- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I'm trying to run model optimizer on my faster rcnn custom model.
This model has 1 input (image:0) and 4 outputs (num_detections:0 detection_boxes:0 detection_scores:0 detection_classes:0)
I a working in a ubuntu 16.04 VM (if it can influence the result).
I run :
python3 mo_tf.py --input_model /home/movidius/inference_graph.pb --tensorflow_use_custom_operations_config extensions/front/tf/faster_rcnn_support.json --tensorflow_object_detection_api_pipeline_config ~/model_test/pipeline.config
And got this output:
Model Optimizer arguments: Common parameters: - Path to the Input Model: /home/movidius/inference_graph.pb - Path for generated IR: /opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/model_optimizer/. - IR output name: inference_graph - 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: Not specified, inherited from the model - 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 - Offload unsupported operations: False - Path to model dump for TensorBoard: None - Update the configuration file with input/output node names: None - Use configuration file used to generate the model with Object Detection API: /home/movidius/model_test/pipeline.config - Operations to offload: None - Patterns to offload: None - Use the config file: /opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/model_optimizer/extensions/front/tf/faster_rcnn_support.json Model Optimizer version: 1.2.185.5335e231 [ ERROR ] ------------------------------------------------- [ ERROR ] ----------------- INTERNAL ERROR ---------------- [ ERROR ] Unexpected exception happened. [ ERROR ] Please contact Model Optimizer developers and forward the following information: [ ERROR ] 0 [ ERROR ] Traceback (most recent call last): File "/opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/model_optimizer/mo/main.py", line 321, in main return driver(argv) File "/opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/model_optimizer/mo/main.py", line 263, in driver mean_scale_values=mean_scale) File "/opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/model_optimizer/mo/pipeline/tf.py", line 171, in tf2nx class_registration.apply_replacements(graph, class_registration.ClassType.FRONT_REPLACER) File "/opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/model_optimizer/mo/utils/class_registration.py", line 102, in apply_replacements replacer.find_and_replace_pattern(graph) File "/opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/model_optimizer/mo/front/tf/replacement.py", line 91, in find_and_replace_pattern self.replace_sub_graph(graph, match) File "/opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/model_optimizer/mo/front/common/replacement.py", line 115, in replace_sub_graph new_sub_graph = self.generate_sub_graph(graph, match) File "/opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/model_optimizer/extensions/front/tf/ObjectDetectionAPI.py", line 133, in generate_sub_graph sub_node = match.output_node(0)[0] File "/opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/model_optimizer/mo/front/subgraph_matcher.py", line 130, in output_node return self._output_nodes_map[port] KeyError: 0 [ ERROR ] ---------------- END OF BUG REPORT -------------- [ ERROR ] -------------------------------------------------
Any idea of what's wrong ?
Regards.
Magaly
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Magaly,
as you have re-trained your own faster rcnn model, you should use the faster_rcnn_support_api_v1.7.json.
Best,
Severine
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
Thank you for your answer
Indeed I've retrained the model and tried with the *.json file but only changing the input an output tensors (which are basically what I've modified from the original fast-rcnn). I finally had the optimizer working but from the *.meta file. And tthis is enough for the tests we are making but it will be convenient to use the .pb later so I'll dive in the *.json file.
Thank you again
Regards,
Magay
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I trained a model faster_rcnn_resnet50 on oxford pets database, using tensorflow object detction api.
I fail to model optimize frozen_inference_graph.pb.
C:\Intel\computer_vision_sdk_2018.3.343\deployment_tools\model_optimizer>python mo_tf.py --input_model d:\TFS\LPR\IP\MAIN\SRC\PythonProjects\TensorFlow\FreezeGraph\FreezeGraph\faster_rcnn_resnet50_pets_shay\frozen_inference_graph.pb --tensorflow_object_detection_api_pipeline_config d:\TFS\LPR\IP\MAIN\SRC\PythonProjects\TensorFlow\FreezeGraph\FreezeGraph\faster_rcnn_resnet50_pets_shay\faster_rcnn_resnet50_pets_shay.config
Model Optimizer arguments:
Common parameters:
- Path to the Input Model: d:\TFS\LPR\IP\MAIN\SRC\PythonProjects\TensorFlow\FreezeGraph\FreezeGraph\faster_rcnn_resnet50_pets_shay\frozen_inference_graph.pb
- Path for generated IR: C:\Intel\computer_vision_sdk_2018.3.343\deployment_tools\model_optimizer\.
- IR output name: frozen_inference_graph
- 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: Not specified, inherited from the model
- 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
- Offload unsupported operations: False
- Path to model dump for TensorBoard: None
- Update the configuration file with input/output node names: None
- Use configuration file used to generate the model with Object Detection API: d:\TFS\LPR\IP\MAIN\SRC\PythonProjects\TensorFlow\FreezeGraph\FreezeGraph\faster_rcnn_resnet50_pets_shay\faster_rcnn_resnet50_pets_shay.config
- Operations to offload: None
- Patterns to offload: None
- Use the config file: None
Model Optimizer version: 1.2.185.5335e231
[ ERROR ] Node Preprocessor/map/while/ResizeToRange/unstack has more than one outputs. Provide output port explicitly.
If I can optimize on the meta checkpoint file it would be great. Can you tell me how?
Thanks.
My files can be viewed at:
https://www.dropbox.com/sh/dh1c325m0t22qsn/AAAJRfedjbF0uMsTLWyS6uVYa?dl=0
![](/skins/images/872293744008A34B36F8ABF94A46CC66/responsive_peak/images/icon_anonymous_message.png)
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page