int8 Calibration data with semantic segmentation
3 次查看(过去 30 天)
显示 更早的评论
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
0 个评论
采纳的回答
Jaya Shankar
2019-10-28
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
0 个评论
更多回答(1 个)
Christian Huggler
2021-8-30
Are there any news according INT8 for semantic segmentation networks?
0 个评论
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Deep Learning with GPU Coder 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!