DeepHarmony - Revision history

Edavis: /* Getting Deep Harmony set up on your computer */

2016-10-22T18:42:07Z

‎Getting Deep Harmony set up on your computer

2016-10-17T01:12:58Z

2016-10-17T01:02:00Z

2016-10-12T00:24:21Z

2016-10-12T00:17:13Z

2016-10-12T00:05:00Z

‎Recommended skills: =

2016-10-12T00:04:42Z

‎Dependencies:

2016-10-12T00:04:13Z

‎Summary

2016-10-12T00:01:34Z

‎Tasks

2016-10-11T23:59:03Z

‎Dependencies:

@@ Line 43: / Line 43: @@
 =Getting Deep Harmony set up on your computer=
 All project files and resources are located in this git repository:
 [https://github.com/samkhal/deepharmony https://github.com/samkhal/deepharmony]

← Older revision		Revision as of 01:12, 17 October 2016
Line 1:		Line 1:
		+	[[:Category:Inquiry_Seminary_in_Music_Technology:_Gaming_and_Multimedia_(3910) \|'''Go Back to Main Project Menu''']]
		+	<br/>
		+
	[[File:Deepharmony-screenshot.png\|400px]]		[[File:Deepharmony-screenshot.png\|400px]]
−
−	~~=Summary=~~

	Deep Harmony is a machine learning project for creating harmonies based on a given melody.		Deep Harmony is a machine learning project for creating harmonies based on a given melody.

@@ Line 1: / Line 1: @@
-<!--[[File:DeepHarmonyScreenshot.png]]-->
+[[File:Deepharmony-screenshot.png|400px]]
 =Summary=
@@ Line 9: / Line 8: @@
 Deep Harmony is written in [https://www.python.org Python 3.5] and uses the [https://keras.io Keras] machine learning library.
 =Possible Tasks=

← Older revision		Revision as of 00:24, 12 October 2016
Line 1:		Line 1:
−	[[File:DeepHarmonyScreenshot.png]]	+	<!--[[File:DeepHarmonyScreenshot.png]]-->
		+

	=Summary=		=Summary=

← Older revision		Revision as of 00:17, 12 October 2016
Line 1:		Line 1:
−	~~#PICTURE HERE#~~	+	[[File:DeepHarmonyScreenshot.png]]
−

	=Summary=		=Summary=

@@ Line 26: / Line 26: @@
 == Make Deep Harmony predict whole songs ==
 Deep Harmony currently creates the next note corresponding to a melody line, this is great for generating accompaniment, but you could make it generate entire songs.
-==== Recommended skills: =====
+==== Recommended skills: ====
 * Basic Python programming
 * Familiarity with machine learning

@@ Line 46: / Line 46: @@
 * [http://jupyter.org Jupyter Notebook], an interactive programming environment and editor (necessary for using the .ipynb files)
 * Python 3.5, and the following libraries:
-** numpy and matplotlib (they are packaged in [https://www.continuum.io/downloads Anaconda], and we recommend installing it that way)
+** numpy and matplotlib, for numerical computation and graphical plotting.
 ** [http://web.mit.edu/music21 music21], for processing music data
 ** [https://pypi.python.org/pypi/tqdm tqdm], for nice progress bars
 ** [https://keras.io Keras], a deep learning library. We recommend installing it with the Theano backend, but the code should work with the TensorFlow backend as well.
 * musescore 2+, for allowing music21 to render music as pictures
 =WPI Student contributors=

← Older revision		Revision as of 00:04, 12 October 2016
Line 7:		Line 7:

	Currently, Deep Harmony is learning to mimic the behavior of Bach Chorales created by [http://artsites.ucsc.edu/faculty/cope/ David Cope].		Currently, Deep Harmony is learning to mimic the behavior of Bach Chorales created by [http://artsites.ucsc.edu/faculty/cope/ David Cope].
		+
		+	Deep Harmony is written in [https://www.python.org Python 3.5] and uses the [https://keras.io Keras] machine learning library.

	=Possible Tasks=		=Possible Tasks=

@@ Line 8: / Line 8: @@
 Currently, Deep Harmony is learning to mimic the behavior of Bach Chorales created by [http://artsites.ucsc.edu/faculty/cope/ David Cope].
-=Tasks=
+=Possible Tasks=
 ==Integrating Deep Harmony into a Max Patch==