v0.2.1-alpha

General

• Added [DLPack](https://dmlc.github.io/dlpack/latest/) interop support to Python

• Added CV-CUDA build package for various Python versions

• Updated documentation to include [NVIDIA VPF](https://github.com/NVIDIA/VideoProcessingFramework) update

• Downgraded C++ version required from [20](https://en.cppreference.com/w/cpp/compiler_support/20) to [17](https://en.cppreference.com/w/cpp/compiler_support/17)

• Made public headers compatible with [C++11](https://en.cppreference.com/w/cpp/compiler_support/11)

• Changed default CUDA stream in Python to be 0

• Removed library build dependency on [OpenSSL](https://www.openssl.org/)

• Relaxed nvcv::Tensor bit restrictions on strides

• Updated Segmentation sample app with [NVIDIA VPF](https://github.com/NVIDIA/VideoProcessingFramework) and Joint Bilateral Filter

New Operators

• Joint Bilateral Filter

Improved Testing

• Full operator test coverage for interleaved (HWC) and planar (CHW) tensors

• Removed Numba dependency on tests

Bug Fixes

• [BUG #25 Addressed](https://github.com/CVCUDA/CV-CUDA/issues/25) TypeError: as_tensor(): incompatible function arguments. The following argument types are supported

• [BUG #26 Addressed](https://github.com/CVCUDA/CV-CUDA/issues/26) libdl-2.17_stub.so: file format not recognized; treating as linker script

• [BUG #28 Addressed](https://github.com/CVCUDA/CV-CUDA/issues/28) cannot find -lcvcuda

• Fixed memory leak from exception thrown by constructor

• Fixed CMake code generation for header compatibility tests

• Fixed reformated from CHW to NHWC error

• Fixed NVCV_ASSERT_STATUS macro failing to compile prompt added when testing for exception

• Tensor shapes must be exported as tuples, not lists, in Python

• cudaIllegalMemoryAddress prompt added in Python tests when GPU is under load

• cudaMallocs prompt added in pipelines driven by Python incur performance penalty