Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
N
neural_filters
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
0
Issues
0
List
Boards
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Analytics
Analytics
CI / CD
Repository
Value Stream
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
software
neural_filters
Commits
cf0fc7d9
Commit
cf0fc7d9
authored
Jun 07, 2018
by
M. François
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Dist version checked
parent
f8e3beb5
Changes
4
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
186 additions
and
7 deletions
+186
-7
docs/README.rst
docs/README.rst
+175
-0
docs/sphinx/conf.py
docs/sphinx/conf.py
+0
-5
docs/sphinx/index.rst
docs/sphinx/index.rst
+10
-1
setup.py
setup.py
+1
-1
No files found.
docs/README.rst
View file @
cf0fc7d9
...
...
@@ -2,6 +2,181 @@ Welcome to Neural Filters’s documentation!
******************************************
NeuralFilterCell
================
This module implements a basic trainable all-pole first order filter
using pyTorch
Copyright (c) 2018 Idiap Research Institute, http://www.idiap.ch/
Written by Francois Marelli <Francois.Marelli@idiap.ch>
This file is part of neural_filters.
neural_filters is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License version 3 as
published by the Free Software Foundation.
neural_filters is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
General Public License for more details.
You should have received a copy of the GNU General Public License
along with neural_filters. If not, see <http://www.gnu.org/licenses/>.
class neural_filters.neural_filter.NeuralFilter(hidden_size)
A trainable first-order all-pole filter \frac{1}{1 - P z^{-1}}
* **hidden_size** (int) - the size of the data vector
forward(input_var, hidden=None)
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note: Although the recipe for forward pass needs to be defined
within this function, one should call the "Module" instance
afterwards instead of this since the former takes care of
running the registered hooks while the latter silently ignores
them.
NeuralFilter2R
==============
This module implements a trainable all-pole second order filter with
real poles using pyTorch
Copyright (c) 2018 Idiap Research Institute, http://www.idiap.ch/
Written by Francois Marelli <Francois.Marelli@idiap.ch>
This file is part of neural_filters.
neural_filters is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License version 3 as
published by the Free Software Foundation.
neural_filters is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
General Public License for more details.
You should have received a copy of the GNU General Public License
along with neural_filters. If not, see <http://www.gnu.org/licenses/>.
class neural_filters.neural_filter_2R.NeuralFilter2R(hidden_size)
A trainable second-order all-(real)pole filter \frac{1}{1 - P_{1}
z^{-1}} \frac{1}{1 - P_{2} z^{-1}}
* **hidden_size** (int) - the size of data vector
forward(input_var, hx=(None, None))
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note: Although the recipe for forward pass needs to be defined
within this function, one should call the "Module" instance
afterwards instead of this since the former takes care of
running the registered hooks while the latter silently ignores
them.
NeuralFilter2CD
===============
This module implements a trainable critically damped all-pole second
order filter with real poles using pyTorch
Copyright (c) 2018 Idiap Research Institute, http://www.idiap.ch/
Written by Francois Marelli <Francois.Marelli@idiap.ch>
This file is part of neural_filters.
neural_filters is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License version 3 as
published by the Free Software Foundation.
neural_filters is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
General Public License for more details.
You should have received a copy of the GNU General Public License
along with neural_filters. If not, see <http://www.gnu.org/licenses/>.
class neural_filters.neural_filter_2CD.NeuralFilter2CD(hidden_size)
A trainable second-order critically damped all-pole filter
\frac{1}{(1 - P z^{-1})^{2}}
* **hidden_size** (int) - the size of data vector
forward(input_var, hx=(None, None))
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note: Although the recipe for forward pass needs to be defined
within this function, one should call the "Module" instance
afterwards instead of this since the former takes care of
running the registered hooks while the latter silently ignores
them.
NeuralFilter2CC
===============
This module implements a trainable all-pole second order filter with
complex conjugate poles using pyTorch
Copyright (c) 2018 Idiap Research Institute, http://www.idiap.ch/
Written by Francois Marelli <Francois.Marelli@idiap.ch>
This file is part of neural_filters.
neural_filters is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License version 3 as
published by the Free Software Foundation.
neural_filters is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
General Public License for more details.
You should have received a copy of the GNU General Public License
along with neural_filters. If not, see <http://www.gnu.org/licenses/>.
class neural_filters.neural_filter_2CC.NeuralFilter2CC(hidden_size)
A trainable second-order all-pole filter \frac{1}{1 - 2 P
\cos(\theta) z^{-1} + P^{2} z^{-2}}
* **hidden_size** (int) - the size of the data vector
forward(input_var, hidden=None)
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note: Although the recipe for forward pass needs to be defined
within this function, one should call the "Module" instance
afterwards instead of this since the former takes care of
running the registered hooks while the latter silently ignores
them.
Indices and tables
******************
...
...
docs/sphinx/conf.py
View file @
cf0fc7d9
...
...
@@ -17,11 +17,6 @@
# documentation root, use os.path.abspath to make it absolute, like shown here.
#
import
os
import
sys
sys
.
path
.
insert
(
0
,
os
.
path
.
abspath
(
os
.
path
.
join
(
'..'
,
'..'
,
'neural_filters'
)))
import
neural_filters
# -- General configuration ------------------------------------------------
...
...
docs/sphinx/index.rst
View file @
cf0fc7d9
...
...
@@ -10,7 +10,16 @@ Welcome to Neural Filters's documentation!
:maxdepth: 2
:caption: Contents:
.. automodule:: neural_filters
.. automodule:: neural_filters.neural_filter
:members:
.. automodule:: neural_filters.neural_filter_2R
:members:
.. automodule:: neural_filters.neural_filter_2CD
:members:
.. automodule:: neural_filters.neural_filter_2CC
:members:
Indices and tables
...
...
setup.py
View file @
cf0fc7d9
...
...
@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
setup
(
name
=
'neural-filters'
,
version
=
'
0.2
'
,
version
=
'
1.0
'
,
description
=
'Linear filters for neural networks in pyTorch'
,
author
=
'Idiap research institute - Francois Marelli'
,
author_email
=
'francois.marelli@idiap.ch'
,
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment