szagoruyko

Network-in-Network trained in Torch7

Trained by me using https://github.com/soumith/imagenet-multiGPU.torch, achieves 62.6% top1 center crop accuracy on ImageNet validation set. Tested here: https://github.com/szagoruyko/imagenet-validation.torch

Download links:

1. https://www.dropbox.com/s/mclw90yba6eml60/nin_bn_final.t7 (31 MB)
2. https://www.dropbox.com/s/npmr5egvjbg7ovb/nin_nobn_final.t7 (31 MB) - Batch Normalization intergrated into convolutional layers

JBed

#PCA whitening involves finding the inverse square root of the covariance matrix 
#of a set of observations, which is prohibitively expensive when dealing 
#with natural images 

#starting with a path to a single image (img_path)
import numpy as np
from PIL import Image
from sklearn import preprocessing

eickenberg

# Disclaimer: This doesn't seem to work 100% yet, but almost ;)

# Convolutional ZCA
# When images are too large in amount of pixels to be able to determine the
# principal components of an image batch, one can suppose translation
# invariance of the eigen-structure and do the ZCA in a convolutional manner

import theano
import theano.tensor as T
import numpy as np

rtt

# encoding: utf8                                                                                                                                           1,1           Top# encoding: utf8
import argparse
from datetime import datetime
import json
from random import randint
import requests
import sys
from time import sleep

rtt

Tinder API documentation

Note: this was written in April/May 2014 and the API may has definitely changed since. I have nothing to do with Tinder, nor its API, and I do not offer any support for anything you may build on top of this. Proceed with caution

http://rsty.org/

I've sniffed most of the Tinder API to see how it works. You can use this to create bots (etc) very trivially. Some example python bot code is here -> https://gist.github.com/rtt/5a2e0cfa638c938cca59 (horribly quick and dirty, you've been warned!)