Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU): GeForce RTX 3090
• DeepStream Version: 6.1
• TensorRT Version: 8.2
• NVIDIA GPU Driver Version (valid for GPU only): 510
• Issue Type( questions, new requirements, bugs): question
The cameras I’m using output Bayer RG 8 / Bayer RG 12 / Bayer RG 12 p / YCbCr 422 / RGB 8 / BGR 8 format so I must use the videoconvert
plugin before the nvvideoconvert
plugin. The videoconvert
plugin runs on CPU so it’s really slow and it’s a bottleneck in my pipeline and I’m looking for way to get rid of it. The nvvideoconvert
plugin currently support these format: NV12, I420, P010_10LE, BGRx, RGBA (NVMM/RAW). Is there any plan to support more input format in the future?