- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi there
I trained, froze and converted a custom tensorflow model using the model optimizer. Conversion with the model optimizer completed successfully.
The model is a simple feedforward network that consumes a single image and produces an 8D vector.
To get startet with OpenVino, I adapted the car detection tutorial from:
https://github.com/intel-iot-devkit/inference-tutorials-generic ;
The tutorial runs fine on my laptop when the provided model is loaded (vehicle-detection-adas-0002.xml).
To run the code sample with my own model, I need to adapt the checks for input and outpt sizes (line 223 in ~/inference-tutorials-generic/car_detection_tutorial/step_2/main.cpp) like this:
if (objectSize != 8) { ... } if (outputDims.size() != 2) { ... }
When I run the adapted sample and load my own model, the program fails to load the network.
./car_detection_tutorial -m optimized_graph.xml
Output: InferenceEngine: API version ............ 1.4 Build .................. 17328 [ INFO ] Parsing input parameters [ INFO ] Reading input [ INFO ] Loading plugin CPU API version ............ 1.4 Build .................. lnx_20181004 Description ....... MKLDNNPlugin [ INFO ] Loading network files for VehicleDetection [ INFO ] Batch size is set to 1 for Vehicle Detection [ INFO ] Checking Vehicle Detection inputs [ INFO ] Checking Vehicle Detection outputs [ INFO ] Loading Vehicle Detection model to the CPU plugin [ ERROR ] std::exception
I am aware that the demo will not work entirely with a different network, but I expected that the network should be at least loaded and the first image should be fed through the network.
I attached the converted model from the model optimizer as well as the original frozen graph from tensorflow.
Thanks for any help!
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Dear Elia,
I tried your network through our benchmark app (included in the samples), which allows to load a model without processing the output. The network is working properly, therefore I think the issue is from the output processing.
From my experience, it is better to ramp up from an easier sample like classification_sample or hello_classification in order to customize a sample. The sample you have chosen is having a more complicated structure that the samples I mention.
Best,
Severine
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page