:orphan:


Image Segmentation
******************

Examples for anomaly segmentation.

The examples in this section depend on ``segmentation-models-pytorch`` which you
can install with:

.. code-block:: shell

    pip install segmentation-models-pytorch



.. raw:: html

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

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="We train a Feature Pyramid Segmentation model with a ResNet-50 backbone pre-trained on the ImageNet on the pytorch_ood.dataset.img.StreetHazards. We then use the pytorch_ood.detector.EnergyBased OOD detector.">

.. only:: html

  .. image:: /auto_examples/segmentation/images/thumb/sphx_glr_street_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_segmentation_street.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">StreetHazards</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="We train a Feature Pyramid Segmentation model with a ResNet-50 backbone pre-trained on the ImageNet on the pytorch_ood.dataset.img.StreetHazards test set using the supervised pytorch_ood.loss.EntropicOpenSetLoss.">

.. only:: html

  .. image:: /auto_examples/segmentation/images/thumb/sphx_glr_street_entropic_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_segmentation_street_entropic.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">StreetHazards with Entropic Loss</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="We train a Feature Pyramid Segmentation model with a ResNet-50 backbone pre-trained on the ImageNet on the pytorch_ood.dataset.img.StreetHazards. During training, we insert random COCO objects as anomalies into the image to regularize the model.">

.. only:: html

  .. image:: /auto_examples/segmentation/images/thumb/sphx_glr_street_coco_transform_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_segmentation_street_coco_transform.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">StreetHazards + COCO objects</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="We train a Feature Pyramid Segmentation model with a ResNet-50 backbone pre-trained on the ImageNet on the pytorch_ood.dataset.img.StreetHazards test set using the supervised pytorch_ood.loss.VOSRegLoss.">

.. only:: html

  .. image:: /auto_examples/segmentation/images/thumb/sphx_glr_street_vos_thumb.png
    :alt:

  :ref:`sphx_glr_auto_examples_segmentation_street_vos.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">StreetHazards with VOS Loss</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/segmentation/street
   /auto_examples/segmentation/street_entropic
   /auto_examples/segmentation/street_coco_transform
   /auto_examples/segmentation/street_vos


.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-gallery

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

      :download:`Download all examples in Python source code: segmentation_python.zip </auto_examples/segmentation/segmentation_python.zip>`

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

      :download:`Download all examples in Jupyter notebooks: segmentation_jupyter.zip </auto_examples/segmentation/segmentation_jupyter.zip>`


.. only:: html

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

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