Bjoern Haefner

As indicated by @wzw773828204, this issue seems to be resolved in #11. We will address improving our install instructions for python in a future release.

@scse-l, thank you for your interest in CV-CUDA. Indeed for constructing a CVCUDA tensor object, we expect the strides to be constant for each dimension. As pointed out by @tp-nan...

Hi @tigerzjh, Thank you for your interest in CVCUDA. Could you provide more details on the system you're using, eg via the output of the [print_env.sh script](https://github.com/CVCUDA/CV-CUDA/blob/main/print_env.sh)? Since [release 0.6.0-beta](https://github.com/CVCUDA/CV-CUDA/releases/tag/v0.6.0-beta),...

Hi @tms2003, Thank you for your interest in CVCUDA. Could you please share some details on the use case for this ask? Thanks!

Hi @mortal-Zero, Thank you very much for you interest in CVCUDA! We currently track this bug internally and will fix it in a future release. As a workaround for now,...

Hi @dulishu1999, we will close this issue due to inactivity. Please feel free if the problem persists.

Hi @lokvke, Thank you very much for your interest in CVCUDA! Could you share some information on your use-case? Eg. would you like to get a ROI of the same...

Hi @lokvke, then you could you the padandstack operator, which gets as an input an ImageBatchVarSahpe and outputs a Tensor of the cropped size. Below is a minimal working example...

Hi @tigerzjh , We will close this issue for now, due to inactivity - if the problem persists, please feel free to reopen along with some information on your system,...

Hi @ElinLiu0, Thank you for your interest in CVCUDA. It seems that you invoke the `nms` operator with `scores`, which, according to your example, is an `array` and not an...