Time of inference in FP16 and FP32 is the same

system Closed August 24, 2022, 4:42am 24

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

Topic		Replies	Views
Tensorrt can not speed up well TensorRT	7	1774	June 29, 2022
No performance difference between Float16 and Float32 optimized TensorRT models Jetson AGX Xavier tensorrt	4	3327	October 10, 2021
FP16 doesn't bring improvement to inference TensorRT	0	960	May 29, 2019
No performance improvement on Jetson Nano FP16 vs FP32 TensorRT	6	2790	February 22, 2021
TensorRT Inferencing using TF-TRT framework FP32 vs FP16 Jetson AGX Orin tensorrt	6	463	June 3, 2024
FP16 not even two times faster than using FP32 in TensorRT TensorRT	0	686	June 12, 2019
No performance improvement for Tensorflow TensorRT model on converted on Jetsons Xavier NX Jetson Xavier NX tensorrt , tensorflow	2	734	October 18, 2021
inference speed not improve between FP32 vs FP16 when using tensorflow.contrib.tensorrt Jetson AGX Xavier	4	781	October 18, 2021
Convert the TRT model with FP16 Jetson TX2 jetpack , tensorrt , jetson-inference	7	2639	October 18, 2021
Object Detection Inference Optimisation Jetson Xavier NX jetson-inference	4	728	April 17, 2023