Please provide complete information as applicable to your setup. • Hardware Platform (Jetson / GPU): GeForce 4090 • DeepStream Version: 6.2 • TensorRT Version: 8.5 • NVIDIA GPU Driver Version (valid for GPU only): 525 • Issue Type( questions, new requirements, bugs): questions I noticed that t…

Is layer-device-precision property used at inference time or during engine building?

Morganh May 26, 2023, 6:28am 8

Topic		Replies	Views
How to replicate the affect of Deepstream's layer-device-precision property in tao-converter? TAO Toolkit	6	327	May 27, 2023
[Feature Request] Retrieve the actual precision chosen for each layer after engine is built via IPro... TensorRT	1	385	August 28, 2019
Incompatible TensorRT engine(int8) with deepstream DeepStream SDK	6	52	December 25, 2024
Running int8 engine in DeepStream DeepStream SDK	2	502	October 12, 2021
How to run deepstream-app without building engine? DeepStream SDK	6	532	March 11, 2024
Profile inference time of each layer for .engine model to know where is bottleneck in Deepstream? DeepStream SDK	17	919	June 19, 2023
How to run nvinfer with mixed precision DeepStream SDK	3	224	December 13, 2022
Faild to build engine file DeepStream SDK	2	432	August 14, 2023
Error when generating engine file from a TAO trained yolov4_tiny model in Deepstream 6.1.1 DeepStream SDK	11	430	June 12, 2023
Converting yolov4 model to engine file in deepstream DeepStream SDK jetson , deepstream	6	33	January 9, 2025