Hi, I’m trying to apply a Bisenetv2 model based on Python TensorRT 7. The model I’ve used is Bisenetv2, and it’s already converted from TensorFlow pb to onnx with tf2onnx. The model worked fine when I used FP32 and FP16 model. However, when I use INT8, TensorRT outputs an error message “IndexError:…

TensorRT int8 calibration error: IndexError: _Map_base::at

podkolzin.v.y July 13, 2021, 11:02pm 5

Hello, did u solve that problem?

Topic		Replies	Views
Tenssorrt INT8 precision engine build failed for the models having custom layer (BatchedNMSDynamic_TRT) TensorRT	11	2112	June 29, 2021
Driver error-TensorRT INT8 deploy TensorRT	3	759	November 20, 2020
How to do Int8 calibration for Faster RCNN? TensorRT	1	623	August 17, 2020
TensorRT INT8 Calibration Issue TensorRT tensorrt , tensorflow	7	2367	May 7, 2021
Int8 calibration TensorRT	1	2518	December 17, 2021
[TensorRT] INTERNAL ERROR: Assertion failed: d.nbDims >= 1 int8 TensorRT tensorrt	4	1768	April 15, 2021
Building TensorRT int8 engine fails TensorRT	1	390	January 20, 2021
TensorRT Python INT8 calibration failure TensorRT	3	2020	November 23, 2018
TensorRT INT8 conversion from an ONNX model TensorRT tensorrt , calibration , onnx	4	5949	July 29, 2024
Internal Error (Assertion min_ <= max_ failed.) calibrate model with IInt8MinMaxCalibrator C++ on tensorrt 8.6.11.4 DRIVE AGX Orin General driveos-dl	4	465	May 23, 2024