diff --git a/README.md b/README.md index 3defc42..db1be12 100644 --- a/README.md +++ b/README.md @@ -4,8 +4,8 @@ OpenL3 is an open-source Python library for computing deep audio and image embed [![PyPI](https://img.shields.io/badge/python-2.7%2C%203.5%2C%203.6-blue.svg)](https://pypi.python.org/pypi/openl3) [![MIT license](https://img.shields.io/badge/License-MIT-blue.svg)](https://choosealicense.com/licenses/mit/) -[![Build Status](https://travis-ci.org/marl/openl3.svg?branch=master)](https://travis-ci.org/marl/openl3) -[![Coverage Status](https://coveralls.io/repos/github/marl/openl3/badge.svg?branch=master)](https://coveralls.io/github/marl/openl3?branch=master) +[![Build Status](https://travis-ci.com/marl/openl3.svg?branch=main)](https://travis-ci.com/marl/openl3) +[![Coverage Status](https://coveralls.io/repos/github/marl/openl3/badge.svg?branch=main)](https://coveralls.io/github/marl/openl3?branch=main) [![Documentation Status](https://readthedocs.org/projects/openl3/badge/?version=latest)](http://openl3.readthedocs.io/en/latest/?badge=latest) Please refer to the [documentation](https://openl3.readthedocs.io/en/latest/) for detailed instructions and examples. @@ -69,11 +69,11 @@ if needed. To install OpenL3 using ``pip``, simply run To install the latest version of OpenL3 from source: -1. Clone or pull the lastest version: +1. Clone or pull the latest version, only retrieving the ``main`` branch to avoid downloading the branch where we store the model weight files (these will be properly downloaded during installation). - git clone git@github.com:marl/openl3.git + git clone git@github.com:marl/openl3.git --branch main --single-branch -2. Install using pip to handle python dependencies: +2. Install using pip to handle python dependencies. The installation also downloads model files, **which requires a stable network connection**. cd openl3 pip install -e . diff --git a/docs/changes.rst b/docs/changes.rst index afb2a2c..70ca731 100644 --- a/docs/changes.rst +++ b/docs/changes.rst @@ -3,6 +3,19 @@ Changelog --------- +v0.4.2 +~~~~~~ + - Fix incorrect embedding_size in ``load_image_embedding_model`` docstring + - Add ``tensorflow.keras`` mock modules to ``docs/conf.py`` to fix docs build + - Remove pin on ``sphinx`` version + +v0.4.1 +~~~~~~ + - Add librosa as an explicit dependency + - Remove upper limit pinning for scikit-image dependency + - Fix version number typo in README + - Update TensorFlow information in README + v0.4.0 ~~~~~~ - Upgraded to `tensorflow>=2.0.0`. Tensorflow is now included as a dependency because of dual CPU-GPU support. @@ -22,30 +35,30 @@ v0.4.0 v0.3.1 ~~~~~~ -- Require `keras>=2.0.9,<2.3.0` in dependencies to avoid force installation of TF 2.x during pip installation. -- Update README and installation docs to explicitly state that we do not yet support TF 2.x and to offer a working dependency combination. -- Require `kapre==0.1.4` in dependencies to avoid installing `tensorflow>=1.14` which break regression tests. + - Require `keras>=2.0.9,<2.3.0` in dependencies to avoid force installation of TF 2.x during pip installation. + - Update README and installation docs to explicitly state that we do not yet support TF 2.x and to offer a working dependency combination. + - Require `kapre==0.1.4` in dependencies to avoid installing `tensorflow>=1.14` which break regression tests. v0.3.0 ~~~~~~ -- Rename audio related embedding functions to indicate that they are specific to audio. -- Add image embedding functionality to API and CLI. -- Add video processing functionality to API and CLI. -- Add batch processing functionality to API and CLI to more efficiently process multiple inputs. -- Update documentation with new functionality. -- Address build issues with updated dependencies. + - Rename audio related embedding functions to indicate that they are specific to audio. + - Add image embedding functionality to API and CLI. + - Add video processing functionality to API and CLI. + - Add batch processing functionality to API and CLI to more efficiently process multiple inputs. + - Update documentation with new functionality. + - Address build issues with updated dependencies. v0.2.0 ~~~~~~ -- Update embedding models with ones that have been trained with the kapre bug fixed. -- Allow loaded models to be passed in and used in `process_file` and `get_embedding`. -- Rename `get_embedding_model` to `load_embedding_model`. + - Update embedding models with ones that have been trained with the kapre bug fixed. + - Allow loaded models to be passed in and used in `process_file` and `get_embedding`. + - Rename `get_embedding_model` to `load_embedding_model`. v0.1.1 ~~~~~~ -- Update kapre to fix issue with dynamic range normalization for decibel computation when computing spectrograms. + - Update kapre to fix issue with dynamic range normalization for decibel computation when computing spectrograms. v0.1.0 ~~~~~~ -- First release. + - First release. diff --git a/docs/conf.py b/docs/conf.py index 0408eb9..80f753c 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -27,8 +27,8 @@ # -- Project information ----------------------------------------------------- project = 'OpenL3' -copyright = '2018, Jason Cramer, Ho-Hsiang Wu, and Justin Salamon' -author = 'Jason Cramer, Ho-Hsiang Wu, and Justin Salamon' +copyright = '2018-2021, Aurora Cramer, Ho-Hsiang Wu, Bea Steers, and Justin Salamon' +author = 'Aurora Cramer, Ho-Hsiang Wu, Bea Steers, and Justin Salamon' # -- Mock dependencies @@ -44,8 +44,9 @@ def getattr(cls, name): MOCK_MODULES = [ 'numpy', 'soundfile', 'resampy', 'keras', 'tensorflow', - 'kapre', 'kapre.time_frequency', 'keras.layers', 'keras.models', - 'keras.regularizers', 'sklearn', 'sklearn.decomposition', 'skimage', + 'tensorflow.keras', 'tensorflow.keras.layers', 'tensorflow.keras.backend', + 'tensorflow.keras.regularizers', 'kapre', 'kapre.time_frequency', + 'sklearn', 'sklearn.decomposition', 'skimage', 'moviepy', 'skimage.io', 'moviepy.video', 'moviepy.video.io', 'moviepy.video.io.VideoFileClip' ] diff --git a/docs/installation.rst b/docs/installation.rst index baed98a..8483072 100644 --- a/docs/installation.rst +++ b/docs/installation.rst @@ -47,11 +47,11 @@ if needed. To install OpenL3 using ``pip``, simply run To install the latest version of OpenL3 from source: -1. Clone or pull the lastest version: +1. Clone or pull the latest version, only retrieving the ``main`` branch to avoid downloading the branch where we store the model weight files (these will be properly downloaded during installation). ->>> git clone git@github.com:marl/openl3.git +>>> git clone git@github.com:marl/openl3.git --branch main --single-branch -2. Install using pip to handle python dependencies: +2. Install using pip to handle python dependencies. The installation also downloads model files, which requires a stable network connection. >>> cd openl3 >>> pip install -e . diff --git a/openl3/models.py b/openl3/models.py index e27d716..ed5b021 100644 --- a/openl3/models.py +++ b/openl3/models.py @@ -19,7 +19,8 @@ VALID_FRONTENDS = ("librosa", "kapre") VALID_INPUT_REPRS = ("linear", "mel128", "mel256") VALID_CONTENT_TYPES = ("music", "env") -VALID_EMBEDDING_SIZES = (6144, 512) +VALID_AUDIO_EMBEDDING_SIZES = (6144, 512) +VALID_IMAGE_EMBEDDING_SIZES = (8192, 512) def _log10(x): @@ -179,7 +180,7 @@ def load_image_embedding_model(input_repr, content_type, embedding_size): Spectrogram representation used for audio model. content_type : "music" or "env" Type of content used to train embedding. - embedding_size : 6144 or 512 + embedding_size : 8192 or 512 Embedding dimensionality. Returns diff --git a/openl3/version.py b/openl3/version.py index 2c8afd2..6ea8a52 100644 --- a/openl3/version.py +++ b/openl3/version.py @@ -1,2 +1,2 @@ short_version = '0.4' -version = '0.4.0rc2' +version = '0.4.2-dev' diff --git a/setup.py b/setup.py index f27ba56..5157403 100644 --- a/setup.py +++ b/setup.py @@ -50,8 +50,8 @@ long_description=long_description, long_description_content_type='text/markdown', url='https://github.com/marl/openl3', - author='Jason Cramer, Ho-Hsiang Wu, Bea Steers, and Justin Salamon', - author_email='jtcramer@nyu.edu', + author='Aurora Cramer, Ho-Hsiang Wu, Bea Steers, and Justin Salamon', + author_email='jtc440@nyu.edu', packages=find_packages(), entry_points={ 'console_scripts': ['openl3=openl3.cli:main'], @@ -88,7 +88,7 @@ ], extras_require={ 'docs': [ - 'sphinx==1.2.3', # autodoc was broken in 1.3.1 + 'sphinx', 'sphinxcontrib-napoleon', 'sphinx_rtd_theme', 'numpydoc',