Community
cancel
Showing results for 
Search instead for 
Did you mean: 
Highlighted
14 Views

Issues with split function in Release 5

Hello,

On trying to convert a frozen graph using the MO, I am facing issues with the split function. Error I got is :

 ERROR ]  Exception occurred during running replacer "None" (<class 'extensions.front.eltwise_n.EltwiseNReplacement'>): Node split has more than one outputs. Provide output port explicitly. 
[ 2018-12-21 19:04:10,511 ] [ DEBUG ] [ main:331 ]  Traceback (most recent call last):
  File "/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/utils/class_registration.py", line 114, in apply_replacements
    replacer.find_and_replace_pattern(graph)
  File "/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/front/common/replacement.py", line 125, in find_and_replace_pattern
    apply_pattern(graph, action=self.replace_sub_graph, **self.pattern())
  File "/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/middle/pattern_match.py", line 95, in apply_pattern
    action(graph, match)
  File "/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/front/common/replacement.py", line 189, in replace_sub_graph
    self.replace_output_edges(graph, self.gen_output_edges_match(node, self.replace_op(graph, node)))
  File "/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/extensions/front/eltwise_n.py", line 37, in replace_op
    out_node = eltwise_op.create_node([out_node, node.in_node(ind)])
  File "/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/ops/op.py", line 129, in create_node
    inputs = [Op.extract_port(inp) for inp in inputs]
  File "/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/ops/op.py", line 129, in <listcomp>
    inputs = [Op.extract_port(inp) for inp in inputs]
  File "/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/ops/op.py", line 103, in extract_port
    raise Error('Node {} has more than one outputs. Provide output port explicitly. '.format(node.name))
mo.utils.error.Error: Node split has more than one outputs. Provide output port explicitly. 

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/main.py", line 325, in main
    return driver(argv)
  File "/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/main.py", line 267, in driver
    mean_scale_values=mean_scale)
  File "/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/pipeline/tf.py", line 248, in tf2nx
    class_registration.apply_replacements(graph, class_registration.ClassType.FRONT_REPLACER)
  File "/opt/intel/computer_vision_sdk_2018.5.445/deployment_tools/model_optimizer/mo/utils/class_registration.py", line 121, in apply_replacements
    )) from err
mo.utils.error.Error: Exception occurred during running replacer "None" (<class 'extensions.front.eltwise_n.EltwiseNReplacement'>): Node split has more than one outputs. Provide output port explicitly. 

 

 

Steps to reproduce the error 

sudo python3 mo_tf.py --input_model finalGraph.pb --log_level=DEBUG

 

Please also find the attached frozen pb . 

0 Kudos
0 Replies