:orphan:

Tutorials
=========

This series of tutorials should guide you through the use of the SPyRiT pipeline.

.. figure:: ../fig/direct_net.png
   :width: 600
   :align: center
   :alt: SPyRiT pipeline

|

Each tutorial focuses on a specific submodule of the full pipeline.

* :ref:`Tutorial 1 <sphx_glr_gallery_tuto_01_a_acquisition_operators.py>`.a introduces the basics of measurement operators.

* :ref:`Tutorial 1 <sphx_glr_gallery_tuto_01_b_splitting.py>`.b introduces the splitting of measurement operators.

* :ref:`Tutorial 1 <sphx_glr_gallery_tuto_01_c_HadamSplit2d.py>`.c introduces the 2d Hadamard transform with subsampling.

* :ref:`Tutorial 2 <sphx_glr_gallery_tuto_02_noise.py>` introduces the noise operators.

* :ref:`Tutorial 3 <sphx_glr_gallery_tuto_03_pseudoinverse_linear.py>` demonstrates pseudo-inverse reconstructions from Hadamard measurements.

* :ref:`Tutorial 4 <sphx_glr_gallery_tuto_04_pseudoinverse_cnn_linear.py>`.a introduces data-driven post-processing reconstruction.

* :ref:`Tutorial 4 <sphx_glr_gallery_tuto_04_b_train_pseudoinverse_cnn_linear.py>`.b trains the post-processing CNN used in :ref:`Tutorial 4 <sphx_glr_gallery_tuto_04_pseudoinverse_cnn_linear.py>`.a.

* :ref:`Tutorial 5 <sphx_glr_gallery_tuto_05_dcnet.py>` introduces the denoised completion network for the reconstruction of Poisson-corrupted subsampled measurements.

.. note::

  The Python script (*.py*) or Jupyter notebook (*.ipynb*) corresponding to each tutorial can be downloaded at the bottom of the page. The images used in these files can be found on `GitHub`_.

The tutorials below will gradually be updated to be compatible with SPyRiT 3 (work in progress, in the meantime see SPyRiT `2.4.0`_).


* :ref:`Tutorial 6 <sphx_glr_gallery_tuto_06_dcnet_split_measurements.py>` uses a Denoised Completion Network with a trainable image denoiser to improve the results obtained in Tutorial 5

* :ref:`Tutorial 7 <sphx_glr_gallery_tuto_07_drunet_split_measurements.py>` shows how to perform image reconstruction using a pretrained plug-and-play denoising network.

* :ref:`Tutorial 8 <sphx_glr_gallery_tuto_08_lpgd_split_measurements.py>` shows how to perform image reconstruction using a learnt proximal gradient descent.

* :ref:`Tutorial 9 <sphx_glr_gallery_tuto_09_dynamic.py>` explains motion simulation from an image, dynamic measurements and reconstruction.

.. _GitHub: https://github.com/openspyrit/spyrit/tree/3895b5e61fb6d522cff5e8b32a36da89b807b081/tutorial/images/test

.. _2.4.0: https://spyrit.readthedocs.io/en/2.4.0/gallery/index.html



.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This tutorial shows how to simulate measurements using the spyrit.core.meas submodule.">

.. only:: html

  .. image:: /gallery/images/thumb/sphx_glr_tuto_01_a_acquisition_operators_thumb.png
    :alt:

  :doc:`/gallery/tuto_01_a_acquisition_operators`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">01.a. Acquisition operators (basic)</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This tutorial shows how to simulate linear measurements by splitting an acquisition matrix H\in \mathbb{R}^{M\times N} that contains negative values.  It based on the spyrit.core.meas.LinearSplit class of the spyrit.core.meas submodule.">

.. only:: html

  .. image:: /gallery/images/thumb/sphx_glr_tuto_01_b_splitting_thumb.png
    :alt:

  :doc:`/gallery/tuto_01_b_splitting`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">01.b. Acquisition operators (splitting)</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This tutorial shows how to simulate measurements that correspond to the 2D Hadamard transform of an image.  It based on the spyrit.core.meas.HadamSplit2d class of the spyrit.core.meas submodule.">

.. only:: html

  .. image:: /gallery/images/thumb/sphx_glr_tuto_01_c_HadamSplit2d_thumb.png
    :alt:

  :doc:`/gallery/tuto_01_c_HadamSplit2d`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">01.c. Acquisition operators (HadamSplit2d)</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This tutorial shows how to use noise operators using the spyrit.core.noise submodule.">

.. only:: html

  .. image:: /gallery/images/thumb/sphx_glr_tuto_02_noise_thumb.png
    :alt:

  :doc:`/gallery/tuto_02_noise`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">02. Noise operators</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This tutorial shows how to simulate measurements and perform image reconstruction using the spyrit.core.inverse.PseudoInverse class of the spyrit.core.inverse submodule.">

.. only:: html

  .. image:: /gallery/images/thumb/sphx_glr_tuto_03_pseudoinverse_linear_thumb.png
    :alt:

  :doc:`/gallery/tuto_03_pseudoinverse_linear`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">03. Pseudoinverse solution from linear measurements</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This tutorial shows how to simulate measurements and perform image reconstruction using the spyrit.core.recon.PinvNet class of the spyrit.core.recon submodule.">

.. only:: html

  .. image:: /gallery/images/thumb/sphx_glr_tuto_04_pseudoinverse_cnn_linear_thumb.png
    :alt:

  :doc:`/gallery/tuto_04_pseudoinverse_cnn_linear`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">04.a. Pseudoinverse + CNN (reconstruction)</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This tutorial trains a post processing CNN used by a spyrit.core.recon.PinvNet (see the previous tutorial &lt;tuto_04_pseudoinverse_cnn_linear&gt;).">

.. only:: html

  .. image:: /gallery/images/thumb/sphx_glr_tuto_04_b_train_pseudoinverse_cnn_linear_thumb.png
    :alt:

  :doc:`/gallery/tuto_04_b_train_pseudoinverse_cnn_linear`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">04.b. Pseudoinverse + CNN (training)</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This tutorial shows how to perform image reconstruction using a denoised completion network (DC-Net) [1]_ with a trainable image denoiser.">

.. only:: html

  .. image:: /gallery/images/thumb/sphx_glr_tuto_05_dcnet_thumb.png
    :alt:

  :doc:`/gallery/tuto_05_dcnet`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">05. Denoised Completion Network (DC-Net)</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /gallery/tuto_01_a_acquisition_operators
   /gallery/tuto_01_b_splitting
   /gallery/tuto_01_c_HadamSplit2d
   /gallery/tuto_02_noise
   /gallery/tuto_03_pseudoinverse_linear
   /gallery/tuto_04_pseudoinverse_cnn_linear
   /gallery/tuto_04_b_train_pseudoinverse_cnn_linear
   /gallery/tuto_05_dcnet



.. only:: html

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

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