In [1]:
#@title Imports
import os
from io import BytesIO
import tarfile
import tempfile
from six.moves import urllib
from matplotlib import gridspec
from matplotlib import pyplot as plt
import numpy as np
from PIL import Image
import tensorflow as tf
In [2]:
#@title Helper methods
class DeepLabModel(object):
"""Class to load deeplab model and run inference."""
INPUT_TENSOR_NAME = 'ImageTensor:0'
OUTPUT_TENSOR_NAME = 'SemanticPredictions:0'
INPUT_SIZE = 513
FROZEN_GRAPH_NAME = 'frozen_inference_graph'
def __init__(self, tarball_path):
"""Creates and loads pretrained deeplab model."""
self.graph = tf.Graph()
graph_def = None
# Extract frozen graph from tar archive.
tar_file = tarfile.open(tarball_path)
for tar_info in tar_file.getmembers():
if self.FROZEN_GRAPH_NAME in os.path.basename(tar_info.name):
file_handle = tar_file.extractfile(tar_info)
graph_def = tf.GraphDef.FromString(file_handle.read())
break
tar_file.close()
if graph_def is None:
raise RuntimeError('Cannot find inference graph in tar archive.')
with self.graph.as_default():
tf.import_graph_def(graph_def, name='')
self.sess = tf.Session(graph=self.graph)
def run(self, image):
"""Runs inference on a single image.
Args:
image: A PIL.Image object, raw input image.
Returns:
resized_image: RGB image resized from original input image.
seg_map: Segmentation map of `resized_image`.
"""
width, height = image.size
resize_ratio = 1.0 * self.INPUT_SIZE / max(width, height)
target_size = (int(resize_ratio * width), int(resize_ratio * height))
resized_image = image.convert('RGB').resize(target_size, Image.ANTIALIAS)
batch_seg_map = self.sess.run(
self.OUTPUT_TENSOR_NAME,
feed_dict={self.INPUT_TENSOR_NAME: [np.asarray(resized_image)]})
seg_map = batch_seg_map[0]
return resized_image, seg_map
def create_pascal_label_colormap():
"""Creates a label colormap used in PASCAL VOC segmentation benchmark.
Returns:
A Colormap for visualizing segmentation results.
"""
colormap = np.zeros((256, 3), dtype=int)
ind = np.arange(256, dtype=int)
for shift in reversed(range(8)):
for channel in range(3):
colormap[:, channel] |= ((ind >> channel) & 1) << shift
ind >>= 3
return colormap
def label_to_color_image(label):
"""Adds color defined by the dataset colormap to the label.
Args:
label: A 2D array with integer type, storing the segmentation label.
Returns:
result: A 2D array with floating type. The element of the array
is the color indexed by the corresponding element in the input label
to the PASCAL color map.
Raises:
ValueError: If label is not of rank 2 or its value is larger than color
map maximum entry.
"""
if label.ndim != 2:
raise ValueError('Expect 2-D input label')
colormap = create_pascal_label_colormap()
if np.max(label) >= len(colormap):
raise ValueError('label value too large.')
return colormap[label]
def vis_segmentation(image, seg_map):
"""Visualizes input image, segmentation map and overlay view."""
plt.figure(figsize=(15, 5))
grid_spec = gridspec.GridSpec(1, 4, width_ratios=[6, 6, 6, 1])
plt.subplot(grid_spec[0])
plt.imshow(image)
plt.axis('off')
plt.title('input image')
plt.subplot(grid_spec[1])
seg_image = label_to_color_image(seg_map).astype(np.uint8)
plt.imshow(seg_image)
plt.axis('off')
plt.title('segmentation map')
plt.subplot(grid_spec[2])
plt.imshow(image)
plt.imshow(seg_image, alpha=0.7)
plt.axis('off')
plt.title('segmentation overlay')
unique_labels = np.unique(seg_map)
ax = plt.subplot(grid_spec[3])
plt.imshow(
FULL_COLOR_MAP[unique_labels].astype(np.uint8), interpolation='nearest')
ax.yaxis.tick_right()
plt.yticks(range(len(unique_labels)), LABEL_NAMES[unique_labels])
plt.xticks([], [])
ax.tick_params(width=0.0)
plt.grid('off')
plt.show()
LABEL_NAMES = np.asarray([
'background', 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus',
'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike',
'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tv'
])
FULL_LABEL_MAP = np.arange(len(LABEL_NAMES)).reshape(len(LABEL_NAMES), 1)
FULL_COLOR_MAP = label_to_color_image(FULL_LABEL_MAP)
In [3]:
#@title Some more helper functions
def run_visualization(url):
"""Inferences DeepLab model and visualizes result."""
try:
f = urllib.request.urlopen(url)
jpeg_str = f.read()
original_im = Image.open(BytesIO(jpeg_str))
except IOError:
print('Cannot retrieve image. Please check url: ' + url)
return
print('running deeplab on image %s...' % url)
resized_im, seg_map = MODEL.run(original_im)
vis_segmentation(resized_im, seg_map)
def show_images(images, cols = 1, titles = None):
"""Display a list of images in a single figure with matplotlib.
Parameters
---------
images: List of np.arrays compatible with plt.imshow.
cols (Default = 1): Number of columns in figure (number of rows is
set to np.ceil(n_images/float(cols))).
titles: List of titles corresponding to each image. Must have
the same length as titles.
"""
assert((titles is None) or (len(images) == len(titles)))
n_images = len(images)
if titles is None: titles = ['Image (%d)' % i for i in range(1,n_images + 1)]
fig = plt.figure()
for n, (image, title) in enumerate(zip(images, titles)):
a = fig.add_subplot(cols, np.ceil(n_images/float(cols)), n + 1)
plt.imshow(image)
a.set_title(title)
fig.set_size_inches(np.array(fig.get_size_inches()) * n_images)
plt.show()
def image_grabber(url):
f = urllib.request.urlopen(url)
jpeg_str = f.read()
original_im = Image.open(BytesIO(jpeg_str))
return original_im
In [4]:
#@title Select and download models {display-mode: "form"}
MODEL_NAME = 'mobilenetv2_coco_voctrainaug' # @param ['mobilenetv2_coco_voctrainaug', 'mobilenetv2_coco_voctrainval', 'xception_coco_voctrainaug', 'xception_coco_voctrainval']
_DOWNLOAD_URL_PREFIX = 'http://download.tensorflow.org/models/'
_MODEL_URLS = {
'mobilenetv2_coco_voctrainaug':
'deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz',
'mobilenetv2_coco_voctrainval':
'deeplabv3_mnv2_pascal_trainval_2018_01_29.tar.gz',
'xception_coco_voctrainaug':
'deeplabv3_pascal_train_aug_2018_01_04.tar.gz',
'xception_coco_voctrainval':
'deeplabv3_pascal_trainval_2018_01_04.tar.gz',
}
_TARBALL_NAME = 'deeplab_model.tar.gz'
model_dir = tempfile.mkdtemp()
tf.gfile.MakeDirs(model_dir)
### PPROXY Settings
# proxy = urllib.request.ProxyHandler({'http': '0.0.0.0:8123'})
# opener = urllib.request.build_opener(proxy)
# urllib.request.install_opener(opener)
### End of PPROXY Settings
download_path = os.path.join(model_dir, _TARBALL_NAME)
print('downloading model, this might take a while...')
urllib.request.urlretrieve(_DOWNLOAD_URL_PREFIX + _MODEL_URLS[MODEL_NAME],
download_path)
print('download completed! loading DeepLab model...')
MODEL = DeepLabModel(download_path)
print('model loaded successfully!')
In [5]:
_URL_BANK = [ 'https://upload.wikimedia.org/wikipedia/commons/7/70/Rorschach_blot_01.jpg',
'https://upload.wikimedia.org/wikipedia/commons/b/bc/Rorschach_blot_02.jpg',
'https://upload.wikimedia.org/wikipedia/commons/8/82/Rorschach_blot_03.jpg',
'https://upload.wikimedia.org/wikipedia/commons/1/14/Rorschach_blot_04.jpg',
'https://upload.wikimedia.org/wikipedia/commons/5/54/Rorschach_blot_05.jpg',
'https://upload.wikimedia.org/wikipedia/commons/7/74/Rorschach_blot_06.jpg',
'https://upload.wikimedia.org/wikipedia/commons/2/2d/Rorschach_blot_07.jpg',
'https://upload.wikimedia.org/wikipedia/commons/4/43/Rorschach_blot_08.jpg',
'https://upload.wikimedia.org/wikipedia/commons/b/b7/Rorschach_blot_09.jpg' ]
In [17]:
#@title Performing the Test
# Downloading images
image_list = [image_grabber(url) for url in _URL_BANK]
# get segmentation map for each image
packed = [MODEL.run(img) for img in image_list]
resized_images = [item[0] for item in packed]
seg_maps = [item[1] for item in packed]
# visualize segment maps
for i in range(len(packed)):
vis_segmentation(resized_images[i], seg_maps[i])
In [ ]: