utils.py

from __future__ import division
import math
import json
import random
import pprint
import scipy.misc
import numpy as np
from time import gmtime, strftime
from six.moves import xrange
import matplotlib.pyplot as plt

pp = pprint.PrettyPrinter()

get_stddev = lambda x, k_h, k_w: 1/math.sqrt(k_w*k_h*x.get_shape()[-1])

def conv_out_size_same(size, stride):
  """Compute the conv layer output size.
  
  Arguments:
    size {int} -- Input size.
    stride {int} -- conv stride.
  
  Returns:
    [int] -- conv layer output size
  """

  return int(math.ceil(float(size) / float(stride)))
  
def get_image(image_path, input_height, input_width,
              resize_height=64, resize_width=64,
              crop=True, grayscale=False):
  image = imread(image_path, grayscale)
  return transform(image, input_height, input_width,
                   resize_height, resize_width, crop)

def get_image_Slicization(image_path, patch_size, patch_step, grayscale=False):
  image = imread(image_path, grayscale).astype(np.float32)
  tmpTransform , nSlicization_shape = transform_Slicization(image/127.5 -1, patch_size, patch_step)  #[100:235,0:360]
  return tmpTransform.reshape(-1,patch_size[0],patch_size[1],1)


def get_image_SlicizationWithShape(image_path, patch_size, patch_step, grayscale=False):
  image = imread(image_path, grayscale).astype(np.float32)
  tmpTransform , nSlicization_shape = transform_Slicization(image/127.5 -1., patch_size, patch_step)   #[100:230,0:360]
  return tmpTransform.reshape(-1,patch_size[0],patch_size[1],1), nSlicization_shape

def transform_Slicization(image, patch_size, patch_step):
  return kh_make_patches(image,patch_size,patch_step)

def save_images(images, size, image_path):
  return imsave(inverse_transform(images), size, image_path)

def imread(path, grayscale = False):
  if (grayscale):
    #print(path)
    return scipy.misc.imread(path, flatten = True).astype(np.float)
  else:
    return scipy.misc.imread(path).astype(np.float)

def merge_images(images, size):
  return inverse_transform(images)

def merge(images, size):
  h, w = images.shape[1], images.shape[2]
  if (images.shape[3] in (3,4)):
    c = images.shape[3]
    img = np.zeros((h * size[0], w * size[1], c))
    try:
      for idx, image in enumerate(images):
        i = idx % size[1]
        j = idx // size[1]
        img[j * h:j * h + h, i * w:i * w + w, :] = image
      return img
    except:
      return img
  elif images.shape[3]==1:
    img = np.zeros((h * size[0], w * size[1]))
    for idx, image in enumerate(images):
      i = idx % size[1]
      j = idx // size[1]
      #print(idx)
      a = img[j * h:j * h + h, i * w:i * w + w]
      if(a.shape == image[:, :, 0].shape):
        img[j * h:j * h + h, i * w:i * w + w] = image[:, :, 0]
    return img
  else:
    raise ValueError('in merge(images,size) images parameter '
                     'must have dimensions: HxW or HxWx3 or HxWx4')

def imsave(images, size, path):
  image = np.squeeze(merge(images, size))
  return scipy.misc.imsave(path, image)

def center_crop(x, crop_h, crop_w,
                resize_h=64, resize_w=64):
  if crop_w is None:
    crop_w = crop_h
  h, w = x.shape[:2]
  j = int(round((h - crop_h)/2.))
  i = int(round((w - crop_w)/2.))
  return scipy.misc.imresize(
      x[j:j+crop_h, i:i+crop_w], [resize_h, resize_w])

def transform(image, input_height, input_width, 
              resize_height=64, resize_width=64, crop=True):
  if crop:
    cropped_image = center_crop(
      image, input_height, input_width, 
      resize_height, resize_width)
  else:
    cropped_image = scipy.misc.imresize(image, [resize_height, resize_width])
  return np.array(cropped_image)/127.5 - 1.

def inverse_transform(images):
  return (images+1.)/2.

def to_json(output_path, *layers):
  with open(output_path, "w") as layer_f:
    lines = ""
    for w, b, bn in layers:
      layer_idx = w.name.split('/')[0].split('h')[1]

      B = b.eval()

      if "lin/" in w.name:
        W = w.eval()
        depth = W.shape[1]
      else:
        W = np.rollaxis(w.eval(), 2, 0)
        depth = W.shape[0]

      biases = {"sy": 1, "sx": 1, "depth": depth, "w": ['%.2f' % elem for elem in list(B)]}
      if bn != None:
        gamma = bn.gamma.eval()
        beta = bn.beta.eval()

        gamma = {"sy": 1, "sx": 1, "depth": depth, "w": ['%.2f' % elem for elem in list(gamma)]}
        beta = {"sy": 1, "sx": 1, "depth": depth, "w": ['%.2f' % elem for elem in list(beta)]}
      else:
        gamma = {"sy": 1, "sx": 1, "depth": 0, "w": []}
        beta = {"sy": 1, "sx": 1, "depth": 0, "w": []}

      if "lin/" in w.name:
        fs = []
        for w in W.T:
          fs.append({"sy": 1, "sx": 1, "depth": W.shape[0], "w": ['%.2f' % elem for elem in list(w)]})

        lines += """
          var layer_%s = {
            "layer_type": "fc", 
            "sy": 1, "sx": 1, 
            "out_sx": 1, "out_sy": 1,
            "stride": 1, "pad": 0,
            "out_depth": %s, "in_depth": %s,
            "biases": %s,
            "gamma": %s,
            "beta": %s,
            "filters": %s
          };""" % (layer_idx.split('_')[0], W.shape[1], W.shape[0], biases, gamma, beta, fs)
      else:
        fs = []
        for w_ in W:
          fs.append({"sy": 5, "sx": 5, "depth": W.shape[3], "w": ['%.2f' % elem for elem in list(w_.flatten())]})

        lines += """
          var layer_%s = {
            "layer_type": "deconv", 
            "sy": 5, "sx": 5,
            "out_sx": %s, "out_sy": %s,
            "stride": 2, "pad": 1,
            "out_depth": %s, "in_depth": %s,
            "biases": %s,
            "gamma": %s,
            "beta": %s,
            "filters": %s
          };""" % (layer_idx, 2**(int(layer_idx)+2), 2**(int(layer_idx)+2),
               W.shape[0], W.shape[3], biases, gamma, beta, fs)
    layer_f.write(" ".join(lines.replace("'","").split()))

def make_gif(images, fname, duration=2, true_image=False):
  import moviepy.editor as mpy

  def make_frame(t):
    try:
      x = images[int(len(images)/duration*t)]
    except:
      x = images[-1]

    if true_image:
      return x.astype(np.uint8)
    else:
      return ((x+1)/2*255).astype(np.uint8)

  clip = mpy.VideoClip(make_frame, duration=duration)
  clip.write_gif(fname, fps = len(images) / duration)

def visualize(sess, dcgan, config, option):
  image_frame_dim = int(math.ceil(config.batch_size**.5))
  if option == 0:
    z_sample = np.random.uniform(-0.5, 0.5, size=(config.batch_size, dcgan.z_dim))
    samples = sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample})
    save_images(samples, [image_frame_dim, image_frame_dim], './samples/test_%s.png' % strftime("%Y%m%d%H%M%S", gmtime()))
  elif option == 1:
    values = np.arange(0, 1, 1./config.batch_size)
    for idx in xrange(100):
      print(" [*] %d" % idx)
      z_sample = np.zeros([config.batch_size, dcgan.z_dim])
      for kdx, z in enumerate(z_sample):
        z[idx] = values[kdx]

      if config.dataset == "mnist":
        y = np.random.choice(10, config.batch_size)
        y_one_hot = np.zeros((config.batch_size, 10))
        y_one_hot[np.arange(config.batch_size), y] = 1

        samples = sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample, dcgan.y: y_one_hot})
      else:
        samples = sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample})

      save_images(samples, [image_frame_dim, image_frame_dim], './samples/test_arange_%s.png' % (idx))
  elif option == 2:
    values = np.arange(0, 1, 1./config.batch_size)
    for idx in [random.randint(0, 99) for _ in xrange(100)]:
      print(" [*] %d" % idx)
      z = np.random.uniform(-0.2, 0.2, size=(dcgan.z_dim))
      z_sample = np.tile(z, (config.batch_size, 1))
      #z_sample = np.zeros([config.batch_size, dcgan.z_dim])
      for kdx, z in enumerate(z_sample):
        z[idx] = values[kdx]

      if config.dataset == "mnist":
        y = np.random.choice(10, config.batch_size)
        y_one_hot = np.zeros((config.batch_size, 10))
        y_one_hot[np.arange(config.batch_size), y] = 1

        samples = sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample, dcgan.y: y_one_hot})
      else:
        samples = sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample})

      try:
        make_gif(samples, './samples/test_gif_%s.gif' % (idx))
      except:
        save_images(samples, [image_frame_dim, image_frame_dim], './samples/test_%s.png' % strftime("%Y%m%d%H%M%S", gmtime()))
  elif option == 3:
    values = np.arange(0, 1, 1./config.batch_size)
    for idx in xrange(100):
      print(" [*] %d" % idx)
      z_sample = np.zeros([config.batch_size, dcgan.z_dim])
      for kdx, z in enumerate(z_sample):
        z[idx] = values[kdx]

      samples = sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample})
      make_gif(samples, './samples/test_gif_%s.gif' % (idx))
  elif option == 4:
    image_set = []
    values = np.arange(0, 1, 1./config.batch_size)

    for idx in xrange(100):
      print(" [*] %d" % idx)
      z_sample = np.zeros([config.batch_size, dcgan.z_dim])
      for kdx, z in enumerate(z_sample): z[idx] = values[kdx]

      image_set.append(sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample}))
      make_gif(image_set[-1], './samples/test_gif_%s.gif' % (idx))

    new_image_set = [merge(np.array([images[idx] for images in image_set]), [10, 10]) \
        for idx in range(64) + range(63, -1, -1)]
    make_gif(new_image_set, './samples/test_gif_merged.gif', duration=8)



from numpy.lib.stride_tricks import as_strided
import numbers
def kh_make_patches(arr, patch_shape=2, extraction_step=1):
    arr_ndim = arr.ndim
    if isinstance(patch_shape, numbers.Number):
        patch_shape = tuple([patch_shape] * arr_ndim)
    if isinstance(extraction_step, numbers.Number):
        extraction_step = tuple([extraction_step] * arr_ndim)

    patch_strides = arr.strides

    slices = [slice(None, None, st) for st in extraction_step]
    indexing_strides = arr[slices].strides

    patch_indices_shape = (np.array(arr.shape) - np.array(patch_shape)) // np.array(extraction_step) + 1

    shape = tuple(list(patch_indices_shape) + list(patch_shape))
    strides = tuple(list(indexing_strides) + list(patch_strides))

    patches = as_strided(arr, shape=shape, strides=strides)
    return patches, shape


	
def montage(images, saveto='montage.png'):
    """
      Draw all images as a montage separated by 1 pixel borders.
      Also saves the file to the destination specified by `saveto`.

    Arguments:
      images {np.array} -- Numpy array containing a list of images.

    Keyword Arguments:
      saveto {str} -- destination file name. (default: {'montage.png'})

    Returns:
      [np.array] -- The montage numpy array.
    """
    if isinstance(images, list):
        images = np.array(images)
    img_h = images.shape[1]
    img_w = images.shape[2]
    n_plots = int(np.ceil(np.sqrt(images.shape[0])))
    if len(images.shape) == 4 and images.shape[3] == 3:
        m = np.ones(
            (images.shape[1] * n_plots + n_plots + 1,
             images.shape[2] * n_plots + n_plots + 1, 3)) * 0.5
    else:
        m = np.ones(
            (images.shape[1] * n_plots + n_plots + 1,
             images.shape[2] * n_plots + n_plots + 1)) * 0.5
    for i in range(n_plots):
        for j in range(n_plots):
            this_filter = i * n_plots + j
            if this_filter < images.shape[0]:
                this_img = images[this_filter]
                m[1 + i + i * img_h:1 + i + (i + 1) * img_h,
                  1 + j + j * img_w:1 + j + (j + 1) * img_w] = this_img
    plt.imsave(arr=m, fname=saveto)
    return m