Forums - snpe-tensorflow-to-dlc fail to convert DeepLabV3 with error_code=803

4 posts / 0 new
Last post
snpe-tensorflow-to-dlc fail to convert DeepLabV3 with error_code=803
Lee
Join Date: 16 Oct 18
Posts: 1
Posted: Wed, 2018-10-31 02:29

Hi all,

I face error when i convert DeepLabV3 as SNPE SDK Reference Guide mentioned.

I follow the steps to setup SNPE and Tensorflow with virtualenv. Not sure what steps i miss to cause this error.

SNPE version: 1.19.2

Tensorflow : 1.6

Error log:

$ snpe-tensorflow-to-dlc --graph deeplabv3_mnv2_pascal_train_aug/frozen_inference_graph.pb -i sub_7 1,513,513,3 --out_node ArgMax --dlc deeplabv3.dlc --allow_unconsumed_nodes
RuntimeWarning: error_code=803; error_message=Layer parameters combination is invalid in GPU Layer MobilenetV2/expanded_conv_7/depthwise/depthwise: input depth must be divisible by 4 * number of groups; error_component=GPU Runtime; line_no=78; thread_id=140182270043968
  groups=descriptor.groups)
 
RuntimeWarning: error_code=1000; error_message=Layer is not supported. Layer ArgMax of type ArgMax not supported by GPU runtime; error_component=Model Validation; line_no=274; thread_id=140182270043968
  output_name=output_name)
 
thanks

 

  • Up0
  • Down0
Jaden Kong
Join Date: 15 Jun 16
Posts: 1
Posted: Thu, 2018-11-15 19:17
I got same issue, anyone can help?
  • Up0
  • Down0
chenfeng
Join Date: 30 Aug 17
Posts: 6
Posted: Thu, 2018-12-20 01:08

 

This is Warning message that should not impact the functional.   If the layers was not support by GPU runtime, it should fall back to CPU.

  • Up0
  • Down0
gesqdn-forum
Join Date: 4 Nov 18
Posts: 184
Posted: Fri, 2019-05-10 00:04

The error is displayed is for just inform that the particular layers will not support with the GPU runtime. So after conversion, You will get the converted DLC file. For Running the application properly please set CPU fallback option which will helps you to run layers on CPU which are not supported by GPU or DSP.
Hope This will resolve your problem.

  • Up0
  • Down0
or Register

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.