Description Hello, I am trying to convert an .onnx model to a fp16 .engine using the below command: trtexec --onnx=-beit-base-patch16-224.onnx --fp16 --saveEngine=model.engine --minShapes=\'pixel_values\':1x3x224x224 --optShapes=\'pixel_values\':8x3x224x224 --maxShapes=\'pixel_values\':8x3x224x224…

Hi, Please see the related post for more information. [image] Subnormal FP16 values detected TensorRT Hi, If accuracy is not affected, you can ignore this warning. Just as the logs, Weights [name=xxx] has some FP32 values that are in the subnormal range of FP16. We are…

Trtexec --layerPrecision and --precisionConstraints not respected when converting onnx model

AI & Data Science Deep Learning (Training & Inference) TensorRT

spolisetty February 1, 2023, 5:37pm 2

Hi,

Please see the related post for more information.

Could you please try on the latest TensorRT version 8.5.3 and let us know if you still face this issue.

Thank you.

Topic		Replies	Views
Meet some problem with --precisionConstraints=obey --layerPrecisions TensorRT	1	1489	January 17, 2023
255 weights are affected by this issue: Detected subnormal FP16 values TensorRT	1	1376	January 17, 2023
Convert the TRT model with FP16 Jetson TX2 jetpack , tensorrt , jetson-inference	7	2663	October 18, 2021
Tensorrt FP16 conversion issue TensorRT tensorrt , cuda , gstreamer , onnx , deep-learning , deepstream	8	2758	March 6, 2023
TRTExec - Force precision on certain ONNX Op Nodes TensorRT	1	1192	February 23, 2023
Error on converting ONNX to FP16 TensorRT with my model Deep Learning (Training & Inference)	0	436	August 17, 2020
Warning While DS App Converts ONNX Model To Engine DeepStream SDK tensorrt	5	971	July 11, 2022
Can convert to INT32 but not with FP16 TensorRT	3	1106	November 29, 2022
TensorRT encountered issues when converting weights between types and that could affect accuracy TensorRT	7	1981	September 22, 2023
Error during conversion of ONNX panoptic model to TensorRT fp16 TensorRT cudnn	3	347	June 5, 2024

Trtexec --layerPrecision and --precisionConstraints not respected when converting onnx model

Related topics