Hi Guys,
Congratulations on a well thought through product portfolio and quality implementation.

I've just started on trying to convert a custom TensorFlow model to MyriadX blob format and using the blob converter, I just get a downloading message but nothing ever completes.

Also, trying to access the online converter at http://luxonis.com:8080/ hangs with a blank page. I don't have port 8080 firewalled so would like to check if the server is down. Thanks.

  • erik replied to this.

    Hello mikegardner, thanks for the kind words🙂
    Sorry for the trouble, we have (properly) updated the app, so now you can find it at http://blobconverter.luxonis.com/
    We might not have updated the link everywhere, I will make sure it gets updated. Thanks for reminding/notifying us!
    Erik

      Just found out we forgot to update the URL to the blobconverter web app everywhere. PR here. We apologize for the inconvenience.
      Thanks, Erik

      Thanks for the very prompt response guys. I've just given it a go and have an error. Any clues from the error message that could hint what is wrong and anything that can be done to remedy the issue? Basically, the model is British Garden Birds, the smaller of the two files at https://github.com/secretbatcave/Uk-Bird-Classifier

      Here's the error output...

      Command failed with exit code 1, command: /usr/bin/python3 model_compiler/openvino_2021.4/converter.py --precisions FP16 --output_dir /tmp/blobconverter/808e578f8d504462917e36a87a426f25 --download_dir /tmp/blobconverter/808e578f8d504462917e36a87a426f25 --name ukGardenModel --model_root /tmp/blobconverter/808e578f8d504462917e36a87a426f25

      (some command usage info, then) ...

      2021-08-13 14:22:11.262581: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /opt/intel/openvino/opencv/lib:/opt/intel/openvino/deployment_tools/ngraph/lib:/opt/intel/opencl:/opt/intel/openvino/deployment_tools/inference_engine/external/hddl/lib:/opt/intel/openvino/deployment_tools/inference_engine/external/gna/lib:/opt/intel/openvino/deployment_tools/inference_engine/external/mkltiny_lnx/lib:/opt/intel/openvino/deployment_tools/inference_engine/external/tbb/lib:/opt/intel/openvino/deployment_tools/inference_engine/lib/intel64:
2021-08-13 14:22:11.262644: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
/usr/local/lib/python3.6/dist-packages/tensorflow/python/autograph/impl/api.py:22: DeprecationWarning: the imp module is deprecated in favour of importlib; see the module's documentation for alternative uses
  import imp
2021-08-13 14:22:16.881597: W tensorflow/core/framework/op_def_util.cc:371] Op BatchNormWithGlobalNormalization is deprecated. It will cease to work in GraphDef version 9. Use tf.nn.batch_normalization().
[ WARNING ]  Failed to parse a tensor with Unicode characters. Note that Inference Engine does not support string literals, so the string constant should be eliminated from the graph.
[ WARNING ]  Failed to parse a tensor with Unicode characters. Note that Inference Engine does not support string literals, so the string constant should be eliminated from the graph.
[ ERROR ]  Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.front.output_cut.OutputCut'>): Graph contains 0 node after executing <class 'extensions.front.output_cut.OutputCut'>. It considered as error because resulting IR will be empty which is not usual

      Thanks again