This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
-- "cabal install vector-fftw split" | |
import qualified Numeric.FFT.Vector.Unnormalized as FFT | |
import Data.Vector (fromList, toList) | |
import Data.List.Split (splitOneOf) | |
import Data.List (intersperse) | |
import Control.Monad (forever) | |
import Control.Arrow ((>>>)) | |
main = forever $ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{-# LANGUAGE ScopedTypeVariables #-} | |
module CrazyIO (module CrazyIO, mmapFileByteString) where | |
import qualified Data.Vector.Storable as V | |
import qualified Data.ByteString as BS | |
import qualified Data.ByteString.Internal as BS | |
import Foreign | |
import System.IO.MMap | |
crazyLoad :: forall a. Storable a => FilePath -> Maybe (Int64, Int) -> IO (V.Vector a) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
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) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
from keras.models import Sequential | |
from keras.layers.core import Activation, Dense | |
from keras.optimizers import SGD | |
X = np.array([[0,0],[0,1],[1,0],[1,1]], "float32") | |
y = np.array([[0],[1],[1],[0]], "float32") | |
model = Sequential() | |
model.add(Dense(2, input_dim=2, activation='sigmoid')) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from random import random | |
from numpy import tanh | |
from scipy import array, vectorize, transpose | |
class Network: | |
""" Class builds neural network | |
""" | |
def __init__(self, inputs, outputs, hlayers=None, activation=tanh, | |
learning_rate=1.): |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<!DOCTYPE html> | |
<html> | |
<head> | |
<title>My Presentation</title> | |
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/> | |
<style type="text/css"> | |
.red { color: red } | |
</style> | |
</head> | |
<body> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
-- Run a one dimensional gradient descent written in Clash [1], | |
-- a high level language that compiles to Verilog and VHDL. | |
-- Gradient descent can be described by a formula: | |
-- | |
-- a_n+1 = a_n - gamma * Grad F(a_n), | |
-- | |
-- where the constant `gamma` is what is referred to in deep learning as | |
-- the learning rate. | |
-- | |
-- [1] https://clash-lang.org/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
descent1D gradF iterN gamma x0 = take iterN (iterate _descend x0) | |
where | |
_descend gamma' x = x - gamma' * gradF x | |
-- Suppose, we have a function F(x) = (x - 3)^2. | |
-- Therefore, Grad F(x) = 2 * (x - 3). | |
gradF_test x = 2 * (x - 3) | |
main = print (descent1D gradF_test 10 gamma 0.0) | |
where gamma = 0.5 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
""" | |
Cellular automata in Python | |
""" | |
import sys | |
Z = '.' | |
O = '#' |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Concatenate images | |
ffmpeg -framerate 5 -pattern_type glob -i "*.jpg" output.mp4 | |
# Compress | |
ffmpeg -i output.mp4 -vcodec libx265 -acodec aac -crf 23 output_compressed.mp4 |
OlderNewer