usernaamee’s gists

usernaamee / 10102016.py

Created October 10, 2016 13:32

xt = alpha f + (1-alpha) e + const ? (var input frame size for f, alpha, e)? not lstm?

	import sys
	import librosa
	import numpy as np


	def normalize_audio(raw_audio):
	minval = raw_audio.min()
	maxval = raw_audio.max()
	audio = (((raw_audio - minval) / float(maxval - minval)) - 0.5) * 2.0
	return audio

usernaamee / MDN (Keras + Theano).py

Created December 9, 2016 10:54

mixture density network in theano + keras

	import os
	import theano
	import numpy as np
	import theano.tensor as T
	from keras import backend as K
	from keras.models import Sequential
	from keras.layers.core import Layer, Dense, Lambda


	def log_sum_exp(x, axis=None):

usernaamee / binfile2pycode.py

Created March 13, 2017 19:03

Create self extracting python 2.6+ source code from any binary file

	"""
	:\|
	- Email provider doesn't allow me to send certain file types.
	- I have python installed on all my machines.
	- Inflates the file size by ~4.5X, still remains under 25M for me.
	"""

	from __future__ import print_function
	import sys

usernaamee / rwa.py

Created April 10, 2017 15:12 — forked from shamatar/rwa.py

Keras (keras.is) implementation of Recurrent Weighted Average, as described in https://arxiv.org/abs/1703.01253. Follows original implementation in Tensorflow from https://github.com/jostmey/rwa. Works with fixed batch sizes, requires "batch_shape" parameter in input layer. Outputs proper config, should save and restore properly. You are welcome…

	from keras.layers import Recurrent
	import keras.backend as K
	from keras import activations
	from keras import initializers
	from keras import regularizers
	from keras import constraints
	from keras.engine import Layer
	from keras.engine import InputSpec

usernaamee / wld-feature-extractor.py

Created June 9, 2017 13:31

wld-feature-extractor

	import cv2
	import sys
	import numpy as np
	from scipy import signal
	import matplotlib.pyplot as plt

	def get_wld_feats(gray_img):
	f00 =np.array([[1, 1, 1], [1, -8, 1], [1, 1, 1]])
	f10 = np.array([[0, -1, 0], [0, 0, 0], [0, 1, 0]])
	f11 = np.array([[0, 0, 0], [1, 0, -1], [0, 0, 0]])

usernaamee / Bi-LSTM-kws.py

Created October 19, 2017 18:41

Bi-LSTM-kws.py

	import os
	import sys
	import torch
	import librosa
	import numpy as np
	import torch.nn as nn
	import torch.optim as optim
	from torch.autograd import Variable
	from sklearn.model_selection import train_test_split

usernaamee / spectre.c

Created January 10, 2018 16:53 — forked from ErikAugust/spectre.c

Spectre example code

	#include <stdio.h>
	#include <stdlib.h>
	#include <stdint.h>
	#ifdef _MSC_VER
	#include <intrin.h> /* for rdtscp and clflush */
	#pragma optimize("gt",on)
	#else
	#include <x86intrin.h> /* for rdtscp and clflush */
	#endif

usernaamee / compare-two-ml-models.ipynb

Created January 30, 2018 07:38

Compare the performance of two machine learning models

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

usernaamee / create-qgis-dock-plugin.py

Last active March 1, 2018 13:00

Dock widget based plugin builder for QGIS

	"""
	Replace following four appropriately first:
	yourname yourcompany http://yourcompany.com http://yourcompany.com/logo.png
	"""
	import os
	import sys
	import urllib
	import argparse

	parser = argparse.ArgumentParser()

usernaamee / change_ps1

Created March 23, 2018 08:49

some awesome ps1 prompts

	function snip() {
	PS1="\n\[\033[35m\]\$(/bin/date)\n\[\033[32m\]\w\n\[\033[1;31m\]\u@\h: \[\033[1;34m\]\$(/usr/bin/tty \| /bin/sed -e 's:/dev/::'): \[\033[1;36m\]\$(/bin/ls -1 \| /usr/bin/wc -l \| /bin/sed 's: ::g') files \[\033[1;33m\]\$(/bin/ls -lah \| /bin/grep -m 1 total \| /bin/sed 's/total //')b\[\033[0m\] -> \[\033[0m\] "
	}

	function swog() {
	PS1="\[\e[36;45m\]▓\[\e[m\]\[\e[36;45m\]▒\[\e[m\]\[\e[36;45m\]░\[\e[m\]\[\e[36;45m\]\u\[\e[m\]\[\e[36;45m\]@\[\e[m\]\[\e[36;45m\]\h\[\e[m\]\[\e[36;45m\]:\[\e[m\]\[\e[35;46m\]\w\[\e[m\]\[\e[35;46m\]░\[\e[m\]\[\e[35;46m\]▒\[\e[m\]\[\e[35;46m\]▓\[\e[m\]>>> "
	}