Attempt to connect X to TFSubgraphCall_. Missing in port (1) in TFSubgraphCall_ node

Ferraro__Giampaolo · ‎10-17-2019

Hey,

I am trying to use the model optimizer to convert my Tensorflow 1.14 model. Have run into a few errors, about while loops so i have used the suggested --tensorflow_subgraph_patterns argument.

But now I get an error for each node that has a connection to this sub graph pattern

```[ ERROR ] Exception occurred during running replacer "REPLACEMENT_ID (<class 'extensions.front.tf.tensorflow_patterns.TensorflowSubgraphPatterns'>)": Attempt to connect strided_slice_11 to TFSubgraphCall_. Missing in port (1) in TFSubgraphCall_ node```

Any help would be appreciated, Thanks
Full Output
   - Batch:    Not specified, inherited from the model
   - Input layers:    X,state_in
   - Output layers:    state_out,prediction
   - Input shapes:    [1,1,5,48,48],[1,256,2]
   - Mean values:    Not specified
   - Scale values:    Not specified
   - Scale factor:    Not specified
   - Precision of IR:    FP32
   - Enable fusing:    True
   - Enable grouped convolutions fusing:    True
   - Move mean values to preprocess section:    False
   - Reverse input channels:    False
TensorFlow specific parameters:
   - Input model in text protobuf format:    False
   - Path to model dump for TensorBoard:    None
   - List of shared libraries with TensorFlow custom layers implementation:    None
   - Update the configuration file with input/output node names:    None
   - Use configuration file used to generate the model with Object Detection API:    None
   - Operations to offload:    Abs,StridedSlice
   - Patterns to offload:    lstm/.*
   - Use the config file:    None
Model Optimizer version:    2019.3.0-375-g332562022

[ ERROR ] -------------------------------------------------
[ ERROR ] ----------------- INTERNAL ERROR ----------------
[ ERROR ] Unexpected exception happened.
[ ERROR ] Please contact Model Optimizer developers and forward the following information:
[ ERROR ] Exception occurred during running replacer "REPLACEMENT_ID (<class 'extensions.front.tf.tensorflow_patterns.TensorflowSubgraphPatterns'>)": Attempt to connect strided_slice_11 to TFSubgraphCall_. Missing in port (1) in TFSubgraphCall_ node
[ ERROR ] Traceback (most recent call last):
File "/opt/intel/openvino_2019.3.334/deployment_tools/model_optimizer/mo/utils/class_registration.py", line 273, in apply_replacements
for_graph_and_each_sub_graph_recursively(graph, replacer.find_and_replace_pattern)
File "/opt/intel/openvino_2019.3.334/deployment_tools/model_optimizer/mo/middle/pattern_match.py", line 58, in for_graph_and_each_sub_graph_recursively
func(graph)
File "/opt/intel/openvino_2019.3.334/deployment_tools/model_optimizer/extensions/front/tf/tensorflow_patterns.py", line 35, in find_and_replace_pattern
csc.replace_subgraph_calls(graph, argv.tensorflow_subgraph_patterns)
File "/opt/intel/openvino_2019.3.334/deployment_tools/model_optimizer/mo/front/tf/custom_subgraph_call.py", line 41, in replace_subgraph_calls
merge_nodes(graph, matched_nodes)
File "/opt/intel/openvino_2019.3.334/deployment_tools/model_optimizer/mo/front/tf/custom_subgraph_call.py", line 165, in merge_nodes
edge_attrs)
File "/opt/intel/openvino_2019.3.334/deployment_tools/model_optimizer/mo/graph/graph.py", line 524, in add_edge
assert vnode.has_port('in', in_port, control_flow=is_control_flow), "{} Missing in port ({}) in {} node".format(message, in_port, vnode.name)
AssertionError: Attempt to connect strided_slice_11 to TFSubgraphCall_. Missing in port (1) in TFSubgraphCall_ node

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

Traceback (most recent call last):
File "/opt/intel/openvino_2019.3.334/deployment_tools/model_optimizer/mo/main.py", line 302, in main
return driver(argv)
File "/opt/intel/openvino_2019.3.334/deployment_tools/model_optimizer/mo/main.py", line 251, in driver
is_binary=not argv.input_model_is_text)
File "/opt/intel/openvino_2019.3.334/deployment_tools/model_optimizer/mo/pipeline/tf.py", line 136, in tf2nx
class_registration.apply_replacements(graph, class_registration.ClassType.FRONT_REPLACER)
File "/opt/intel/openvino_2019.3.334/deployment_tools/model_optimizer/mo/utils/class_registration.py", line 299, in apply_replacements
)) from err
Exception: Exception occurred during running replacer "REPLACEMENT_ID (<class 'extensions.front.tf.tensorflow_patterns.TensorflowSubgraphPatterns'>)": Attempt to connect strided_slice_11 to TFSubgraphCall_. Missing in port (1) in TFSubgraphCall_ node

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