.. ENOT framework documentation master file.

################
ENOT User Manual
################


****************************************
Embedded Network Optimization Technology
****************************************

ENOT, or Embedded Network Optimization Technology, is a flexible tool for Deep
Learning developers which automates neural architecture optimization. It can be
useful in the following scenarios:

1) Target metric maximization (e.g., classification accuracy or intersection
   over union);
2) Target metric maximization with constrained computational resources (e.g.,
   RAM, latency);
3) Pareto frontier (latency vs target metric) search.

Framework advantages:

1) Controlled ratio between latency and network performance;
2) Networks in the pre-trained search space can exceed their stand-alone
   variants (in some scenarios);
3) Compatibility with almost any DL task and simple integration with the
   existing training pipelines.

Before reading the documentation, we recommend you to look at the
:ref:`ENOT Tutorials` to clarify basic notions and concepts of the framework.

Other ENOT LLC products:

* `enot-lite <https://enot-lite.rtd.enot.ai/en/latest/>`_ for easy-to-use
  inference on CPUs and NVIDIA GPUs.
* `enot_yolov5 <https://github.com/ENOT-AutoDL/enot_yolov5>`_ - ENOT framework
  integration into `YOLOv5`_ for Neural Architecture Search of YOLOv5-like
  models.
* `mmdetection-enot <https://github.com/ENOT-AutoDL/mmdetection-enot>`_ - ENOT
  framework integration into `MMDetection`_ for Neural Architecture Search.

.. _YOLOv5: https://github.com/ultralytics/yolov5
.. _MMDetection: https://github.com/open-mmlab/mmdetection


*****************
Table of contents
*****************

.. toctree::
   :maxdepth: 1

   Installation <installation_guide>
   Reference Documentation <reference_documentation/index>
   Tutorials <tutorials>
   OpenMMLab Integration <openmmlab/mmenot>
   ENOT Latency server <latency_server>
   ENOT Prunable Modules <prunable_modules>