Hi, I am getting output like below while running inference on LPRnet instead of numbers. input: shape:(-1, 3, 48, 96) dtype:DataType.FLOAT output: shape:(-1, 24) dtype:DataType.INT32 output: shape:(-1, 24) dtype:DataType.FLOAT [array([35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35, 35,…

Not Getting Correct output while running inference using TensorRT on LPRnet fp16 Model

kayccc July 22, 2021, 5:33am 9

Topic		Replies	Views
Not Getting Correct output while running inference using TensorRT on LPRnet fp16 Model TAO Toolkit	23	1538	September 27, 2021
Falure to do inference TAO Toolkit tensorrt	9	1075	January 11, 2022
Running nvidia pretrained models in Tensorrt inference TAO Toolkit	14	933	October 6, 2022
Converted model is broken if half precision with dynamic batch size and batch size is greater than 1 TensorRT	11	2456	October 18, 2024
How can I access the same TensorRT engine model in different thread TensorRT cudnn	1	573	November 27, 2023
Batch Inference Wrong in Python API TensorRT	15	3557	October 12, 2021
Different FP16 inference with tensorrt and pytorch TensorRT	5	4523	October 25, 2021
Inference result gets worse when converting pytorch model to TensorRT model TensorRT pytorch	6	1156	January 19, 2022
TensorRT Inference form a .etlt model on Python TAO Toolkit tensorrt	7	1237	November 16, 2021
TensorRT waiting after inference seemingly for no reason TensorRT tensorrt , cuda , performance , python	12	1577	October 20, 2022