.. _l-modules:

Modules
=======

.. contents::
    :local:
    :depth: 1


Summary
+++++++

+-----------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| module                            | truncated documentation                                                                                                                                                                                                                                                                                                                                                                                  |
+===================================+==========================================================================================================================================================================================================================================================================================================================================================================================================+
| :ref:`__init__ <f-init>`          | module ``ensae_teaching_dl``    Around :epkg:`deep learning`.      :githublink:`%|py|6`                                                                                                                                                                                                                                                                                                                  |
+-----------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| :ref:`faq_gpu <f-faqgpu>`         | module ``ensae_teaching_dl.faq.faq_gpu``    A few functions about :epkg:`GPU`.      :githublink:`%|py|6`                                                                                                                                                                                                                                                                                                 |
+-----------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| :ref:`keras_mnist <f-kerasmnist>` | module ``ensae_teaching_dl.examples.keras_mnist``    Taken from `mnist_cnn.py <https://github.com/fchollet/keras/blob/master/examples/mnist_cnn.py>`_.    Trains a simple convolution network on the :epkg:`MNIST` dataset.    Gets to 99.25% test accuracy after 12 epochs  (there is still a lot of margin for parameter tuning).  16 seconds per epoch on a GRID K520 GPU.      :githublink:`%|py|11` |
+-----------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+


.. toctree::
    :maxdepth: 1

    ensae_teaching_dl/__init__
    ensae_teaching_dl/examples/keras_mnist
    ensae_teaching_dl/faq/faq_gpu