jiqiujia’s gists

jiqiujia / notebook.ipynb

Last active April 12, 2017 02:27 — forked from vmarkovtsev/notebook.ipynb

lapjv blog post/https://blog.sourced.tech/post/lapjv/

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

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

jiqiujia / dcgan.py

Created January 30, 2017 13:43 — forked from soumith/dcgan.py

	import torch
	import torch.nn as nn
	import torch.nn.parallel

	class DCGAN_D(nn.Container):
	def __init__(self, isize, nz, nc, ndf, ngpu, n_extra_layers=0):
	super(DCGAN_D, self).__init__()
	self.ngpu = ngpu
	assert isize % 16 == 0, "isize has to be a multiple of 16"

jiqiujia / utils.py

Last active April 1, 2017 09:15

keras

	#adjust learning rate policy by callbacks
	def scheduler(epoch):
	if epoch == 5:
	model.lr.set_value(.02)
	return model.lr.get_value()

	change_lr = LearningRateScheduler(scheduler)

	model.fit(x_embed, y, nb_epoch=1, batch_size = batch_size, show_accuracy=True,
	callbacks=[chage_lr])

jiqiujia / ncut.py

Last active December 24, 2016 08:39

graph util functions in python, from https://github.com/mdeff/ntds_2016

	# ### python_ncut_lib.py
	# Copyright (C) 2010 R. Cameron Craddock ([email protected])
	#
	# This script is a part of the pyClusterROI python toolbox for the spatially constrained clustering of fMRI
	# data. It provides the library functions for performing normalized cut clustering according to:
	#
	# Shi, J., & Malik, J. (2000). Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis
	# and Machine Intelligence, 22(8), 888-905. doi: 10.1109/34.868688.
	#
	# Yu, S. X., & Shi, J. (2003). Multiclass spectral clustering. Proceedings Ninth IEEE International Conference

jiqiujia / vim config file

Created December 2, 2016 06:37

vimrc

	"Pathogen
	execute pathogen#infect()
	syntax on
	filetype plugin indent on

	"NERDtree
	" open NERDTree with ctrl+n
	map <F2> :NERDTreeToggle<CR>
	" close vim if the only window left open is a NERDTree
	autocmd bufenter * if(winnr("$")==1 && exists("b:NERDTree") && b:NERDTree.isTabTree()) \| q \| endif

jiqiujia / tmux.conf

Last active March 14, 2017 08:04

tmux2.3 configuration file

	#设置前缀为Ctrl + a
	unbind ^b
	set -g prefix 'C-a'
	#将r 设置为加载配置文件，并显示信息
	bind r source-file ~/.tmux.conf \; display-message "Config reloaded"

	#up
	bind-key k select-pane -U
	#down
	bind-key j select-pane -D

jiqiujia / magnet_loss_utils.py

Created November 21, 2016 11:28

util functions of paper 'metric learning with adaptive density discrimination'

	from math import ceil
	import numpy as np
	from sklearn.cluster import KMeans

	import theano
	import theano.tensor as T

	def compute_reps(extract_fn, X, chunk_size):
	"""Compute representations for input in chunks."""
	chunks = int(ceil(float(X.shape[0]) / chunk_size))

jiqiujia / learn.lua

Created November 7, 2016 14:03 — forked from tylerneylon/learn.lua

Learn Lua quickly with this short yet comprehensive and friendly script. It's written as both an introduction and a quick reference. It's also a valid Lua script so you can verify that the code does what it says, and learn more by modifying and running this script in your Lua interpreter.

	-- Two dashes start a one-line comment.

	--[[
	Adding two ['s and ]'s makes it a
	multi-line comment.
	--]]

	----------------------------------------------------
	-- 1. Variables and flow control.
	----------------------------------------------------

jiqiujia / clustering.py

Last active June 5, 2017 08:55

python util functions/preprocessing

	def create_conf_matrix(expected, predicted, n_classes):
	m = np.zeros((n_classes, n_classes))
	for pred, exp in zip(predicted, expected):
	m[pred][exp] += 1
	return m

	def calc_accuracy(conf_matrix):
	t = sum(sum(l) for l in conf_matrix)
	return sum(conf_matrix[i][i] for i in range(len(conf_matrix))) / t

jiqiujia / layers.py

Last active February 15, 2017 15:07

theano

	class BatchNormLayer(lasagne.layers.Layer):
	def __init__(self, incoming, b=lasagne.init.Constant(0.), g=lasagne.init.Constant(1.),
	W=lasagne.init.Normal(0.05), nonlinearity=relu, **kwargs):
	super(BatchNormLayer, self).__init__(incoming, **kwargs)
	self.nonlinearity = nonlinearity
	k = self.input_shape[1]
	if b is not None:
	self.b = self.add_param(b, (k,), name="b", regularizable=False)
	if g is not None:
	self.g = self.add_param(g, (k,), name="g")

Overfit jiqiujia