Forums - WARNING_TF_SCOPE_OP_NOT_CONSUMED by common op like "Conv2D", "Relu" and "FusedBatchNorm"

1 post / 0 new
WARNING_TF_SCOPE_OP_NOT_CONSUMED by common op like "Conv2D", "Relu" and "FusedBatchNorm"
cf.hsieh
Join Date: 3 Jan 18
Posts: 2
Posted: Wed, 2018-03-07 21:45

Hi ,

my system configurations are:

Ubuntu 16.04

Python-2.7

Tensorflow-1.6 gpu version

snpe-1.13.0

I have run the example and generate "inception_v3.dlc" and "inception_v3_quantized.dlc" successfully.

I also test the .pb from my simple tutorial and it work fine with some common op like "Conv2D", "pooling" etc...

But when I try to convert my .pb model into .dlc, it fail at some common op like "Conv2D", "Relu" and "FusedBatchNorm"

part of my error msg:

2018-03-08 13:19:44,989 - 364 - WARNING - WARNING_TF_SCOPE_OP_NOT_CONSUMED: Operation (seq_3/list_1/0/Conv/Conv2D) not consumed by converter: Conv2D.
 
2018-03-08 13:19:44,990 - 364 - WARNING - WARNING_TF_SCOPE_OP_NOT_CONSUMED: Operation (seq_3/list_0/3/list_0/1/BatchNorm_1/FusedBatchNorm) not consumed by converter: FusedBatchNorm.
 
2018-03-08 13:19:44,990 - 364 - WARNING - WARNING_TF_SCOPE_OP_NOT_CONSUMED: Operation (seq_3/list_0/3/list_1/0/Relu_5) not consumed by converter: Relu.
 
2018-03-08 13:19:44,990 - 364 - WARNING - WARNING_TF_SCOPE_OP_NOT_CONSUMED: Operation (seq_3/list_0/3/list_0/5/Conv_2/BiasAdd) not consumed by converter: BiasAdd.
 
2018-03-08 13:19:44,991 - 123 - ERROR - Conversion failed: ERROR_TF_OPERATION_NOT_MAPPED_TO_LAYER: Some operations in the Tensorflow graph were not resolved to a layer. You can use --allow_unconsumed_nodes for partial graph resolution!
 
Any suggestion? Thanks~~~
 
 
 
  • 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.