psycharo-zz

w = w.transpose([2, 3, 1, 0])
w = w[::-1,::-1,:,:]

psycharo-zz

import threading
import numpy as np
import tensorflow as tf

class FeedingRunner(object):
  """Takes care of feeding/dequeueing data into the queue
  Based on tf.train.QueueRunner
  """

  def __init__(self, generator, dtypes, shapes, names, num_threads,

psycharo-zz

def instance_to_regression_map(instances, cids):
  """Convert instance label map to the regression map
  Args:
    instances: instance label mask
    cids: ids of classes to load
  """
  # TODO: for all the classes that have instances, we can compute this
  image_size = instances.shape[:2]
  reg = np.zeros(image_size + (4,), dtype=np.uint16)
  # instead of this, we can simply ???

psycharo-zz

def _next_instance(mask, iid, instances):
  """Process single instance and add it to the mask
  Args:
    mask: source mask
    iid: instance id
    instances: instance segmentation mask
  Returns:
    updated mask
  """
  yx = tf.to_int32(tf.where(tf.equal(instances, iid)))

psycharo-zz

class ImageCoder(object):
  """Helper class for handling images in TensorFlow."""

  def __init__(self, channels=3, config=None):
    # Create a single TensorFlow Session for all image decoding calls.
    self._sess = tf.Session(config=config)

    # TensorFlow ops for JPEG decoding.
    self._src_png = tf.placeholder(dtype=tf.string)
    self._dst_raw = tf.image.decode_png(self._src_png, channels=channels)

psycharo-zz

// register a callback when the IPython.notebook instance is created.
$([IPython.events]).on('app_initialized.NotebookApp', function(){
	function to(mode) {
		// this can be either 'vim' or 'emacs'
		var mode = mode || 'emacs';
		// first let's apply mode to all current cells
		function to_mode(c) { return c.code_mirror.setOption('keyMap', mode);};
		var cells = IPython.notebook.get_cells();
		if (cells != null) {

psycharo-zz

vec generate_gmm(size_t N, const vec &mean, const vec &stddev, const vec &weights)
{
    vec result(N);
    const size_t K = weights.size();
    size_t filled = 0;
    for (size_t k = 0; k < K; ++k)
    {
        size_t size_k = weights(k) * N;
        result.subvec(filled, filled + size_k - 1) =  mean(k) + randn(size_k) * stddev(k);
        filled += size_k;

psycharo-zz

#include <cfloat>
#include <armadillo>
using namespace arma;

/**
 * K-means algorithm
 * @param K the number of clusters
 * @param means cluster centers
 * @param counts sizes of clusters
 * @param resps assignments to clusters

psycharo-zz

double randn(double mean, double sigma)
{ 
  gsl_rng *gnr = gsl_rng_alloc(gsl_rng_default);
  return mean + gsl_ran_gaussian(gnr, sigma);
  gsl_rng_free(gnr);
}

psycharo-zz

defaults write com.apple.dashboard mcx-disabled -boolean YES && killall Dock