- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello,
I used the TensorFlow object detection API to train a custom dataset. I used mobilenet_v2.
I tested the model on a PC and now I want to run the inference on the NCS2. I tried to follow this guide
but the model_optimizer throws following errors
[ ERROR ] Shape is not defined for output 0 of "SecondStagePostprocessor/map/TensorArrayUnstack_1/Shape".
[ ERROR ] Cannot infer shapes or values for node "SecondStagePostprocessor/map/TensorArrayUnstack_1/Shape".
[ ERROR ] Not all output shapes were inferred or fully defined for node "SecondStagePostprocessor/map/TensorArrayUnstack_1/Shape".
For more information please refer to Model Optimizer FAQ (/deployment_tools/documentation/docs/MO_FAQ.html), question #40.
[ ERROR ]
[ ERROR ] It can happen due to bug in custom shape infer function .
[ ERROR ] Or because the node inputs have incorrect values/shapes.
[ ERROR ] Or because input shapes are incorrect (embedded to the model or passed via --input_shape).
[ ERROR ] Run Model Optimizer with --log_level=DEBUG for more information.
[ ERROR ] Stopped shape/value propagation at "SecondStagePostprocessor/map/TensorArrayUnstack_1/Shape" node.
For more information please refer to Model Optimizer FAQ (/deployment_tools/documentation/docs/MO_FAQ.html), question #38.
As this error indicates a wrong input_shape, I tried to adjust the input_shape but the error stays the same. The command I use is following:
python mo_tf.py --input_model C:\KI\Object_Detection\inference_graph\frozen_inference_graph.pb --tensorflow_use_custom_operations_config C:\Intel\computer_vision_sdk\deployment_tools\model_optimizer\extensions\front\tf\ssd_v2_support.json --tensorflow_object_detection_api_pipeline_config C:\KI\Object_Detection\inference_graph\pipeline.config --reverse_input_channels --data_type FP16 --input_shape [1,640,480,1]
Thanks you in advance.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi @daoedad
Could you provide a link to your model?
Make sure the information in the "ssd_v2_support.json" file matches the parameters from your config file. The ssd_v2_support.json file was made for the pretrained data set. If you a custom data set, you will have to edit the parameters in the json file.
Regards,
Aroop
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi @Aroop_at_Intel,
here is a link to my model:
https://drive.google.com/open?id=12YHB0Bes6egGSR0ml9QjLilioCpgrbyl
I tried to edit the "ssd_v2_support.json". But I don´t really know what to do and how to match the .json file with my model.
Is there a guide for editing or something?
Thank you for your help.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi @daoedad,
Thanks for sharing your model and json file. Try to make the following change to line 57 of ssd_v2_suport.json.
Change:
"Postprocessor/ToFloat"
To:
"Postprocessor/Cast"
After the change is made, try converting the model again.
Regards,
Aroop
![](/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