Azzera filtri
Azzera filtri

int8 Calibration data with semantic segmentation

5 visualizzazioni (ultimi 30 giorni)
I successfully depoyed a fp16 network with GPU Coder. In order to accelerate speed I would like to test int8 resolution with the GPU Coder.
Therefore I changed the following option in the GPU Coder:
cfg.DeepLearningConfig.DataType = 'int8';
In the help is described that an additional data set must be provided to calibrate the network with limited resolution:
cfg.DeepLearningConfig.DataPath = 'C:\Temp\Matlab\Calibration\';
Even the documentation is not very clear how the provide calibration data for semantic segmentation I simply specified the logos_dataset from the TensorRT example for a first try. However as soon as I switch from fp16 to int8 I get the following error from GPU Coder:
??? Error generating Makefile while generating code for network 2019b-huc0102_0. TensorRT INT8 supports only classification networks. Output layer of network must be a
Are there any plans to support this semantic segmentation with int8 resolution in the future?
Best regards, Markus

Risposta accettata

Jaya Shankar
Jaya Shankar il 28 Ott 2019
Hi Markus
GPU Coder does not support INT8 inference for regression and semantic segmentation networks today. We will be looking to add this in a later release.

Più risposte (1)

Christian Huggler
Christian Huggler il 30 Ago 2021
Are there any news according INT8 for semantic segmentation networks?


Scopri di più su Deep Learning with GPU Coder in Help Center e File Exchange




Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by