.. include:: /keyword.rst


===================
Model Visualization
===================

In this section, we will introduce how to use the model visualization tool - `Netron <https://github.com/lutzroeder/netron>`_,
or command line tool ``ncc-tflite`` to view the information of the tensor.

Because the version of NeuronAPI now we support on |IOT-YOCTO| is v5.0.1, 
there is no way for users to insert the meta information of the model when compiling the DLA model.
Also, model metadata cannot be read out using ``NeuronRuntime_getMetadata`` at runtime. 
That is why in :doc:`/sw/yocto/ml-guide/neuron-dev-flow/example_app`, the value of ``scale`` and ``zero_point`` 
in ``ConvertArrayToFixedPoint`` and ``ConvertArrayToFloatingPoint`` are constants.

Users must have a clear understanding of the model information to have the correct implementation for the inference.
We provides kinds of way for user to get useful model information here.


NETRON
------

Following visualized model is as same as what we used in :doc:`/tools/ai-demo-app` - ``mobilenet_ssd_pascal_quant.tflite``,
which can be found in ``/usr/share/gstinference_example/object_detection``.

- After opening the model in `Netron`, users can have a full view on it.

.. figure:: /_asset/sw_yocto_ml-guide_neuron-sdk_neuron-dev-flow_model-visualization_netron-vis.png
    :align: center
    :height: 800px

    Full view of ``mobilenet_ssd_pascal_quant.tflite``
	
.. note::
	Not only Tensorflow Lite, `Netron` supports various frameworks, like ONNX, Caffe, Keras, Darknet ..etc.

- You can see that `Netron` provides a lot of useful information about tensor. For example, the input tensor, ``Preprocessor/sub``, is a 3-channel image of size 300 * 300, and the parameters of quantized field: zero_point is 128 and scale is 0.0078.
	
.. figure:: /_asset/sw_yocto_ml-guide_neuron-sdk_neuron-dev-flow_model-visualization_tensor-info.png
    :align: center
    :height: 600px

    Information for Specific Tensor


`ncc-tflite`
------------

Neuron compiler(``ncc-tflite``) provides simple command-line interface for user to obtain model information.
Following shows some examples of how to use it for model visualization.

- Show input and output tensors of the TFLite model. For example:

.. code-block::

	$ ncc-tflite --show-io-info mobilenet_ssd_pascal_quant.tflite
	
	# of input tensors: 1
	[0]: Preprocessor/sub
	├ Type: kTfLiteUInt8
	├ AllocType: kTfLiteArenaRw
	├ Shape: {1,300,300,3}
	├ Scale: 0.00787402
	├ ZeroPoint: 128
	└ Bytes: 270000
	
	# of output tensors: 2
	[0]: concat_1
	├ Type: kTfLiteUInt8
	├ AllocType: kTfLiteArenaRw
	├ Shape: {1,1917,21}
	├ Scale: 0.141151
	├ ZeroPoint: 159
	└ Bytes: 40257
	[1]: Squeeze
	├ Type: kTfLiteUInt8
	├ AllocType: kTfLiteArenaRw
	├ Shape: {1,1917,4}
	├ Scale: 0.06461
	├ ZeroPoint: 173
	└ Bytes: 7668


- Show tensors and nodes in the TFLite model. For example:

.. code-block::

	$ ncc-tflite --show-tflite mobilenet_ssd_pascal_quant.tflite
	
	Tensors:
	[0]: BoxPredictor_0/BoxEncodingPredictor/BiasAdd
	├ Type: kTfLiteUInt8
	├ AllocType: kTfLiteArenaRw
	├ Shape: {1,19,19,12}
	├ Scale: 0.06461
	├ ZeroPoint: 173
	└ Bytes: 4332
	[1]: BoxPredictor_0/BoxEncodingPredictor/Conv2D_bias
	├ Type: kTfLiteInt32
	├ AllocType: kTfLiteMmapRo
	├ Shape: {12}
	├ Scale: 7.66586e-05
	├ ZeroPoint: 0
	└ Bytes: 48
	[2]: BoxPredictor_0/BoxEncodingPredictor/weights_quant/FakeQuantWithMinMaxVars
	├ Type: kTfLiteUInt8
	├ AllocType: kTfLiteMmapRo
	├ Shape: {12,1,1,512}
	├ Scale: 0.00325812
	├ ZeroPoint: 132
	└ Bytes: 6144
	
	...

.. Note::

	For the details of ``ncc-tflite``. Please refer to :ref:`Neuron Compiler section <ml_neuron-compiler>`.