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!