.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "dynamics/neuralnet_tutorial.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        Click :ref:`here <sphx_glr_download_dynamics_neuralnet_tutorial.py>`
        to download the full example code

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_dynamics_neuralnet_tutorial.py:


NeuralNet Tutorial
==================

.. GENERATED FROM PYTHON SOURCE LINES 6-12

.. code-block:: default


    from pypose.module.dynamics import System
    import torch as torch
    import matplotlib.pyplot as plt
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")








.. GENERATED FROM PYTHON SOURCE LINES 13-15

Preparation
-----------

.. GENERATED FROM PYTHON SOURCE LINES 15-40

.. code-block:: default


    class nnDynamics(System):
        def __init__(self, hiddenSize):
            super().__init__()
            self.net = torch.nn.Sequential(
                torch.nn.Linear(2, hiddenSize[0]),
                torch.nn.ReLU(),
                torch.nn.Linear(hiddenSize[0], hiddenSize[1]),
                torch.nn.ReLU(),
                torch.nn.Linear(hiddenSize[1], 2))
    
        def state_transition(self, state, input, t=None):
            return self.net(state) + input
    
        def observation(self, state, input, t=None):
            return state

    def createTimePlot(x, y, figname="Un-named plot", title=None, xlabel=None, ylabel=None):
        f = plt.figure(figname)
        plt.plot(x, y)
        plt.xlabel(xlabel)
        plt.ylabel(ylabel)
        plt.title(title)
        return f








.. GENERATED FROM PYTHON SOURCE LINES 41-42

Time Step

.. GENERATED FROM PYTHON SOURCE LINES 42-46

.. code-block:: default


    dt = 0.01  # Time step size
    N  = 1000  # Number of time steps








.. GENERATED FROM PYTHON SOURCE LINES 47-48

Time and input

.. GENERATED FROM PYTHON SOURCE LINES 48-52

.. code-block:: default


    time  = torch.arange(0, N + 1) * dt
    input = torch.sin(time)








.. GENERATED FROM PYTHON SOURCE LINES 53-54

Initial state

.. GENERATED FROM PYTHON SOURCE LINES 54-57

.. code-block:: default


    state = torch.tensor([0,0])








.. GENERATED FROM PYTHON SOURCE LINES 58-59

Create solver object

.. GENERATED FROM PYTHON SOURCE LINES 59-62

.. code-block:: default


    nnSolver = nnDynamics([5, 10])








.. GENERATED FROM PYTHON SOURCE LINES 63-64

Calculate trajectory

.. GENERATED FROM PYTHON SOURCE LINES 64-71

.. code-block:: default


    state_all = torch.zeros(N + 1, 2)
    state_all[0,:] = state
    for i in range(N):
        state_all[i+1], _ = nnSolver.forward(state_all[i], input[i])









.. GENERATED FROM PYTHON SOURCE LINES 72-73

Create plots

.. GENERATED FROM PYTHON SOURCE LINES 73-80

.. code-block:: default


    x, y = (state_all.T).detach().numpy()
    x_fig = createTimePlot(time, x, figname="x Plot", xlabel="Time", ylabel="x", title="x Plot")
    y_fig = createTimePlot(time, y, figname="y Plot", xlabel="Time", ylabel="y", title="y Plot")

    # torch.save([state_all], 'nn_dynamics_data.pt')

    plt.show()


.. rst-class:: sphx-glr-horizontal


    *

      .. image-sg:: /dynamics/images/sphx_glr_neuralnet_tutorial_001.png
         :alt: x Plot
         :srcset: /dynamics/images/sphx_glr_neuralnet_tutorial_001.png
         :class: sphx-glr-multi-img

    *

      .. image-sg:: /dynamics/images/sphx_glr_neuralnet_tutorial_002.png
         :alt: y Plot
         :srcset: /dynamics/images/sphx_glr_neuralnet_tutorial_002.png
         :class: sphx-glr-multi-img






.. rst-class:: sphx-glr-timing

   **Total running time of the script:** ( 0 minutes  0.126 seconds)


.. _sphx_glr_download_dynamics_neuralnet_tutorial.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example


    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: neuralnet_tutorial.py <neuralnet_tutorial.py>`

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: neuralnet_tutorial.ipynb <neuralnet_tutorial.ipynb>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_