Environment
• Hardware Platform (Jetson / GPU) Jetson AGX orin
• DeepStream Version 7
• JetPack Version (valid for Jetson only) 6.0
• TensorRT Version 8.6
**• Cuda 12.2
Relevant Files
Content of my config file:
[property]
gpu-id=0
model-color-format=2
network-mode=0
model-engine-file=mymodel.engine
batch-size=1
process-mode=1
Description
Hello!
I m new to deepstream, and I want to create a pipeline for a inference on 512x512 float32 image
My network 's input is 512x512x1
I set my config file, put I have this error:
INFO: [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT args_0 512x512x1
1 OUTPUT kFLOAT conv2d_45 512x512x1
0:00:06.104745400 1182606 0xaaaaec81db50 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2198> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-7.0/sources/deepstream_python_apps/apps/deepstream-servorobot-app/mymodel.engine
0:00:06.104815510 1182606 0xaaaaec81db50 ERROR nvinfer gstnvinfer.cpp:676:gst_nvinfer_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::preparePreprocess() <nvdsinfer_context_impl.cpp:1044> [UID = 1]: GRAY input format specified but network input channels is not 1.
ERROR: Infer Context prepare preprocessing resource failed., nvinfer error:NVDSINFER_CONFIG_FAILED
Can you help me?
Thanks!