@Matt-Turi I wanted to try the resnet architecture as the accuracy/speed ratio is a bit better than the mobilenet architecture. But it's not a hard requirement, so I'll just use the mobilenet architectures. Thanks!

@Matt-Turi Any update?

@Matt-Turi Yep, looks like 'image_tensor' and 'detection_classes' are the input and outputs names, respectively.

converter =  tf.compat.v1.lite.TFLiteConverter.from_frozen_graph(
    graph_def_file = 'faster_rcnn_resnet101_coco_2018_01_28/frozen_inference_graph.pb', 
    input_arrays = ['image_tensor'],
    input_shapes={'image_tensor': [1,300,300,3]},
    output_arrays = ['detection_classes'] 
  )

  converter.use_experimental_new_converter = True
  converter.allow_custom_ops = True
  converter.target_spec.supported_types = [tf.float16]
  tflite_model = converter.convert()

  # Save the model.
  with open('custom_model.tflite', 'wb') as f:
    f.write(tflite_model)

When I run the code now, I get the following:

(tflite_env) stevearias@Steves-Macbook-Pro tflite_env % python3 convert_to_tflite_model.py
2022-02-14 14:41:58.792670: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2022-02-14 14:41:58.827082: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f9606206700 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2022-02-14 14:41:58.827104: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
Traceback (most recent call last):
  File "convert_to_tflite_model.py", line 22, in <module>
    main()
  File "convert_to_tflite_model.py", line 14, in main
    tflite_model = converter.convert()
  File "/Users/stevearias/Documents/src/ece-498-repo/python-scripts/tflite_env/tflite_env/lib/python3.7/site-packages/tensorflow/lite/python/lite.py", line 1084, in convert
    **converter_kwargs)
  File "/Users/stevearias/Documents/src/ece-498-repo/python-scripts/tflite_env/tflite_env/lib/python3.7/site-packages/tensorflow/lite/python/convert.py", line 496, in toco_convert_impl
    enable_mlir_converter=enable_mlir_converter)
  File "/Users/stevearias/Documents/src/ece-498-repo/python-scripts/tflite_env/tflite_env/lib/python3.7/site-packages/tensorflow/lite/python/convert.py", line 227, in toco_convert_protos
    raise ConverterError("See console for info.\n%s\n%s\n" % (stdout, stderr))
tensorflow.lite.python.convert.ConverterError: See console for info.
2022-02-14 14:42:07.697347: W tensorflow/compiler/mlir/lite/python/graphdef_to_tfl_flatbuffer.cc:144] Ignored output_format.
2022-02-14 14:42:07.697406: W tensorflow/compiler/mlir/lite/python/graphdef_to_tfl_flatbuffer.cc:147] Ignored drop_control_dependency.
Traceback (most recent call last):
  File "/Users/stevearias/Documents/src/ece-498-repo/python-scripts/tflite_env/tflite_env/bin/toco_from_protos", line 8, in <module>
    sys.exit(main())
  File "/Users/stevearias/Documents/src/ece-498-repo/python-scripts/tflite_env/tflite_env/lib/python3.7/site-packages/tensorflow/lite/toco/python/toco_from_protos.py", line 93, in main
    app.run(main=execute, argv=[sys.argv[0]] + unparsed)
  File "/Users/stevearias/Documents/src/ece-498-repo/python-scripts/tflite_env/tflite_env/lib/python3.7/site-packages/tensorflow/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/Users/stevearias/Documents/src/ece-498-repo/python-scripts/tflite_env/tflite_env/lib/python3.7/site-packages/absl/app.py", line 312, in run
    _run_main(main, args)
  File "/Users/stevearias/Documents/src/ece-498-repo/python-scripts/tflite_env/tflite_env/lib/python3.7/site-packages/absl/app.py", line 258, in _run_main
    sys.exit(main(argv))
  File "/Users/stevearias/Documents/src/ece-498-repo/python-scripts/tflite_env/tflite_env/lib/python3.7/site-packages/tensorflow/lite/toco/python/toco_from_protos.py", line 56, in execute
    enable_mlir_converter)
Exception: Merge of two inputs that differ on more than one predicate {s(SecondStagePostprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/Greater:0,else), s(SecondStagePostprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/cond/cond/pred_id/_564__cf__570:0,then), s(SecondStagePostprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/cond/Greater/_563__cf__569:0,then)} and {s(SecondStagePostprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/Greater:0,else), s(SecondStagePostprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/cond/cond/pred_id/_564__cf__570:0,else), s(SecondStagePostprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/cond/Greater/_563__cf__569:0,else)}
	for node {{node SecondStagePostprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/cond/cond/Merge}}

Any idea on what the issue is?

I made a virtualenv environment which has Python3.7 and Tensorflow (version 2.2.3). I am trying to convert the faster_rcnn_resnet101_coco model (labelled as "faster_rcnn_resnet101_coco" in https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf1_detection_zoo.md) to a tflite model so that I can put it on the board and run via voxl-tflite-server. I have read the documentation on the voxl-tflite-server. I understand that quantization will allow GPU support for the model. Here's what my conversion code looks like so far:

  converter =  tf.compat.v1.lite.TFLiteConverter.from_frozen_graph(
    graph_def_file = 'faster_rcnn_resnet101_coco_2018_01_28/frozen_inference_graph.pb', 
    input_arrays = ['normalized_input_image_tensor'],
    input_shapes={'normalized_input_image_tensor': [1,300,300,3]},
    output_arrays = ['TFLite_Detection_PostProcess', 'TFLite_Detection_PostProcess:1', 'TFLite_Detection_PostProcess:2', 'TFLite_Detection_PostProcess:3'] 
  )

  converter.use_experimental_new_converter = True
  converter.allow_custom_ops = True
  converter.target_spec.supported_types = [tf.float16]
  tflite_model = converter.convert()

  # Save the model.
  with open('custom_model.tflite', 'wb') as f:
    f.write(tflite_model)

I get the following output:

(tflite_env) stevearias@Steves-Macbook-Pro tflite_env % python3 convert_to_tflite_model.py
2022-02-12 19:48:02.033093: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2022-02-12 19:48:02.071654: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f925aaec760 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2022-02-12 19:48:02.071679: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
Traceback (most recent call last):
  File "convert_to_tflite_model.py", line 22, in <module>
    main()
  File "convert_to_tflite_model.py", line 8, in main
    output_arrays = ['TFLite_Detection_PostProcess', 'TFLite_Detection_PostProcess:1', 'TFLite_Detection_PostProcess:2', 'TFLite_Detection_PostProcess:3'] 
  File "/Users/stevearias/Documents/src/ece-498-repo/python-scripts/tflite_env/tflite_env/lib/python3.7/site-packages/tensorflow/lite/python/lite.py", line 780, in from_frozen_graph
    sess.graph, input_arrays)
  File "/Users/stevearias/Documents/src/ece-498-repo/python-scripts/tflite_env/tflite_env/lib/python3.7/site-packages/tensorflow/lite/python/util.py", line 128, in get_tensors_from_tensor_names
    ",".join(invalid_tensors)))
ValueError: Invalid tensors 'normalized_input_image_tensor' were found.

Did you encounter this error when trying to convert the ssdlite_mobilenet_v2_coco model to a tflite model?

@James-Strawson thanks for the suggestions!

I've forked libmodal_pipe (https://gitlab.com/SteveArias1/libmodal_pipe) and have made changes to this forked repo. I have generated and installed an ipk package of this custom libmodal_pipe via voxl-docker -i voxl-cross and the other usual commands that follow (./install_build_deps.sh stable, etc.). I'm able to install this custom version of libmodal_pipe on the VOXL board. It's running this custom libmodal_pipe on the board as we speak..

I've made a new MPA service that uses libmodal_pipe. I've been using voxl-docker to build and install this service to the VOXL board. Specifically, I use the voxl-cross docker image and run a custom ./install_build_deps.sh script which downloads libmodal_pipe, libmodal_json and voxl-mavlink from the stable opkg repo (http://voxl-packages.modalai.com/stable).

I want to use a custom function that I made in the custom libmodal_pipe library in my MPA service. How can I use the custom libmodal_pipe library that I have? I can't use opkg to get it since the stable repo only has the stable ipk packages that ModalAI provides by default.

I want to use the boost C++ library (https://www.boost.org/) on one of the MPA services (voxl-tflite-server, https://gitlab.com/voxl-public/modal-pipe-architecture/voxl-tflite-server). I read a post where someone was trying to use apt-get functionality, where the answer was to look at the documentation on running Ubuntu on VOXL (https://docs.modalai.com/docker-on-voxl/). I have been developing on VOXL by doing the following dev flow:

• Make changes on local PC running Ubuntu
• Run voxl-docker -i voxl-cross on PC which runs the voxl-cross docker image
• In docker image:
  • Run ./install_build_deps.sh stable which installs the dependencies of the MPA service via opkg
  • Build via ./build.sh
  • Make ipk package via ./make_package.sh
  • Exit docker image
• Run install_on_voxl.sh which pushes ipk package to VOXL board via ADB and installs it via opkg

Do I need to create my own custom docker image that has boost installed on it, or can I install boost on my voxl-cross docker image?

This is what I get on voxl-portal.

It looks like the preview for hires is enabled.

I'm asking because voxl-tflite-server isn't receiving any camera frames. It used to work fine since hires was up and running. But for some reason, hires is gone and I don't know how to start it up again.

I see that hires_preview is running but not hires. How do I start up hires?