GMAT

GMAT copied to clipboard

TensorRT image No such filter: 'scale_npp' and more

2

Hi, I followed your guide but it seems it is incomplete. No scale_npp, also no nvdec/nvenc decoders/encoders ``` ./configure --disable-ptx-compression --enable-cvcuda --enable-libtensorrt --extra-cflags=-I/opt/nvidia/cvcuda0/include/ --disable-static --enable-shared --enable-nonfree --enable-cuda-nvcc --extra-cflags=-I/usr/local/cuda/include --extra-ldflags=-L/usr/local/cuda/lib64 --nvccflags='-gencode...

efschu

https://docs.nvidia.com/video-technologies/video-codec-sdk/12.0/ffmpeg-with-nvidia-gpu/index.html#hwaccel-transcode-with-scaling According to https://github.com/NVIDIA/GMAT/blob/main/ffmpeg-gpu/libswscale/cuda/swscale_cuda.c#L34, supported_fmts do not include AV_PIX_FMT_CUDA， which my ffmpeg hw_decoder px_fmt is AV_PIX_FMT_CUDA, how to scale and transform px_fmt to RGB, then to host memory? As far...

bug-developer021

About decinfer open source

zhoukk

tensorrt version: 8.2.3 nvidia driver version:535.161.08 cuda version:11.6 git branch:ffmpeg-gpu-demo the following command works good： ffmpeg -loglevel info -hwaccel cuda -hwaccel_output_format cuda -c:v h264_cuvid -i output_264_2.flv -vf "[0:v]format_cuda=rgbpf32le[fc1];[fc1]format_cuda=nv12[fc2]" -c:v h264_nvenc...

jzl123456