Giter VIP home page Giter VIP logo

udacity-ml-capstone's Introduction

Udacity Capstone Project

Machine Learning Nanodegree 2018

This directory contain all code that was used for the Udacity Machine Learning Engineer Nanodegree Program.

The folder Notebooks contains all of the Jupyter Notebooks used in the project.

The links to the project proposal and the write-up of the final project are below.

Additionally you will find:

  • UrbanSound Dataset sample - subsection of the data used within the project so you don't need to download the full dataset. The full dataset can be downloaded from here.

udacity-ml-capstone's People

Contributors

mikesmales avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

udacity-ml-capstone's Issues

Use k-fold validation split.

Can you post your results for 10-fold validation split? It would provide a more comprehensive result for your model.

num_labels in the output layer

Hello,

I am trying to use the same code for classifying 31 labels. However, while calculating the pre-training accuracy I am getting the error ValueError: Shapes (None, 31) and (None, 99, 31) are incompatible. The X.shape and Y.shape in my case are (67871, 99, 32) and (67871, 31), respectively. How may I fix the error?

Thanks!

Prediction using Saved Model Failed.

@mikesmales Thanks for wonderful code for sound classification.

I used your code for training a model to classify free-spoken-digit-dataset (https://github.com/Jakobovski/free-spoken-digit-dataset). The accuracy of the trained model is 96%.

But the prediction using the saved model fails when I test it for my recorded voice. I recorded some digits using windows 10 voice recorder and converted files to 8KHz Mono WAV format.

Any help you can provide? The model predict accuratley on the recordings provided within the dataset.

My Recorded Digit 3:

Original sample rate: 22050
Librosa sample rate: 22050
Original audio file minmax range: 20 to 239
Librosa audio file min
max range: -0.84375 to 0.8671875
(40, 18)

Dataset : Jackson 1:

Original sample rate: 8000
Librosa sample rate: 22050
Original audio file minmax range: -10989 to 9277
Librosa audio file min
max range: -0.35349792 to 0.28417692
(40, 21)

why normalization isn't applied

I noticed that before training, no normalization step is applied to data, instead they directly feed into CNN, but the result is still satisfying. Is normalization unnecessary in this case?

Errors importing Librosa and matplotlib packages

Hello,

I'm fairly new to Python, Jupyter Notebook and Machine Learning in general. I want to report this issue that I'm having with running your code. After pulling it from Github, I tried running it in Visual Studio Code and was stuck at the importing process. The error that I encountered seems to suggest that my system (Windows 10) had failed to access the required library links, with llvmlite failing to be loaded and matplotlib not being accessible by the system at all. I'm using Anaconda distribution to install the Librosa package. Anyway, here are the two code blocks for the tracebacks

for the matplotlib

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
<ipython-input-12-cc3b387ce607> in <module>
      4 #import librosa
      5 #import librosa.display
----> 6 import matplotlib.pyplot as plt

~\anaconda3\lib\site-packages\matplotlib\__init__.py in <module>
    105 # cbook must import matplotlib only within function
    106 # definitions, so it is safe to import from it here.
--> 107 from . import _api, cbook, docstring, rcsetup
    108 from matplotlib.cbook import MatplotlibDeprecationWarning, sanitize_sequence
    109 from matplotlib.cbook import mplDeprecation  # deprecated

~\anaconda3\lib\site-packages\matplotlib\rcsetup.py in <module>
     22 import numpy as np
     23 
---> 24 from matplotlib import _api, animation, cbook
     25 from matplotlib.cbook import ls_mapper
     26 from matplotlib.colors import Colormap, is_color_like

~\anaconda3\lib\site-packages\matplotlib\animation.py in <module>
     32 
     33 import numpy as np
---> 34 from PIL import Image
     35 
     36 import matplotlib as mpl

~\anaconda3\lib\site-packages\PIL\Image.py in <module>
    107     # Also note that Image.core is not a publicly documented interface,
    108     # and should be considered private and subject to change.
--> 109     from . import _imaging as core
    110 
    111     if __version__ != getattr(core, "PILLOW_VERSION", None):

ImportError: DLL load failed while importing _imaging: The file cannot be accessed by the system.

for the librosa

---------------------------------------------------------------------------
OSError                                   Traceback (most recent call last)
<ipython-input-13-5c79ab56b39a> in <module>
      2 
      3 import IPython.display as ipd
----> 4 import librosa
      5 #import librosa.display
      6 import matplotlib.pyplot as plt

~\anaconda3\lib\site-packages\librosa\__init__.py in <module>
    209 # And all the librosa sub-modules
    210 from ._cache import cache
--> 211 from . import core
    212 from . import beat
    213 from . import decompose

~\anaconda3\lib\site-packages\librosa\core\__init__.py in <module>
      3 """ Core IO and DSP functions"""
      4 
----> 5 from .convert import *  # pylint: disable=wildcard-import
      6 from .audio import *  # pylint: disable=wildcard-import
      7 from .spectrum import *  # pylint: disable=wildcard-import

~\anaconda3\lib\site-packages\librosa\core\convert.py in <module>
      5 import re
      6 import numpy as np
----> 7 from . import notation
      8 from ..util.exceptions import ParameterError
      9 

~\anaconda3\lib\site-packages\librosa\core\notation.py in <module>
      6 import numpy as np
      7 from .._cache import cache
----> 8 from ..util.exceptions import ParameterError
      9 
     10 __all__ = [

~\anaconda3\lib\site-packages\librosa\util\__init__.py in <module>
     81 """
     82 
---> 83 from .utils import *  # pylint: disable=wildcard-import
     84 from .files import *  # pylint: disable=wildcard-import
     85 from .matching import *  # pylint: disable=wildcard-import

~\anaconda3\lib\site-packages\librosa\util\utils.py in <module>
      8 
      9 import numpy as np
---> 10 import numba
     11 from numpy.lib.stride_tricks import as_strided
     12 

~\anaconda3\lib\site-packages\numba\__init__.py in <module>
     17 
     18 
---> 19 from numba.core import config
     20 from numba.testing import _runtests as runtests
     21 from numba.core import types, errors

~\anaconda3\lib\site-packages\numba\core\config.py in <module>
     14 
     15 
---> 16 import llvmlite.binding as ll
     17 
     18 IS_WIN32 = sys.platform.startswith('win32')

~\anaconda3\lib\site-packages\llvmlite\binding\__init__.py in <module>
      2 Things that rely on the LLVM library
      3 """
----> 4 from .dylib import *
      5 from .executionengine import *
      6 from .initfini import *

~\anaconda3\lib\site-packages\llvmlite\binding\dylib.py in <module>
      1 from ctypes import c_void_p, c_char_p, c_bool, POINTER
      2 
----> 3 from llvmlite.binding import ffi
      4 from llvmlite.binding.common import _encode_string
      5 

~\anaconda3\lib\site-packages\llvmlite\binding\ffi.py in <module>
    189         break
    190 else:
--> 191     raise OSError("Could not load shared object file: {}".format(_lib_name))
    192 
    193 

OSError: Could not load shared object file: llvmlite.dll

I have tried uninstalling and reinstalling llvmlite on base environment, creating a new environment and installing the required library over there, yet nothing works.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.