Hi,
I would like to run a Deepstream pipeline that will do semantic segmentation on two channels images.
The problem is that nvinfer doesnt accept this kind of image format.
How can I build a pipeline to run inference on such image ?
Thanks for your help
Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
jetson agx orin
jetpack 6.0
tensorrt 8.6.2.3
CUDA 12.2
it is a general question on how to run a pipeline with 2 channels images (512 x 512 x 2)
what are the two channels? RG color?
nvinfer only supports RGB/BGR/GRAY inputs, but nvdspreprocess plugin can support regular and custom inputs. please refer to sample deepstream-preprocess-test. this plugin is opensource. you can modify prepare_tensor of \opt\nvidia\deepstream\deepstream\sources\gst-plugins\gst-nvdspreprocess\nvdspreprocess_lib\nvdspreprocess_impl.cpp to customize.
There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks