build(deps): bump keras from 3.1.1 to 3.2.0 (#6)

Bumps [keras](https://github.com/keras-team/keras) from 3.1.1 to 3.2.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/keras-team/keras/releases">keras's
releases</a>.</em></p>
<blockquote>
<h2>Keras 3.2.0</h2>
<h2>What changed</h2>
<ul>
<li>Introduce QLoRA-like technique for LoRA fine-tuning of
<code>Dense</code> and <code>EinsumDense</code> layers (thereby any LLM)
in int8 precision.</li>
<li>Extend <code>keras.ops.custom_gradient</code> support to
PyTorch.</li>
<li>Add <code>keras.layers.JaxLayer</code> and
<code>keras.layers.FlaxLayer</code> to wrap JAX/Flax modules as Keras
layers.</li>
<li>Allow <code>save_model</code> &amp; <code>load_model</code> to
accept a file-like object.</li>
<li>Add quantization support to the <code>Embedding</code> layer.</li>
<li>Make it possible to update metrics inside a custom
<code>compute_loss</code> method with all backends.</li>
<li>Make it possible to access <code>self.losses</code> inside a custom
<code>compute_loss</code> method with the JAX backend.</li>
<li>Add <code>keras.losses.Dice</code> loss.</li>
<li>Add <code>keras.ops.correlate</code>.</li>
<li>Make it possible to use cuDNN LSTM &amp; GRU with a mask with the
TensorFlow backend.</li>
<li>Better JAX support in <code>model.export()</code>: add support for
aliases, finer control over <code>jax2tf</code> options, and dynamic
batch shapes.</li>
<li>Bug fixes and performance improvements.</li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a
href="https://github.com/abhaskumarsinha"><code>@​abhaskumarsinha</code></a>
made their first contribution in <a
href="https://redirect.github.com/keras-team/keras/pull/19302">keras-team/keras#19302</a></li>
<li><a href="https://github.com/qaqland"><code>@​qaqland</code></a> made
their first contribution in <a
href="https://redirect.github.com/keras-team/keras/pull/19378">keras-team/keras#19378</a></li>
<li><a href="https://github.com/tvogel"><code>@​tvogel</code></a> made
their first contribution in <a
href="https://redirect.github.com/keras-team/keras/pull/19310">keras-team/keras#19310</a></li>
<li><a
href="https://github.com/lpizzinidev"><code>@​lpizzinidev</code></a>
made their first contribution in <a
href="https://redirect.github.com/keras-team/keras/pull/19409">keras-team/keras#19409</a></li>
<li><a href="https://github.com/Murhaf"><code>@​Murhaf</code></a> made
their first contribution in <a
href="https://redirect.github.com/keras-team/keras/pull/19444">keras-team/keras#19444</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/keras-team/keras/compare/v3.1.1...v3.2.0">https://github.com/keras-team/keras/compare/v3.1.1...v3.2.0</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/keras-team/keras/commit/f77b020e497a353b644df3aeebc97c831c8057fc"><code>f77b020</code></a>
Fix code style.</li>
<li><a
href="https://github.com/keras-team/keras/commit/b37be22bb1fa39816cf7751fc95de5ea9c3dbf19"><code>b37be22</code></a>
Unify behavior of self.losses in compute_loss across backends.</li>
<li><a
href="https://github.com/keras-team/keras/commit/04cad40272cb4cf6d754b9abc699bdd90971edca"><code>04cad40</code></a>
Only rely on CudnnRNNV3 in TF</li>
<li><a
href="https://github.com/keras-team/keras/commit/b01bb52936945d8518b655f2f826334c3352b308"><code>b01bb52</code></a>
Add support for dynamic dimensions with model export. (<a
href="https://redirect.github.com/keras-team/keras/issues/19462">#19462</a>)</li>
<li><a
href="https://github.com/keras-team/keras/commit/804f1289626398ebaef663021a2cd67aa3be5f23"><code>804f128</code></a>
Fix dtype issues in <code>keras.random</code> (<a
href="https://redirect.github.com/keras-team/keras/issues/19459">#19459</a>)</li>
<li><a
href="https://github.com/keras-team/keras/commit/68e0368c680decbc7c9e1da57b56b3a8212b3ec2"><code>68e0368</code></a>
Fix error msg</li>
<li><a
href="https://github.com/keras-team/keras/commit/5dd801a1577919a6457a376c04b4183410a751fb"><code>5dd801a</code></a>
Fix CI</li>
<li><a
href="https://github.com/keras-team/keras/commit/c2733bfa96bc2666f9f214a2e7eed6cb8a5576f4"><code>c2733bf</code></a>
Refactor testing logic</li>
<li><a
href="https://github.com/keras-team/keras/commit/a48c46182a6a01efc660d65d3e0606053fc96097"><code>a48c461</code></a>
skip test on tf</li>
<li><a
href="https://github.com/keras-team/keras/commit/4dd458bf45ff53e2c02935ea89a9525b2892173d"><code>4dd458b</code></a>
Add test files for <code>keras/datasets</code> (<a
href="https://redirect.github.com/keras-team/keras/issues/19447">#19447</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/keras-team/keras/compare/v3.1.1...v3.2.0">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=keras&package-manager=pip&previous-version=3.1.1&new-version=3.2.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

Author: dependabot[bot]

requirements.txt

@@ -1,6 +1,6 @@
 h5py == 3.10.0
 jupyter == 1.0.0
-keras == 3.1.1
+keras == 3.2.0
 matplotlib == 3.8.4
 notebook == 7.1.2
 numpy == 1.26.4