Skip to content

Instantly share code, notes, and snippets.

View soroushmehr's full-sized avatar

Soroush Mehri soroushmehr

126 followers · 82 following
  • Microsoft Research (prev. Maluuba and MILA-UdeM)
  • Vancouver, BC
View GitHub Profile
@endolith
endolith / frequency_estimator.py
Last active October 30, 2023 18:08
Frequency estimation methods in Python
from __future__ import division
from numpy.fft import rfft
from numpy import argmax, mean, diff, log, nonzero
from scipy.signal import blackmanharris, correlate
from time import time
import sys
try:
import soundfile as sf
except ImportError:
from scikits.audiolab import flacread
@henrik
henrik / tmux_cheatsheet.markdown
Created March 3, 2012 19:47
tmux cheatsheet

tmux cheatsheet

As configured in my dotfiles.

start new:

tmux

start new with session name:

@hrldcpr
hrldcpr / tree.md
Last active May 1, 2024 00:11
one-line tree in python

One-line Tree in Python

Using Python's built-in defaultdict we can easily define a tree data structure:

def tree(): return defaultdict(tree)

That's it!

@jboner
jboner / latency.txt
Last active May 2, 2024 09:45
Latency Numbers Every Programmer Should Know
Latency Comparison Numbers (~2012)
----------------------------------
L1 cache reference 0.5 ns
Branch mispredict 5 ns
L2 cache reference 7 ns 14x L1 cache
Mutex lock/unlock 25 ns
Main memory reference 100 ns 20x L2 cache, 200x L1 cache
Compress 1K bytes with Zippy 3,000 ns 3 us
Send 1K bytes over 1 Gbps network 10,000 ns 10 us
Read 4K randomly from SSD* 150,000 ns 150 us ~1GB/sec SSD
@Newmu
Newmu / conv_deconv_variational_autoencoder.py
Last active November 13, 2023 16:35
Prototype code of conv/deconv variational autoencoder, probably not runable, lots of inter-dependencies with local codebase =/
import theano
import theano.tensor as T
from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
from theano.tensor.signal.downsample import max_pool_2d
from theano.tensor.extra_ops import repeat
from theano.sandbox.cuda.dnn import dnn_conv
from time import time
import numpy as np
from matplotlib import pyplot as plt
@karpathy
karpathy / gist:587454dc0146a6ae21fc
Last active March 19, 2024 05:50
An efficient, batched LSTM.
"""
This is a batched LSTM forward and backward pass
"""
import numpy as np
import code
class LSTM:
@staticmethod
def init(input_size, hidden_size, fancy_forget_bias_init = 3):
@karpathy
karpathy / min-char-rnn.py
Last active May 1, 2024 11:00
Minimal character-level language model with a Vanilla Recurrent Neural Network, in Python/numpy
"""
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np
# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)
@bishboria
bishboria / springer-free-maths-books.md
Last active April 25, 2024 06:27
Springer made a bunch of books available for free, these were the direct links
@samim23
samim23 / forward.py
Last active October 13, 2022 07:54
# "Colorizing B/W Movies with Neural Nets",
# Network/Code Created by Ryan Dahl, hacked by samim.io to work with movies
# BACKGROUND: http://tinyclouds.org/colorize/
# DEMO: https://www.youtube.com/watch?v=_MJU8VK2PI4
# USAGE:
# 1. Download TensorFlow model from: http://tinyclouds.org/colorize/
# 2. Use FFMPEG or such to extract frames from video.
# 3. Make sure your images are 224x224 pixels dimension. You can use imagemagicks "mogrify", here some useful commands:
# mogrify -resize 224x224 *.jpg
# mogrify -gravity center -background black -extent 224x224 *.jpg
@mickypaganini
mickypaganini / TestDense&HW.ipynb
Created May 7, 2016 19:13
Test Dense and Highway layers in Keras using the same inputs as in our lwtnn-test-highway.cxx
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.