Deepstream PGIE config error, NvDsInfer Error: NVDSINFER_CONFIG_FAILED

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson AGX Orin
• DeepStream Version 6.2
• JetPack Version (valid for Jetson only) 5.1
• TensorRT Version 8.5.2.2
• 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)

Hi, I got an error while converting the onnx model into an engine file.

The onnx file is a segmentation model with 3 outputs and one of them is the segmentation mask while the others are negligible.

The Pgie config file I use is like the following.

[property]
gpu-id=0
net-scale-factor=1.0
model-color-format=0

model-engine-file=../model/segmentation_model.engine
onnx-file=../model/segmentation_model.onnx
infer-dims=3;1024;1024

uff-input-order=0
uff-input-blob-name=input
## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=0
num-detected-classes=30
interval=0
gie-unique-id=2

network-type=2
output-blob-names=output
segmentation-threshold=0.0
batch-size=1

[class-attrs-all]
roi-top-offset=0
roi-bottom-offset=0
detected-min-w=0
detected-min-h=0
detected-max-w=0
detected-max-h=0

The error I got is

Config file path: config/pgie_config_1.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED

The infer-dims and uff-input-blob-name are right.
But the output-blob-names seem to be the problem.

I put the name of the segmentation mask output among the 3 outputs but the engine build fails.

Is it not possible to use a multiple output segmentation model on deepstream pipeline?

3

Yes, it’s possible. Could you attch more log?

4

Thanks for the reply yuweiw!
Here are more logs.

 <nvdsinfer_context_impl.cpp:1923> [UID = 2]: Trying to create engine from model files
WARNING: [TRT]: onnx2trt_utils.cpp:375: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
ERROR: [TRT]: 4: [graphShapeAnalyzer.cpp::analyzeShapes::1872] Error Code 4: Miscellaneous (IShuffleLayer Unsqueeze_69: reshape changes volume. Reshaping [1,128,128] to [8,1,128,128].)
ERROR: Build engine failed from config file
ERROR: failed to build trt engine.
0:00:07.804872823  2596      0x8748900 ERROR                nvinfer gstnvinfer.cpp:674:gst_nvinfer_logger:<nvinfer_1> NvDsInferContext[UID 2]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1943> [UID = 2]: build engine file failed
0:00:07.978689195  2596      0x8748900 ERROR                nvinfer gstnvinfer.cpp:674:gst_nvinfer_logger:<nvinfer_1> NvDsInferContext[UID 2]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2029> [UID = 2]: build backend context failed
0:00:07.978740107  2596      0x8748900 ERROR                nvinfer gstnvinfer.cpp:674:gst_nvinfer_logger:<nvinfer_1> NvDsInferContext[UID 2]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1266> [UID = 2]: generate backend failed, check config file settings
0:00:07.978861483  2596      0x8748900 WARN                 nvinfer gstnvinfer.cpp:888:gst_nvinfer_start:<nvinfer_1> error: Failed to create NvDsInferContext instance
0:00:07.978890155  2596      0x8748900 WARN                 nvinfer gstnvinfer.cpp:888:gst_nvinfer_start:<nvinfer_1> error: Config file path: config/pgie_config_1.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED

The path is correct since the config file works fine with the Unet model.

5

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

There are some issues with your model reshape. Could you describe how your model was generated? If convenient, you can also attach your ONNX model.

6

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.