After re-inference of Add2_157 node, old and new shapes do not match.

Lam__Carson · ‎01-15-2019

Model Optimizer arguments:
Common parameters:
   - Path to the Input Model: /onnx/test1.onnx
   - Path for generated IR: /NCS/bin_xml/FP16
   - IR output name:    test1
   - Log level:    ERROR
   - Batch:    Not specified, inherited from the model
   - Input layers:    Not specified, inherited from the model
   - Output layers:    Not specified, inherited from the model
   - Input shapes:    [1,3,1024,1024]
   - Mean values:    Not specified
   - Scale values:    [255,255,255]
   - Scale factor:    Not specified
   - Precision of IR:    FP16
   - Enable fusing:    False
   - Enable grouped convolutions fusing:    False
   - Move mean values to preprocess section:    False
   - Reverse input channels:    False
ONNX specific parameters:
Model Optimizer version:    1.5.12.49d067a0
[ ERROR ] -------------------------------------------------
[ ERROR ] ----------------- INTERNAL ERROR ----------------
[ ERROR ] Unexpected exception happened.
[ ERROR ] Please contact Model Optimizer developers and forward the following information:
[ ERROR ] After re-inference of Add2_157 node, old and new shapes do not match. Old shapes: [array([ 1, 16, 128, 128])], new shapes: [array([ 16, 1, 16, 128, 128])].
[ ERROR ] Traceback (most recent call last):
File "/home/carson/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/main.py", line 325, in main
return driver(argv)
File "/home/carson/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/main.py", line 302, in driver
mean_scale_values=mean_scale)
File "/home/carson/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/pipeline/onnx.py", line 152, in driver
convert_batch_norm(graph)
File "/home/carson/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/middle/passes/fusing/decomposition.py", line 78, in convert_batch_norm
_fused_batch_norm_decomposition(graph, tinput, toutput, const, beta, scale, shift, can_be_fused)
File "/home/carson/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/middle/passes/fusing/decomposition.py", line 113, in _fused_batch_norm_decomposition
data_nodes=toutput)
File "/home/carson/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/ops/op.py", line 204, in create_node_with_data
[data_node.shape for data_node in data_nodes])
AssertionError: After re-inference of Add2_157 node, old and new shapes do not match. Old shapes: [array([ 1, 16, 128, 128])], new shapes: [array([ 16, 1, 16, 128, 128])].

[ ERROR ] ---------------- END OF BUG REPORT --------------
[ ERROR ] -------------------------------------------------