Merge remote-tracking branch 'origin/master'

README.md

+# ML Binaural Audio
+
+## Goals
+
+The aim of this project is to apply Machine Learning techniques to binaural audio sound source localization. This project may lead to numerous works and scientific contributions:
+
+* the proposal of novel neural networks architecture that may achieve or outperform state of art algorithms,
+* generation of novel results, which may lead to an increase knowledge in terms of sound source localization performance,
+* etc.
+
+## Usage
+
+Install dependancies:
+> pip install -r requirements.txt
+
+Run one of the scripts located in ./scripts : see next section for more details.
+
+## Repository structure
+
+| Project path   | Description |
+| :------ |:-----------|
+| ./core | Package containing the core code. |
+| ./databases/ | Folder containing data of multiple databases (IRCAM, CIPIC, etc.), stored as Pandas.Dataframe objects in pickle binary files. |
+| ./scripts | Some useful python scripts. |
+| ./scripts/generate_database.py | Generate files stored in ./databases from RAW databses files, usually raw .wav files or .mat files. |
+| ./scripts/train2.py | Train a model. |
+| ./scripts/generate_results2.py | Generate results, stored as .csv files, from one or multiple trained models stored in a root directory. |
+| ./r-scripts | Generate some plots from stored results .csv files. |
+
+# Some links that you may find interesting
+
+Some binaural localization models: https://docs.google.com/document/d/1H5lV5_VNZ3JGffw8hrTtF9f8u89AS0pDubqrTOAHs3U/edit?usp=sharing
\ No newline at end of file

requirements.txt

@@ -3,6 +3,4 @@ scipy
 numpy
 matplotlib
 pandas
-plotly
-ipywidgets
 pytest