search

foss-for-synopsys-dwc-arc-processors / embarc_osp

embARC Open Software Platform (OSP) - An embedded software distribution for IoT and other embedded applications for ARC
https://www.embarc.org/
BSD 3-Clause "New" or "Revised" License
70 stars 62 forks source link

How to transform the pre-trained model on caffe or tensorflow to c file for iotdk inference application? #113

Closed CWLiang closed 5 years ago

CWLiang commented 5 years ago

Issue Summary

I want to use ARC iotdk to do some machine learning inference application. So I reference the example that provided in embarc_osp/example/baremetal/embarc_mli/cifar10_caffe. There are two files "cifar10_coefficients_chw_big.c" and "cifar10_coefficients_chw_small.c" that list all the coefficients of the convolution layers. I wonder how to transform the pre-trained model into that coefficient files. Is there any automation tool or flow could support the transformation?

Development Environment

Question

I wonder how to transform the pre-trained model into that coefficient files. Is there any automation tool or flow could support the transformation?

vonhust commented 5 years ago

pls move this issue to embarc mli repo: https://github.com/foss-for-synopsys-dwc-arc-processors/embarc_mli