}
</style>
<div class="devsite-landing-row-item-description">
- <a href="#">
- <h3 class="hide-from-toc">Learn and use ML</h3>
- </a>
+ <h3 class="hide-from-toc">Learn and use ML</h3>
<div class="devsite-landing-row-item-description-content">
<p>
The high-level Keras API provides building blocks to create and
- items:
- custom_html: >
<div class="devsite-landing-row-item-description" style="border-right: 2px solid #eee;">
- <a href="https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/eager/python/examples/notebooks">
- <h3 class="hide-from-toc">Research and experimentation</h3>
- </a>
+ <h3 class="hide-from-toc">Research and experimentation</h3>
<div class="devsite-landing-row-item-description-content">
<p>
Eager execution provides an imperative, define-by-run interface for advanced operations. Write custom layers, forward passes, and training loops with auto‑differentiation. Start with
</div>
- custom_html: >
<div class="devsite-landing-row-item-description">
- <a href="#">
- <h3 class="hide-from-toc">ML at production scale</h3>
- </a>
+ <h3 class="hide-from-toc">ML at production scale</h3>
<div class="devsite-landing-row-item-description-content">
<p>
Estimators can train large models on multiple machines in a