I converted the centerface onnx file to trt using trtexec, through tensorrt module and through nvinfer runtime conversion in deepstream but the converted model is giving wrong detection bboxes and landmarks point whereas the inference through onnx is correct. Onnx file link : CenterFace/centerface.…

Hi, could please provide the setup info as other topics? do you mean providing trt engine to nvinfer gets wrong output, but providing onnx to nvinfer can get correct output?

Providing onnx to nvinferserver gives correct output. If i give onnx file in nvinfer , it implicitly builds a trt engine for that and infer on it which gives wrong output.

@agarwalindraksha On this I have a question, have you tried explicit conversion to TRT before giving it to Nvinfer -OR- you let it to nvinfer to convert on the fly from ONNX and generate TRT?

Yes , i also tried using engine file build through trtexec and InsightFace-REST/build_centerface_trt.py at master · SthPhoenix/InsightFace-REST · GitHub but the output was same for all cases

I think this indicates the model is correct, did you check if the model output parser of nvinfer is correct ?

I am using the same customparser in nvinferserver and its working fine. Moreover, In nvinferserver also its giving different output for onnx and trt file, so i guess issue is not with ouptut parser. I am attaching the sample output for onnx and trt file for your reference. First one is TRT output…

[image] agarwalindraksha: Yes , i also tried using engine file build through trtexec and InsightFace-REST/build_centerface_trt.py at master · SthPhoenix/InsightFace-REST · GitHub but the output was same for all cases Hi @agarwalindraksha , Di you solve the issue? I am facing the exact same …

I checked with these steps on DS-5.0 container its still giving wrong output there but working fine with DS-5.1 so i guess this is the version issue. Anyway this issue has been resolved. Thanks

Centerface TRT giving wrong output

Accelerated Computing Intelligent Video Analytics DeepStream SDK

mchi April 11, 2021, 11:04am 11

for centerface TRT, please check if you can refer to No Detection for Centerface Model Inference with Deepstream(for Centerface) - #3 by mchi

Topic		Replies	Views
TensorFlow EfficientDet-D0 -> ONNX -> TensorRT converted model fails to run in Deepstream DeepStream SDK deepstream61	8	1129	August 11, 2022
Output from ONNX inference and trt inference are different Jetson TX2 tensorrt , tensorflow , nvbugs	6	964	October 18, 2021
Incorrect inference results after converting from ONNX to TRT with trtexec TensorRT tensorrt , python , onnx	4	1725	December 9, 2022
TensorRT model giving constant output TensorRT deepstream	4	1484	November 30, 2021
Nvinferserver with TensorRT OSS version DeepStream SDK	6	661	August 23, 2021
Issues while converting ONNX to TRT Jetson Nano tensorrt , onnx	9	1445	October 18, 2021
Ouput of infer with trt not maching vs onnx and pytorch model (SlowFast use Retnet 3D Conv) TensorRT tensorrt , inference-server-triton	13	1378	February 16, 2022
Can't load InsightFace Onnx model on TX2 by using TensorRT 4.1.3 TensorRT	0	659	September 11, 2019
Tensorrt8.5 inference different with origin onnx model TensorRT	6	1183	December 13, 2022
Wrong results when I convert Movenet models from ONNX to TensorRT TensorRT tensorrt , onnx	5	1350	September 28, 2023

Centerface TRT giving wrong output

Related topics