Wrong inference result with python API for tensorflow model

dht7166 · July 11, 2018, 4:22pm

Hi, I am using a frozen tensorflow version of YOLOv2. The problem is when I used tensorrt with it, the inferred result is way off, with almost all of the result are -inf.

I am using tensorrt on GTX 1050, tensorrt 3.0.4 with cuda 8.0. Any help would be appreciated.

dht7166 · July 23, 2018, 4:08pm

The problem turns out to be some error with setting up some code.

Topic		Replies	Views
TensorRT inference producing incorrect results TensorRT	0	745	July 22, 2019
Inference error using YOLOv2 on Jetson TX2 Jetson TX2	4	1084	October 18, 2021
tensorflow inference result is error Jetson TX2	7	610	October 18, 2021
TensorRT model inference result is not correctly TensorRT tensorrt , tensorflow , onnx	1	649	July 1, 2022
inference time of tensorrt is slower than tensorflow !!! TensorRT	2	1433	September 27, 2019
Strange results when benchmarking YoloV2 and YoloV3 models in TensorRT TensorRT	4	464	April 9, 2021
[PythonAPI] Multi-outputs for TensorRT TensorRT tensorrt , python	3	651	June 16, 2023
TensorRT Inference is Slower Than Other Frameworks TensorRT	7	3709	December 9, 2019
Issue with Inferencing with TensorRT on Python TensorRT	7	1125	July 20, 2022
TensorRT 10.4 inference gives incorrect results (correct when using v8.6) TensorRT tensorrt , cudnn	0	52	October 10, 2024

Wrong inference result with python API for tensorflow model

Related topics