Forums - error_message=Layer parameters combination is invalid in GPU Layer MobilenetV2/expanded_conv_7/depthwise/depthwise: input depth

3 posts / 0 new
or Register
Last post
error_message=Layer parameters combination is invalid in GPU Layer MobilenetV2/expanded_conv_7/depthwise/depthwise: input depth
oms1226
Join Date: 24 Mar 19
Posts: 4
Posted: Wed, 2019-04-03 00:53
Top

I want to know the reason of the below error.

  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; 

I run snpe(1.24) on the snapdragon 855 and Qualcomm, Adreno (TM) 640.

If set up  com.qualcomm.qti.snpe.NeuralNetwork.Runtime.GPU and dlc file's outputnode is argmax, I met the error!

But on com.qualcomm.qti.snpe.NeuralNetwork.Runtime.DSP, run well.

need your help!

 

 

 

  • Up0
  • Down0
Re: error_message=Layer parameters combination is invalid in...
oms1226
Join Date: 24 Mar 19
Posts: 4
Posted: Fri, 2019-04-12 22:25
Top

I know argmax only running cpu.

Also, https://developer.qualcomm.com/docs/snpe/network_layers.html, this link declars that argmax is only used in cpu.

But, argmax is running on DSP.

I wonder that reason.

  • Up0
  • Down0
Re: error_message=Layer parameters combination is invalid in...
gesqdn-forum
Join Date: 4 Nov 18
Posts: 184
Posted: Sun, 2019-04-14 02:40
Top

If you see the support from Neural Processing SDK for layer ArgMax of Tensorflow is provided only on CPU runtime.
Please check SNPE Docs for more information.
If you running it on GPU/DSP it will throw the error. Please make sure that you've set the GPU/DSP fallback to the CPU runtime in the code.
So whenever your code fails to run on GPU/DSP will switch to CPU automatically and complete the execution.

  • 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.