int8 Calibration data with semantic segmentation

7 views (last 30 days)
Hi
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
ClassificationOutputLayer
Are there any plans to support this semantic segmentation with int8 resolution in the future?
Best regards, Markus

Accepted Answer

Jaya Shankar
Jaya Shankar on 28 Oct 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.
Jaya

More Answers (1)

Christian Huggler
Christian Huggler on 30 Aug 2021
Are there any news according INT8 for semantic segmentation networks?

Products


Release

R2019b

Community Treasure Hunt

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

Start Hunting!