Wenwei Zhang ba059611d1
Momentum scheduler (#167)
* track progress of iter&enum

* restore

* add momentum scheduler

* fix small bug

* cyclic scheduler"

* fix bug

* fix second phase's bug

* reformat

* feature (cosine lr): use relative ratio for more flexible scheduler

* Fix (runner): fix bugs in runner

* Refactor (hook): refactor cosing/cyclic LR/momentum hook with unittest

* Clean unnecessary files and reformat

* Fix memory key error when GPU is not avaliable

* Resolve comments

* Do not print momentum in text log

* Change hook register order

* Refactor max_iter

* Fix max_iter bugs in runner

* Enforce target_ratio to be either tuple or float
2020-04-20 01:23:53 +08:00
2020-04-20 01:23:53 +08:00
2020-04-20 01:23:53 +08:00
2019-11-21 23:34:26 +08:00
2020-02-01 10:14:55 +08:00
2019-11-21 23:34:26 +08:00
2020-01-10 13:34:42 +08:00

MMCV
====

.. image:: https://travis-ci.com/open-mmlab/mmcv.svg?branch=master
  :target: https://travis-ci.com/open-mmlab/mmcv

.. image:: https://codecov.io/gh/open-mmlab/mmcv/branch/master/graph/badge.svg
  :target: https://codecov.io/gh/open-mmlab/mmcv

.. image:: 	https://img.shields.io/github/license/open-mmlab/mmcv.svg
  :target: https://github.com/open-mmlab/mmcv/blob/master/LICENSE


Introduction
------------

MMCV is a foundational python library for computer vision research and supports many
research projects in MMLAB, such as `MMDetection <https://github.com/open-mmlab/mmdetection>`_
and `MMAction <https://github.com/open-mmlab/mmaction>`_.

It provides the following functionalities.

- Universal IO APIs
- Image processing
- Video processing
- Image and annotation visualization
- Useful utilities (progress bar, timer, ...)
- PyTorch runner with hooking mechanism
- Various CNN architectures

See the `documentation <http://mmcv.readthedocs.io/en/latest>`_ for more features and usage.

Note: MMCV requires Python 3.5+.


Installation
------------

Try and start with

.. code::

    pip install mmcv


or install from source

.. code::

    git clone https://github.com/open-mmlab/mmcv.git
    cd mmcv
    pip install -e .

Note: If you would like to use :code:`opencv-python-headless` instead of :code:`opencv-python`,
e.g., in a minimum container environment or servers without GUI,
you can first install it before installing MMCV to skip the installation of :code:`opencv-python`.
Description
OpenMMLab Computer Vision Foundation
Readme 42 MiB
Languages
Python 52%
C++ 33.1%
Cuda 14.6%
Objective-C++ 0.2%