Forums - Compatibility problem between slice layer and concatenation layer

1 post / 0 new
Compatibility problem between slice layer and concatenation layer
taewoo83.lee
Join Date: 26 Apr 16
Posts: 3
Posted: Thu, 2018-01-04 17:16

I met this error message as below

Conversion failed: ERROR_TF_CONCAT_INPUT: Concatenation layer requires at least two inputs

 

My tensorflow code is as below:

Xs=tf.split(X, 2, 3)

Xr=tf.concat(Xs, 2)

 

Xs is a list including two tensors.

 

when I convert pb to dlc, a slice layer in SNPE returns only one descriptor but concatenation layer needs two descriptors at least.

anyone has solution for this problem?

 

 

  • Up0
  • Down0

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.