https://community.intel.com/t5/Items-with-no-label/Error-converting-a-model/m-p/666155#M15376 <P>Hi </P><P>I am trying to convert a model (20180402-114759.pb )using mo_tf.py but the following error is occurred could u help me with that&nbsp;</P><P>&nbsp;</P><P>ERROR:</P><P>Common parameters:</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Path to the Input Model:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/20180402-114759.pb</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Path for generated IR:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;/home/icsltd/Desktop/FP16</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- IR output name:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;20180402-114759</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Log level:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;ERROR</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Batch:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Not specified, inherited from the model</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Input layers:&nbsp;&nbsp;Not specified, inherited from the model</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Output layers:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Not specified, inherited from the model</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Input shapes: Not specified, inherited from the model</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Mean values: [127,127,127]</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Scale values:&nbsp;&nbsp;Not specified</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Scale factor:&nbsp;&nbsp;&nbsp;256.0</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Precision of IR:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;FP16</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Enable fusing:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;True</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Enable grouped convolutions fusing:&nbsp;&nbsp;True</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Move mean values to preprocess section:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;False</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Reverse input channels:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;False</P><P>TensorFlow specific parameters:</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Input model in text protobuf format:&nbsp;False</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Offload unsupported operations:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;False</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Path to model dump for TensorBoard:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- List of shared libraries with TensorFlow custom layers implementation:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Update the configuration file with input/output node names:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Use configuration file used to generate the model with Object Detection API:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Operations to offload:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Patterns to offload:&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Use the config file:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>Model Optimizer version:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;1.5.12.49d067a0</P><P>[ ERROR ]&nbsp;-------------------------------------------------</P><P>[ ERROR ]&nbsp;----------------- INTERNAL ERROR ----------------</P><P>[ ERROR ]&nbsp;Unexpected exception happened.</P><P>[ ERROR ]&nbsp;Please contact Model Optimizer developers and forward the following information:</P><P>[ ERROR ]&nbsp;After re-inference of Mul1_13841 node, old and new shapes do not match. Old shapes: [array([], dtype=int64)], new shapes: [array([1])].</P><P>[ ERROR ]&nbsp;Traceback (most recent call last):</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/<A href="http://main.py">main.py</A>", line 325, in main</P><P>&nbsp;&nbsp;&nbsp;return driver(argv)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/<A href="http://main.py">main.py</A>", line 267, in driver</P><P>&nbsp;&nbsp;&nbsp;mean_scale_values=mean_scale)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/pipeline/<A href="http://tf.py">tf.py</A>", line 316, in tf2nx</P><P>&nbsp;&nbsp;&nbsp;scale_input(graph, scale)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/middle/passes/<A href="http://infer.py">infer.py</A>", line 338, in scale_input</P><P>&nbsp;&nbsp;&nbsp;action=lambda graph, match: _scale_input_action_mul(graph, match, scale)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/middle/pattern_match.py", line 95, in apply_pattern</P><P>&nbsp;&nbsp;&nbsp;action(graph, match)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/middle/passes/<A href="http://infer.py">infer.py</A>", line 338, in &lt;lambda&gt;</P><P>&nbsp;&nbsp;&nbsp;action=lambda graph, match: _scale_input_action_mul(graph, match, scale)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/middle/passes/<A href="http://infer.py">infer.py</A>", line 318, in _scale_input_action_mul</P><P>&nbsp;&nbsp;&nbsp;mul_node.create_node_with_data(inputs=[mul_input, mul_data], data_nodes=toutput)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/ops/<A href="http://op.py">op.py</A>", line 204, in create_node_with_data</P><P>&nbsp;&nbsp;&nbsp;[data_node.shape for data_node in data_nodes])</P><P>AssertionError: After re-inference of Mul1_13841 node, old and new shapes do not match. Old shapes: [array([], dtype=int64)], new shapes: [array([1])].</P><P>&nbsp;</P><P>[ ERROR ]&nbsp;---------------- END OF BUG REPORT --------------</P><P>[ ERROR ]&nbsp;-------------------------------------------------</P><P>Thanks&amp;regards</P><P>Deepika</P> Wed, 13 Mar 2019 12:12:59 GMT KDeep 2019-03-13T12:12:59Z https://community.intel.com/t5/Items-with-no-label/Error-converting-a-model/m-p/666155#M15376 <P>Hi </P><P>I am trying to convert a model (20180402-114759.pb )using mo_tf.py but the following error is occurred could u help me with that&nbsp;</P><P>&nbsp;</P><P>ERROR:</P><P>Common parameters:</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Path to the Input Model:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/20180402-114759.pb</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Path for generated IR:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;/home/icsltd/Desktop/FP16</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- IR output name:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;20180402-114759</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Log level:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;ERROR</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Batch:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Not specified, inherited from the model</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Input layers:&nbsp;&nbsp;Not specified, inherited from the model</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Output layers:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Not specified, inherited from the model</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Input shapes: Not specified, inherited from the model</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Mean values: [127,127,127]</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Scale values:&nbsp;&nbsp;Not specified</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Scale factor:&nbsp;&nbsp;&nbsp;256.0</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Precision of IR:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;FP16</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Enable fusing:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;True</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Enable grouped convolutions fusing:&nbsp;&nbsp;True</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Move mean values to preprocess section:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;False</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Reverse input channels:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;False</P><P>TensorFlow specific parameters:</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Input model in text protobuf format:&nbsp;False</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Offload unsupported operations:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;False</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Path to model dump for TensorBoard:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- List of shared libraries with TensorFlow custom layers implementation:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Update the configuration file with input/output node names:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Use configuration file used to generate the model with Object Detection API:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Operations to offload:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Patterns to offload:&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;- Use the config file:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;None</P><P>Model Optimizer version:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;1.5.12.49d067a0</P><P>[ ERROR ]&nbsp;-------------------------------------------------</P><P>[ ERROR ]&nbsp;----------------- INTERNAL ERROR ----------------</P><P>[ ERROR ]&nbsp;Unexpected exception happened.</P><P>[ ERROR ]&nbsp;Please contact Model Optimizer developers and forward the following information:</P><P>[ ERROR ]&nbsp;After re-inference of Mul1_13841 node, old and new shapes do not match. Old shapes: [array([], dtype=int64)], new shapes: [array([1])].</P><P>[ ERROR ]&nbsp;Traceback (most recent call last):</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/<A href="http://main.py">main.py</A>", line 325, in main</P><P>&nbsp;&nbsp;&nbsp;return driver(argv)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/<A href="http://main.py">main.py</A>", line 267, in driver</P><P>&nbsp;&nbsp;&nbsp;mean_scale_values=mean_scale)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/pipeline/<A href="http://tf.py">tf.py</A>", line 316, in tf2nx</P><P>&nbsp;&nbsp;&nbsp;scale_input(graph, scale)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/middle/passes/<A href="http://infer.py">infer.py</A>", line 338, in scale_input</P><P>&nbsp;&nbsp;&nbsp;action=lambda graph, match: _scale_input_action_mul(graph, match, scale)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/middle/pattern_match.py", line 95, in apply_pattern</P><P>&nbsp;&nbsp;&nbsp;action(graph, match)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/middle/passes/<A href="http://infer.py">infer.py</A>", line 338, in &lt;lambda&gt;</P><P>&nbsp;&nbsp;&nbsp;action=lambda graph, match: _scale_input_action_mul(graph, match, scale)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/middle/passes/<A href="http://infer.py">infer.py</A>", line 318, in _scale_input_action_mul</P><P>&nbsp;&nbsp;&nbsp;mul_node.create_node_with_data(inputs=[mul_input, mul_data], data_nodes=toutput)</P><P>&nbsp;File "/opt/intel/computer_vision_sdk_2018.5.455/deployment_tools/model_optimizer/mo/ops/<A href="http://op.py">op.py</A>", line 204, in create_node_with_data</P><P>&nbsp;&nbsp;&nbsp;[data_node.shape for data_node in data_nodes])</P><P>AssertionError: After re-inference of Mul1_13841 node, old and new shapes do not match. Old shapes: [array([], dtype=int64)], new shapes: [array([1])].</P><P>&nbsp;</P><P>[ ERROR ]&nbsp;---------------- END OF BUG REPORT --------------</P><P>[ ERROR ]&nbsp;-------------------------------------------------</P><P>Thanks&amp;regards</P><P>Deepika</P> Wed, 13 Mar 2019 12:12:59 GMT https://community.intel.com/t5/Items-with-no-label/Error-converting-a-model/m-p/666155#M15376 KDeep 2019-03-13T12:12:59Z https://community.intel.com/t5/Items-with-no-label/Error-converting-a-model/m-p/666156#M15377 <P>Although I do not have direct experience of model conversion with <B>mo_tf</B>, the guide by Intel I have linked to below may be useful to check your process against to see if something has been missed.</P><P>&nbsp;</P><P><A href="https://software.intel.com/en-us/articles/OpenVINO-Using-TensorFlow#inpage-nav-5">https://software.intel.com/en-us/articles/OpenVINO-Using-TensorFlow#inpage-nav-5</A></P> Wed, 13 Mar 2019 13:52:49 GMT https://community.intel.com/t5/Items-with-no-label/Error-converting-a-model/m-p/666156#M15377 MartyG 2019-03-13T13:52:49Z