💫

ktnyt ktnyt

💫

Yet another web centric developer that writes pretty much anything.

45 followers · 9 following

LAPRAS inc.
Osaka
https://charaxiv.app
@_ktnyt

View GitHub Profile

Recently created

Least recently created

Recently updated

Least recently updated

ktnyt / pickleTinyImageNet.py

Last active November 3, 2017 08:32

Create a pickle of numpy arrays for Tiny ImageNet dataset training images.

	#!/usr/bin/env python
	import numpy as np
	from PIL import Image
	import six.moves.cPickle as pickle

	wnids = map(lambda x: x.strip(), open('wnids.txt').readlines())

	data = {}
	data['train'] = {}
	data['train']['data'] = np.ndarray(shape=(100000, 3, 64, 64), dtype=np.uint8)

ktnyt / brica_chainer_sda.py

Created August 17, 2015 05:53

BriCA + Chainer based simple SDA implementation

	import numpy as np
	from chainer import Variable, FunctionSet, optimizers
	import chainer.functions as F
	import data

	import brica1

	class SLP(FunctionSet):
	def __init__(self, n_input, n_output):
	super(SLP, self).__init__(

ktnyt / brica_svm.py

Created July 3, 2015 09:59

Linear SVM Component Implementation with BriCA

	#!/usr/bin/env python
	# -- coding: utf-8 --

	import numpy as np
	import matplotlib.pyplot as plt
	from sklearn import svm, datasets

	import brica1

	# SVM Component Definition

ktnyt / conv_dae.py

Last active August 29, 2015 14:24

FunctionSet model for Chainer based Convolutional Denoising Autoencoder

	class ConvolutionalAutoencoder(FunctionSet):
	def __init__(self, n_in, n_out, ksize, stride=1, pad=0, wscale=1, bias=0, nobias=False):
	super(ConvolutionalAutoencoder, self).__init__(
	encode=F.Convolution2D(n_in, n_out, ksize, stride=stride, pad=pad, wscale=wscale, bias=bias, nobias=nobias),
	decode=F.Convolution2D(n_out, n_in, ksize, stride=stride, pad=pad, wscale=wscale, bias=bias, nobias=nobias)
	)

	def forward(self, x_data, train=True):
	x = Variable(x_data)
	t = Variable(x_data)

ktnyt / chainer_ca.py

Last active August 10, 2020 17:41

Refactored code for a Convolutional Autoencoder implemented with Chainer.

	import argparse
	import numpy as np
	from chainer import Variable, FunctionSet, optimizers, cuda
	import chainer.functions as F
	import cv2
	import random
	import cPickle as pickle
	import sys

	class ConvolutionalAutoencoder(FunctionSet):

ktnyt / genbankn_batch_downloader.pl

Created June 22, 2015 07:31

Batch download GENBANK entries via TogoWS.

	#!/usr/bin/env perl
	use strict;
	use warnings;

	my $base = "togows.dbcls.jp/entry/nucleotide";

	my ($prefix, $from_id, $to_id) = (@ARGV);

	if($from_id > $to_id) {
	($from_id, $to_id) = ($to_id, $from_id);

ktnyt / brica_chainer_sda.py

Last active October 3, 2015 11:20

Implementation of stacked denoising autoencoder using BriCA1 and Chainer.

	import argparse
	import numpy as np
	from sklearn.datasets import fetch_mldata
	from chainer import Variable, FunctionSet, optimizers, cuda
	import chainer.functions as F
	import brica1

	class Perceptron():
	def __init__(self, n_in, n_out, use_cuda=False):
	self.model = FunctionSet(

ktnyt / chainer_mnist_autoencoder.py

Last active March 15, 2016 18:56

Chainer implementation of MNIST classification with Denoising Autoencoders. `utils` from here: https://gist.github.com/kiyukuta/6170759. You may need to change line 32 from utils.py to `image.astype(numpy.uint8).`

	import argparse
	import numpy as np
	from sklearn.datasets import fetch_mldata
	from chainer import Variable, FunctionSet, optimizers, cuda
	import chainer.functions as F
	#import utils

	parser = argparse.ArgumentParser(description='Chainer example: MNIST')
	parser.add_argument('--gpu', '-g', default=-1, type=int,
	help='GPU ID (negative value indicates CPU)')

ktnyt / chainer_xor

Created June 10, 2015 08:14

Minimum Chainer implementation of 3-Layer Perceptron for solving XOR

	#!/usr/bin/env python
	import numpy as np
	from chainer import cuda, Function, FunctionSet, gradient_check, Variable, optimizers
	import chainer.functions as F

	x_train = np.array([
	[[0., 0.]],
	[[0., 1.]],
	[[1., 0.]],
	[[1., 1.]]

ktnyt / iqstat.c

Last active April 5, 2018 03:07

Iteractive qstat viewer $ gcc -o iqstat -O3 -lncurses iqstat.c

	/******************************************************************************
	** iqstat - Interactive qstat viewer
	**
	** Created by kotone on 2015/01/16.
	** Copyright (c) 2015 Kotone Itaya. All rights reserved.
	**
	** iqstat is free software: you can redistribute it and/or modify
	** it under the terms of the GNU General Public License as published by
	** the Free Software Foundation, either version 3 of the License, or
	** (at your option) any later version.

Newer Older