visualization_utils.py

# Copyright 2017 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================

"""A set of functions that are used for visualization.

These functions often receive an image, perform some visualization on the image.
The functions do not return a value, instead they modify the image itself.

"""
import collections
import numpy as np
import PIL.Image as Image
import PIL.ImageColor as ImageColor
import PIL.ImageDraw as ImageDraw
import PIL.ImageFont as ImageFont
import six
import tensorflow as tf
import speech_recognition as sr
import urllib2
import ssl

context = ssl._create_unverified_context()


_TITLE_LEFT_MARGIN = 10
_TITLE_TOP_MARGIN = 10
STANDARD_COLORS = [
    'AliceBlue', 'Chartreuse', 'Aqua', 'Aquamarine', 'Azure', 'Beige', 'Bisque',
    'BlanchedAlmond', 'BlueViolet', 'BurlyWood', 'CadetBlue', 'AntiqueWhite',
    'Chocolate', 'Coral', 'CornflowerBlue', 'Cornsilk', 'Crimson', 'Cyan',
    'DarkCyan', 'DarkGoldenRod', 'DarkGrey', 'DarkKhaki', 'DarkOrange',
    'DarkOrchid', 'DarkSalmon', 'DarkSeaGreen', 'DarkTurquoise', 'DarkViolet',
    'DeepPink', 'DeepSkyBlue', 'DodgerBlue', 'FireBrick', 'FloralWhite',
    'ForestGreen', 'Fuchsia', 'Gainsboro', 'GhostWhite', 'Gold', 'GoldenRod',
    'Salmon', 'Tan', 'HoneyDew', 'HotPink', 'IndianRed', 'Ivory', 'Khaki',
    'Lavender', 'LavenderBlush', 'LawnGreen', 'LemonChiffon', 'LightBlue',
    'LightCoral', 'LightCyan', 'LightGoldenRodYellow', 'LightGray', 'LightGrey',
    'LightGreen', 'LightPink', 'LightSalmon', 'LightSeaGreen', 'LightSkyBlue',
    'LightSlateGray', 'LightSlateGrey', 'LightSteelBlue', 'LightYellow', 'Lime',
    'LimeGreen', 'Linen', 'Magenta', 'MediumAquaMarine', 'MediumOrchid',
    'MediumPurple', 'MediumSeaGreen', 'MediumSlateBlue', 'MediumSpringGreen',
    'MediumTurquoise', 'MediumVioletRed', 'MintCream', 'MistyRose', 'Moccasin',
    'NavajoWhite', 'OldLace', 'Olive', 'OliveDrab', 'Orange', 'OrangeRed',
    'Orchid', 'PaleGoldenRod', 'PaleGreen', 'PaleTurquoise', 'PaleVioletRed',
    'PapayaWhip', 'PeachPuff', 'Peru', 'Pink', 'Plum', 'PowderBlue', 'Purple',
    'Red', 'RosyBrown', 'RoyalBlue', 'SaddleBrown', 'Green', 'SandyBrown',
    'SeaGreen', 'SeaShell', 'Sienna', 'Silver', 'SkyBlue', 'SlateBlue',
    'SlateGray', 'SlateGrey', 'Snow', 'SpringGreen', 'SteelBlue', 'GreenYellow',
    'Teal', 'Thistle', 'Tomato', 'Turquoise', 'Violet', 'Wheat', 'White',
    'WhiteSmoke', 'Yellow', 'YellowGreen'
]


def save_image_array_as_png(image, output_path):
  """Saves an image (represented as a numpy array) to PNG.

  Args:
    image: a numpy array with shape [height, width, 3].
    output_path: path to which image should be written.
  """
  image_pil = Image.fromarray(np.uint8(image)).convert('RGB')
  with tf.gfile.Open(output_path, 'w') as fid:
    image_pil.save(fid, 'PNG')


def encode_image_array_as_png_str(image):
  """Encodes a numpy array into a PNG string.

  Args:
    image: a numpy array with shape [height, width, 3].

  Returns:
    PNG encoded image string.
  """
  image_pil = Image.fromarray(np.uint8(image))
  output = six.BytesIO()
  image_pil.save(output, format='PNG')
  png_string = output.getvalue()
  output.close()
  return png_string


def draw_bounding_box_on_image_array(image,
                                     ymin,
                                     xmin,
                                     ymax,
                                     xmax,
                                     color='red',
                                     thickness=4,
                                     display_str_list=(),
                                     use_normalized_coordinates=True):
  """Adds a bounding box to an image (numpy array).

  Args:
    image: a numpy array with shape [height, width, 3].
    ymin: ymin of bounding box in normalized coordinates (same below).
    xmin: xmin of bounding box.
    ymax: ymax of bounding box.
    xmax: xmax of bounding box.
    color: color to draw bounding box. Default is red.
    thickness: line thickness. Default value is 4.
    display_str_list: list of strings to display in box
                      (each to be shown on its own line).
    use_normalized_coordinates: If True (default), treat coordinates
      ymin, xmin, ymax, xmax as relative to the image.  Otherwise treat
      coordinates as absolute.
  """
  image_pil = Image.fromarray(np.uint8(image)).convert('RGB')
  draw_bounding_box_on_image(image_pil, ymin, xmin, ymax, xmax, color,
                             thickness, display_str_list,
                             use_normalized_coordinates)
  np.copyto(image, np.array(image_pil))


def draw_bounding_box_on_image(image,
                               ymin,
                               xmin,
                               ymax,
                               xmax,
                               color='red',
                               thickness=4,
                               display_str_list=(),
                               use_normalized_coordinates=True):
  """Adds a bounding box to an image.

  Each string in display_str_list is displayed on a separate line above the
  bounding box in black text on a rectangle filled with the input 'color'.

  Args:
    image: a PIL.Image object.
    ymin: ymin of bounding box.
    xmin: xmin of bounding box.
    ymax: ymax of bounding box.
    xmax: xmax of bounding box.
    color: color to draw bounding box. Default is red.
    thickness: line thickness. Default value is 4.
    display_str_list: list of strings to display in box
                      (each to be shown on its own line).
    use_normalized_coordinates: If True (default), treat coordinates
      ymin, xmin, ymax, xmax as relative to the image.  Otherwise treat
      coordinates as absolute.
  """
  draw = ImageDraw.Draw(image)
  im_width, im_height = image.size
  if use_normalized_coordinates:
    (left, right, top, bottom) = (xmin * im_width, xmax * im_width,
                                  ymin * im_height, ymax * im_height)
  else:
    (left, right, top, bottom) = (xmin, xmax, ymin, ymax)
  draw.line([(left, top), (left, bottom), (right, bottom),
             (right, top), (left, top)], width=thickness, fill=color)
  try:
    font = ImageFont.truetype('arial.ttf', 24)
  except IOError:
    font = ImageFont.load_default()

  text_bottom = top
  # Reverse list and print from bottom to top.
  for display_str in display_str_list[::-1]:
    text_width, text_height = font.getsize(display_str)
    margin = np.ceil(0.05 * text_height)
    draw.rectangle(
        [(left, text_bottom - text_height - 2 * margin), (left + text_width,
                                                          text_bottom)],
        fill=color)
    draw.text(
        (left + margin, text_bottom - text_height - margin),
        display_str,
        fill='black',
        font=font)
    text_bottom -= text_height - 2 * margin


def draw_bounding_boxes_on_image_array(image,
                                       boxes,
                                       color='red',
                                       thickness=4,
                                       display_str_list_list=()):
  """Draws bounding boxes on image (numpy array).

  Args:
    image: a numpy array object.
    boxes: a 2 dimensional numpy array of [N, 4]: (ymin, xmin, ymax, xmax).
           The coordinates are in normalized format between [0, 1].
    color: color to draw bounding box. Default is red.
    thickness: line thickness. Default value is 4.
    display_str_list_list: list of list of strings.
                           a list of strings for each bounding box.
                           The reason to pass a list of strings for a
                           bounding box is that it might contain
                           multiple labels.

  Raises:
    ValueError: if boxes is not a [N, 4] array
  """
  image_pil = Image.fromarray(image)
  draw_bounding_boxes_on_image(image_pil, boxes, color, thickness,
                               display_str_list_list)
  np.copyto(image, np.array(image_pil))


def draw_bounding_boxes_on_image(image,
                                 boxes,
                                 color='red',
                                 thickness=4,
                                 display_str_list_list=()):
  """Draws bounding boxes on image.

  Args:
    image: a PIL.Image object.
    boxes: a 2 dimensional numpy array of [N, 4]: (ymin, xmin, ymax, xmax).
           The coordinates are in normalized format between [0, 1].
    color: color to draw bounding box. Default is red.
    thickness: line thickness. Default value is 4.
    display_str_list_list: list of list of strings.
                           a list of strings for each bounding box.
                           The reason to pass a list of strings for a
                           bounding box is that it might contain
                           multiple labels.

  Raises:
    ValueError: if boxes is not a [N, 4] array
  """
  boxes_shape = boxes.shape
  if not boxes_shape:
    return
  if len(boxes_shape) != 2 or boxes_shape[1] != 4:
    raise ValueError('Input must be of size [N, 4]')
  for i in range(boxes_shape[0]):
    display_str_list = ()
    if display_str_list_list:
      display_str_list = display_str_list_list[i]
    draw_bounding_box_on_image(image, boxes[i, 0], boxes[i, 1], boxes[i, 2],
                               boxes[i, 3], color, thickness, display_str_list)


def draw_keypoints_on_image_array(image,
                                  keypoints,
                                  color='red',
                                  radius=2,
                                  use_normalized_coordinates=True):
  """Draws keypoints on an image (numpy array).

  Args:
    image: a numpy array with shape [height, width, 3].
    keypoints: a numpy array with shape [num_keypoints, 2].
    color: color to draw the keypoints with. Default is red.
    radius: keypoint radius. Default value is 2.
    use_normalized_coordinates: if True (default), treat keypoint values as
      relative to the image.  Otherwise treat them as absolute.
  """
  image_pil = Image.fromarray(np.uint8(image)).convert('RGB')
  draw_keypoints_on_image(image_pil, keypoints, color, radius,
                          use_normalized_coordinates)
  np.copyto(image, np.array(image_pil))


def draw_keypoints_on_image(image,
                            keypoints,
                            color='red',
                            radius=2,
                            use_normalized_coordinates=True):
  """Draws keypoints on an image.

  Args:
    image: a PIL.Image object.
    keypoints: a numpy array with shape [num_keypoints, 2].
    color: color to draw the keypoints with. Default is red.
    radius: keypoint radius. Default value is 2.
    use_normalized_coordinates: if True (default), treat keypoint values as
      relative to the image.  Otherwise treat them as absolute.
  """
  draw = ImageDraw.Draw(image)
  im_width, im_height = image.size
  keypoints_x = [k[1] for k in keypoints]
  keypoints_y = [k[0] for k in keypoints]
  if use_normalized_coordinates:
    keypoints_x = tuple([im_width * x for x in keypoints_x])
    keypoints_y = tuple([im_height * y for y in keypoints_y])
  for keypoint_x, keypoint_y in zip(keypoints_x, keypoints_y):
    draw.ellipse([(keypoint_x - radius, keypoint_y - radius),
                  (keypoint_x + radius, keypoint_y + radius)],
                 outline=color, fill=color)


def draw_mask_on_image_array(image, mask, color='red', alpha=0.7):
  """Draws mask on an image.

  Args:
    image: uint8 numpy array with shape (img_height, img_height, 3)
    mask: a float numpy array of shape (img_height, img_height) with
      values between 0 and 1
    color: color to draw the keypoints with. Default is red.
    alpha: transparency value between 0 and 1. (default: 0.7)

  Raises:
    ValueError: On incorrect data type for image or masks.
  """
  if image.dtype != np.uint8:
    raise ValueError('`image` not of type np.uint8')
  if mask.dtype != np.float32:
    raise ValueError('`mask` not of type np.float32')
  if np.any(np.logical_or(mask > 1.0, mask < 0.0)):
    raise ValueError('`mask` elements should be in [0, 1]')
  rgb = ImageColor.getrgb(color)
  pil_image = Image.fromarray(image)

  solid_color = np.expand_dims(
      np.ones_like(mask), axis=2) * np.reshape(list(rgb), [1, 1, 3])
  pil_solid_color = Image.fromarray(np.uint8(solid_color)).convert('RGBA')
  pil_mask = Image.fromarray(np.uint8(255.0*alpha*mask)).convert('L')
  pil_image = Image.composite(pil_solid_color, pil_image, pil_mask)
  np.copyto(image, np.array(pil_image.convert('RGB')))

def get_input():
	global obj

	obj = urllib2.urlopen('http://8f1670b0.ngrok.io/text').read().replace('\n', '')
	
'''
	#obj = raw_input("Put yo shizz: ") 
	bs = urllib2.urlopen("https://10.89.115.83:8080/audio.wav", context=context)

	r = sr.Recognizer()
	with sr.WavFile(bs) as source:
    		print("Say something!")
    		audio = r.listen(source)
 
# Speech recognition using Google Speech Recognition
	try:
    		# for testing purposes, we're just using the default API key
    		# to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
    		# instead of `r.recognize_google(audio)`
		obj = r.recognize_google(audio)
    		print("You said: " + obj)
	except sr.UnknownValueError:
    		print("Google Speech Recognition could not understand audio")
	except sr.RequestError as e:
    		print("Could not request results from Google Speech Recognition service; {0}".format(e))
'''


def visualize_boxes_and_labels_on_image_array(image,
                                              boxes,
                                              classes,
                                              scores,
                                              category_index,
                                              instance_masks=None,
                                              keypoints=None,
                                              use_normalized_coordinates=False,
                                              max_boxes_to_draw=20,
                                              min_score_thresh=.5,
                                              agnostic_mode=False,
                                              line_thickness=4):
  """Overlay labeled boxes on an image with formatted scores and label names.

  This function groups boxes that correspond to the same location
  and creates a display string for each detection and overlays these
  on the image.  Note that this function modifies the image array in-place
  and does not return anything.

  Args:
    image: uint8 numpy array with shape (img_height, img_width, 3)
    boxes: a numpy array of shape [N, 4]
    classes: a numpy array of shape [N]
    scores: a numpy array of shape [N] or None.  If scores=None, then
      this function assumes that the boxes to be plotted are groundtruth
      boxes and plot all boxes as black with no classes or scores.
    category_index: a dict containing category dictionaries (each holding
      category index `id` and category name `name`) keyed by category indices.
    instance_masks: a numpy array of shape [N, image_height, image_width], can
      be None
    keypoints: a numpy array of shape [N, num_keypoints, 2], can
      be None
    use_normalized_coordinates: whether boxes is to be interpreted as
      normalized coordinates or not.
    max_boxes_to_draw: maximum number of boxes to visualize.  If None, draw
      all boxes.
    min_score_thresh: minimum score threshold for a box to be visualized
    agnostic_mode: boolean (default: False) controlling whether to evaluate in
      class-agnostic mode or not.  This mode will display scores but ignore
      classes.
    line_thickness: integer (default: 4) controlling line width of the boxes.
  """
  # Create a display string (and color) for every box location, group any boxes
  # that correspond to the same location.
  box_to_display_str_map = collections.defaultdict(list)
  box_to_color_map = collections.defaultdict(str)
  box_to_instance_masks_map = {}
  box_to_keypoints_map = collections.defaultdict(list)
  if not max_boxes_to_draw:
    max_boxes_to_draw = boxes.shape[0]
  for i in range(min(max_boxes_to_draw, boxes.shape[0])):
    if scores is None or scores[i] > min_score_thresh:
      box = tuple(boxes[i].tolist())
      if instance_masks is not None:
        box_to_instance_masks_map[box] = instance_masks[i]
      if keypoints is not None:
        box_to_keypoints_map[box].extend(keypoints[i])
      if scores is None:
        box_to_color_map[box] = 'black'
      else:
        if not agnostic_mode:
          if classes[i] in category_index.keys():
            class_name = category_index[classes[i]]['name']
	    if class_name == 'on9':
		break
	    elif class_name == obj:
		print("Found " + obj)
		#urllib2.urlopen('http://6ed37409.ngrok.io/buz')		
          else:
            class_name = 'N/A'
          display_str = '{}: {}%'.format(
              class_name,
              int(100*scores[i]))
        else:
          display_str = 'score: {}%'.format(int(100 * scores[i]))
        box_to_display_str_map[box].append(display_str)
        if agnostic_mode:
          box_to_color_map[box] = 'DarkOrange'
        else:
          box_to_color_map[box] = STANDARD_COLORS[
              classes[i] % len(STANDARD_COLORS)]

  # Draw all boxes onto image.
  for box, color in box_to_color_map.items():
    ymin, xmin, ymax, xmax = box
    if instance_masks is not None:
      draw_mask_on_image_array(
          image,
          box_to_instance_masks_map[box],
          color=color
      )
    draw_bounding_box_on_image_array(
        image,
        ymin,
        xmin,
        ymax,
        xmax,
        color=color,
        thickness=line_thickness,
        display_str_list=box_to_display_str_map[box],
        use_normalized_coordinates=use_normalized_coordinates)

    if keypoints is not None:
      draw_keypoints_on_image_array(
          image,
          box_to_keypoints_map[box],
          color=color,
          radius=line_thickness / 2,
          use_normalized_coordinates=use_normalized_coordinates)

'''
    if class_name == obj:
	if (xmin + xmax)/2  <  0.3 :
		print("right")
    	elif (xmin + xmax)/2  >  0.7 :
		print("left") 
'''