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

.. only:: html

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

        :ref:`Go to the end <sphx_glr_download_auto_examples_detectors_gradnorm.py>`
        to download the full example code.

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

.. _sphx_glr_auto_examples_detectors_gradnorm.py:


GradNorm
==============================

Running :class:`GradNorm <pytorch_ood.detector.GradNorm>` on CIFAR 10.

.. GENERATED FROM PYTHON SOURCE LINES 8-25

.. code-block:: Python
   :lineno-start: 9


    import logging

    from torch.utils.data import DataLoader
    from torchvision.datasets import CIFAR10

    from pytorch_ood.dataset.img import Textures
    from pytorch_ood.detector import GradNorm
    from pytorch_ood.model import WideResNet
    from pytorch_ood.utils import OODMetrics, ToUnknown, fix_random_seed

    logging.basicConfig(level=logging.INFO)

    fix_random_seed(123)

    device = "cuda"


.. GENERATED FROM PYTHON SOURCE LINES 26-27

Setup preprocessing and data

.. GENERATED FROM PYTHON SOURCE LINES 27-40

.. code-block:: Python
   :lineno-start: 27

    trans = WideResNet.transform_for("cifar10-pt")

    dataset_train = CIFAR10(root="data", train=True, download=True, transform=trans)
    dataset_in_test = CIFAR10(root="data", train=False, download=True, transform=trans)
    dataset_out_test = Textures(
        root="data", download=True, transform=trans, target_transform=ToUnknown()
    )

    train_loader = DataLoader(dataset_train, batch_size=128, shuffle=True, num_workers=10)

    # create data loaders
    test_loader = DataLoader(dataset_in_test + dataset_out_test, batch_size=128, num_workers=10)


.. GENERATED FROM PYTHON SOURCE LINES 41-42

Stage 1: Create DNN pre-trained on CIFAR 10

.. GENERATED FROM PYTHON SOURCE LINES 42-48

.. code-block:: Python
   :lineno-start: 42

    model = WideResNet(num_classes=10, pretrained="cifar10-pt").to(device).eval()

    model.requires_grad_(False)
    model.fc.requires_grad_(True)



.. GENERATED FROM PYTHON SOURCE LINES 49-54

.. code-block:: Python
   :lineno-start: 50


    # Stage 2: Create detector, fitting is not required
    detector = GradNorm(model, param_filter=lambda name: name.startswith("fc"))



.. GENERATED FROM PYTHON SOURCE LINES 55-56

Stage 3: Evaluate Detectors

.. GENERATED FROM PYTHON SOURCE LINES 56-65

.. code-block:: Python
   :lineno-start: 56

    print("Testing...")

    metrics = OODMetrics()
    for x, y in test_loader:
        metrics.update(detector(x.to(device)), y)


    print(metrics.compute())


.. GENERATED FROM PYTHON SOURCE LINES 66-68

This produces the following output:
{'AUROC': 0.4999113380908966, 'AUTC': 0.5440057516098022, 'AUPR-IN': 0.31969308853149414, 'AUPR-OUT': 0.6802297830581665, 'FPR95TPR': 1.0}


.. _sphx_glr_download_auto_examples_detectors_gradnorm.py:

.. only:: html

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

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

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

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

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

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: gradnorm.zip <gradnorm.zip>`


.. only:: html

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

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