s444337/praca-magisterska
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

readme update

Browse Source
This commit is contained in:
Cezary Pukownik 2019-06-19 13:24:31 +02:00
parent 23f406d053
commit 75e1c6cb90
1 changed files with 10 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
project/readme.md
View File

@ -1,28 +1,26 @@
### MUSIC GENERATION USING DEEP LEARNING ## ###MUSIC GENERATION USING DEEP LEARNING
### AUTHOR: CEZARY PUKOWNIK ###AUTHOR: CEZARY PUKOWNIK
files: #Files:
- midi.py - code for data extraction, and midi convertion - midi.py - code for data extraction, and midi convertion
- train.py - code for model definition, and training session - train.py - code for model definition, and training session
- generate.py - code for model loading, predicting ang saving to midi_dir - generate.py - code for model loading, predicting ang saving to midi_dir
- settings.py - file where deafult settings are stored - settings.py - file where deafult settings are stored
- readme - this file - readme.md - this file
#Directories:
- data/midi - directory where input midi are stored - data/midi - directory where input midi are stored
- data/models - directory where trained models are stored - data/models - directory where trained models are stored
- data/output - directory where generated music is stored - data/output - directory where generated music is stored
- data/samples - directory where extracted data from midi is stored - data/samples - directory where extracted data from midi is stored
- data/samples.npz - deprecated - data/samples.npz - deprecated
How to use: #How to use:
1. Use midi.py to export data from midi files 1. Use midi.py to export data from midi files
>>> ./midi.py [midi_folder_path] [output_path]
./midi.py <midi_folder_path> <output_path>
2. Use train.py to train a model (this can take a while) 2. Use train.py to train a model (this can take a while)
>>> ./train.py [input_training_data] [model_save_path] [epochs]
./train.py <input_training_data> <model_save_path> <epochs>
3. Use generate.py to generate music from trained models 3. Use generate.py to generate music from trained models
>>> ./generate.py [trained_model_path] [output_path] [treshold]
./generate.py <trained_model_path> <output_path> <treshold>