Deepstream DGPU version infer instantiation error

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU) GPU
**• DeepStream Version 6.0.1

deepstream-app version 6.0.1
DeepStreamSDK 6.0.1
CUDA Driver Version: 11.4
CUDA Runtime Version: 11.4
TensorRT Version: 8.0
cuDNN Version: 8.9
libNVWarp360 Version: 2.0.1d3

run sudo deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8_gpu1.txt error
error: Config file path: /opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app/config_infer_primary.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
0:00:00.824150517 3862 0x5609bc610950 WARN GST_PADS gstpad.c:1149:gst_pad_set_active:<primary_gie:sink> Failed to activate pad
[NvMultiObjectTracker] De-initialized
** ERROR: main:707: Failed to set pipeline to PAUSED
Quitting
ERROR from primary_gie: Failed to create NvDsInferContext instance
Debug info: gstnvinfer.cpp(841): gst_nvinfer_start (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie:
Config file path: /opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app/config_infer_primary.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED

This error means inference engine was not created successfully.

Have you ever modified config_infer_primary.txt ?

Can you update DeepStream to version 6.2?Some bugs was fixed in lastest version.

I used the config_infer_primary.txt configuration on the official website, and tried to refer to the official website to modify a part, but all reported errors

Can you share your configuration file ?

If I don’t know what you modified,I can’t help you

I have found the problem. The problem is that there is an error in the official website document. I referred to a corresponding driver version of BBS and installed it. I suggest updating the document on the official website. The error document I referenced is 6.0.1

true url

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