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

.. only:: html

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

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

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

.. _sphx_glr_usage_examples_flow_plot_animated_reveal_flow.py:

Animated Reveal
=======================================

``visualtorch.animate(style="flow")`` renders the same diagram as ``style="flow"`` in
``visualtorch.render()``, but as an animated GIF that reveals the model one column (depth level)
at a time instead of all at once. Parallel branches at the same depth reveal together, in the
same frame, correctly implying they happen simultaneously - a skip connection stays hidden until
its merge point is reached, then draws in exactly as it would in the static image.

The model here is the same residual block used elsewhere in this gallery, since a merge point is
the most interesting thing to watch animate in.

.. raw:: html

    <img src="../../_static/images/animations/flow_animated_demo.gif" alt="Animated flow_view reveal" width="600">

.. GENERATED FROM PYTHON SOURCE LINES 17-51







.. code-block:: Python


    # sphinx_gallery_thumbnail_path = '_static/images/animations/flow_animated_demo_thumbnail.png'

    import torch
    import visualtorch
    from torch import nn


    class ResidualBlock(nn.Module):
        """A classic ResNet-style block with a plain identity shortcut."""

        def __init__(self, channels: int) -> None:
            super().__init__()
            self.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
            self.bn1 = nn.BatchNorm2d(channels)
            self.relu = nn.ReLU()
            self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
            self.bn2 = nn.BatchNorm2d(channels)

        def forward(self, x: torch.Tensor) -> torch.Tensor:
            """Define the forward pass, with a skip connection around conv1/bn1/relu/conv2/bn2."""
            identity = x
            out = self.relu(self.bn1(self.conv1(x)))
            out = self.bn2(self.conv2(out))
            out = out + identity
            return self.relu(out)


    model = ResidualBlock(channels=8)
    input_shape = (1, 8, 16, 16)

    # Returns a list[Image.Image], one per column, in reveal order - pass to_file="your_path.gif" to
    # save it directly as an animated GIF instead.
    frames = visualtorch.animate(model, input_shape, style="flow", scale_xy=3)


.. _sphx_glr_download_usage_examples_flow_plot_animated_reveal_flow.py:

.. only:: html

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

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

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

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

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

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

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


.. only:: html

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

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