signal Performance Primitives (NPP) Is...
I have build tar.gz deb success. But how can I build python wheels
**What is your question?** 根据sample/classification/python/inference.py将其改为cv2进行预处理，inference.py使用torchnvjpeg+cvcuda进行预处理，对标改为cv2处理，打印resize为224*224的输出值，发现两者预处理输出并不一致，最后预测结果top1都是一致，但是数值差别很大。结果如下： inference.py输出结果: resize224输出的tensor tensor([[[[ 84, 81, 76], [ 84, 81, 76], [ 84, 81, 76], ..., [ 65, 78, 38], [ 69, 82, 42], [ 73,...
**Describe the bug** When I try to use cvcuda with torch dataloader, I get an exception: `TypeError: cannot pickle 'nvcv.Tensor' object` Is there any solution to use cvcuda with torch...
I have installed "nvcv_python-0.2.0_alpha-cp38-cp38-linux_x86_64.whl" in environment (python3.8.3 / cuda11.0 / ubuntu18.04). and then I code "import nvcv", but this message "no module named 'nvcv'" posts
环境：  torch cu11.7 ubuntu20.04 显卡1080ti 代码 import os os.environ["CUDA_VISIBLE_DEVICES"] = "0" import torch import cvcuda,nvcv import torchnvjpeg print("torch.cuda.is_available():",torch.cuda.is_available()) image_path = "./CV-CUDA-0.2.0-alpha/data/images/1.jpg" decoder = torchnvjpeg.Decoder() image_data = open(image_path, 'rb').read() image_tensor...
How to add NVCV_WARP_INVERSE_MAP flag into warp_affine_into func? as [api doc](https://cvcuda.github.io/_exhale_api/group__NVCV__C__ALGORITHM__WARP__AFFINE.html) shows
