Skip to content

Commit

Permalink
Minor updates to comments
Browse files Browse the repository at this point in the history
Ji-Sung Linux committed Dec 4, 2016
1 parent a24b04c commit dea4bde
Showing 4 changed files with 8 additions and 6 deletions.
2 changes: 2 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -6,6 +6,8 @@
mp3/
deepjazz_on*.midi
*_old*
_private/
_misc/

# Byte-compiled / optimized / DLL files
__pycache__/
6 changes: 3 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
@@ -2,7 +2,7 @@

### Using Keras & Theano for deep learning driven jazz generation

I built [*deepjazz*](http://deepjazz.io) in 36 hours at a hackathon. It uses Keras & Theano, two deep learning libraries, to generate jazz music. Specifically, it builds a two-layer [LSTM](http://deeplearning.net/tutorial/lstm.html), learning from the given MIDI file. It uses deep learning, the AI tech that powers [Google's AlphaGo](https://deepmind.com/alpha-go.html) and [IBM's Watson](https://www.ibm.com/smarterplanet/us/en/ibmwatson/what-is-watson.html), **to make music -- something that's considered as deeply human**.
I built [*deepjazz*](https://deepjazz.io) in 36 hours at a hackathon. It uses Keras & Theano, two deep learning libraries, to generate jazz music. Specifically, it builds a two-layer [LSTM](http://deeplearning.net/tutorial/lstm.html), learning from the given MIDI file. It uses deep learning, the AI tech that powers [Google's AlphaGo](https://deepmind.com/alpha-go.html) and [IBM's Watson](https://www.ibm.com/smarterplanet/us/en/ibmwatson/what-is-watson.html), **to make music -- something that's considered as deeply human**.

[![SoundCloud](https://jisungk.github.io/deepjazz/img/button_soundcloud.png)](https://soundcloud.com/deepjazz-ai)
Check out deepjazz's music on **[SoundCloud](https://soundcloud.com/deepjazz-ai)**!
@@ -31,9 +31,9 @@ Note: `preprocess.py` must be modified to work with other MIDI files (the releva

### Author

[Ji-Sung Kim](http://jisungkim.com)
[Ji-Sung Kim](https://jisungkim.com)
Princeton University, Department of Computer Science
jisungk@princeton.edu
jisungk (at) cs.princeton.edu

### Citations

2 changes: 1 addition & 1 deletion grammar.py
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
'''
Author: Ji-Sung Kim, Evan Chow
Project: jazzml / deepjazz
Project: jazzml / (used in) deepjazz
Purpose: Extract, manipulate, process musical grammar
Directly taken then cleaned up from Evan Chow's jazzml,
4 changes: 2 additions & 2 deletions lstm.py
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
'''
Author: Ji-Sung Kim
Project: jazzml
Project: deepjazz
Purpose: Builds an LSTM, a type of recurrent neural network (RNN).
Code was built while significantly referencing public examples from the
@@ -20,7 +20,7 @@ def build_model(corpus, val_indices, max_len, N_epochs=128):
# number of different values or words in corpus
N_values = len(set(corpus))

# cut the corpus in semi-redundant sequences of max_len values
# cut the corpus into semi-redundant sequences of max_len values
step = 3
sentences = []
next_values = []

0 comments on commit dea4bde

Please sign in to comment.