leonidk

import numpy as np

class QuasiRandom():
    def __init__(self,dim=1,seed=None):
        self.dim = dim
        self.x = np.random.rand(dim) if seed is None else seed
        root_sys = [1] +[0 for i in range(dim-1)] + [-1,-1]
        self.const = sorted(np.roots(root_sys))[-1].real
        self.phi = np.array([1/(self.const)**(i+1) for i in range(dim)])
    def generate(self,n_points=1):

leonidk

leonidk

import gym
import numpy as np
import random

env = gym.make('Pendulum-v0')
dim = env.observation_space.shape[0] + 1
params = int(dim + (dim*(dim-1))/2)

# linear controller with pairwise features
def quad_control(w,ob,t):

leonidk

import argparse
import torch
import torch.nn as nn
from torch.autograd import Variable
from torch.utils.data import DataLoader

import torchvision
import torchvision.transforms as T
from torchvision.datasets import ImageFolder

leonidk

"""
Example TensorFlow script for finetuning a VGG model on your own data.
Uses tf.contrib.data module which is in release candidate 1.2.0rc0
Based on:
    - PyTorch example from Justin Johnson:
      https://gist.github.com/jcjohnson/6e41e8512c17eae5da50aebef3378a4c
Required packages: tensorflow (v1.2)
You can install the release candidate 1.2.0rc0 here:
https://www.tensorflow.org/versions/r1.2/install/
Download the weights trained on ImageNet for VGG:

leonidk

"""Short and sweet LSTM implementation in Tensorflow.

Motivation:
When Tensorflow was released, adding RNNs was a bit of a hack - it required
building separate graphs for every number of timesteps and was a bit obscure
to use. Since then TF devs added things like `dynamic_rnn`, `scan` and `map_fn`.
Currently the APIs are decent, but all the tutorials that I am aware of are not
making the best use of the new APIs.

Advantages of this implementation:

leonidk

from skimage import data, feature, color, filter, img_as_float
from matplotlib import pyplot as plt


original_image = img_as_float(data.chelsea())
img = color.rgb2gray(original_image)

k = 1.6

plt.subplot(2,3,1)

leonidk

#simple correlation vs convolution example
import numpy as np
from matplotlib.pyplot import *

style.use('seaborn-ticks')
for a in [[1,2,3],[1,2,1]]:
    figure()
    x=[-1,0,1]
    b = [0,0,1]

leonidk

import tensorflow as tf
import numpy as np

# takes a pair, returns a projected pair
def distort_func(p):
    x = p[0]
    y = p[1]
    r = p[2]
    # welcome to my hat picking
    K1 = 0.1

leonidk

import sys,os,csv
from pylab import *
from PIL import Image
import time
#from mayavi import mlab

#returns a list (length = 3)  of channels, each of which is a list (length = Z stack depth) of images
def getImages(fN):
	returnArr= [ [], [], [] ]
	tiff = Image.open(fN)