fix inference.py for TF 1.0 && reformat using pep8 code style

.gitignore

@@ -0,0 +1,99 @@
+output
+*.npy
+*.ckpt
+*.ipynb
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# dotenv
+.env
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+
+# Rope project settings
+.ropeproject

.travis.yml

@@ -9,9 +9,9 @@ virtualenv:
 install:
   - echo $TRAVIS_PYTHON_VERSION
   - pip install -U -r ./requirements.txt
-  - pip install -U tensorflow==0.12.1
+  - pip install -U https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-1.0.0-cp27-none-linux_x86_64.whl
   - wget https://www.dropbox.com/s/cd0drt6t9q1mwg0/deeplab_resnet.ckpt?dl=1 -O deeplab_resnet.ckpt
-  
+
 script:
   - python inference.py ./misc/2007_000129.jpg ./deeplab_resnet.ckpt
   - python train.py --batch-size 1 --data-dir ./ --data-list ./dataset/debug.txt --num-steps 1 --random-mirror --random-scale --restore-from ./deeplab_resnet.ckpt --save-num-images 1

deeplab_resnet/image_reader.py

@@ -4,7 +4,9 @@
 import tensorflow as tf
 
 IGNORE_LABEL = 255
-IMG_MEAN = np.array((104.00698793,116.66876762,122.67891434), dtype=np.float32)
+IMG_MEAN = np.array((104.00698793, 116.66876762,
+                     122.67891434), dtype=np.float32)
+
 
 def image_scaling(img, label):
     """
@@ -14,17 +16,20 @@ def image_scaling(img, label):
       img: Training image to scale.
       label: Segmentation mask to scale.
     """
-
-    scale = tf.random_uniform([1], minval=0.5, maxval=1.5, dtype=tf.float32, seed=None)
-    h_new = tf.to_int32(tf.mul(tf.to_float(tf.shape(img)[0]), scale))
-    w_new = tf.to_int32(tf.mul(tf.to_float(tf.shape(img)[1]), scale))
-    new_shape = tf.squeeze(tf.pack([h_new, w_new]), squeeze_dims=[1])
+
+    scale = tf.random_uniform(
+        [1], minval=0.5, maxval=1.5, dtype=tf.float32, seed=None)
+    h_new = tf.to_int32(tf.multiply(tf.to_float(tf.shape(img)[0]), scale))
+    w_new = tf.to_int32(tf.multiply(tf.to_float(tf.shape(img)[1]), scale))
+    new_shape = tf.squeeze(tf.stack([h_new, w_new]), squeeze_dims=[1])
     img = tf.image.resize_images(img, new_shape)
-    label = tf.image.resize_nearest_neighbor(tf.expand_dims(label, 0), new_shape)
+    label = tf.image.resize_nearest_neighbor(
+        tf.expand_dims(label, 0), new_shape)
     label = tf.squeeze(label, squeeze_dims=[0])
-   
+
     return img, label
 
+
 def image_mirroring(img, label):
     """
     Randomly mirrors the images.
@@ -33,13 +38,20 @@ def image_mirroring(img, label):
       img: Training image to mirror.
       label: Segmentation mask to mirror.
     """
-
-    distort_left_right_random = tf.random_uniform([1], 0, 1.0, dtype=tf.float32)[0]
-    mirror = tf.less(tf.pack([1.0, distort_left_right_random, 1.0]), 0.5)
+
+    distort_left_right_random = tf.random_uniform(
+        [1], 0, 1.0, dtype=tf.float32)[0]
+    mirror = tf.less(tf.stack([1.0, distort_left_right_random, 1.0]),
+                     0.5)
+    # tf.reverse() now takes indices of axes to be reversed.
+    # so we should convert boolean_mask into indices
+    mirror = tf.boolean_mask([0, 1, 2], mirror)
+
     img = tf.reverse(img, mirror)
     label = tf.reverse(label, mirror)
     return img, label
 
+
 def random_crop_and_pad_image_and_labels(image, label, crop_h, crop_w, ignore_label=255):
     """
     Randomly crop and pads the input images.
@@ -53,31 +65,34 @@ def random_crop_and_pad_image_and_labels(image, label, crop_h, crop_w, ignore_la
     """
 
     label = tf.cast(label, dtype=tf.float32)
-    label = label - ignore_label # Needs to be subtracted and later added due to 0 padding.
-    combined = tf.concat(2, [image, label]) 
+    # Needs to be subtracted and later added due to 0 padding.
+    label = label - ignore_label
+    combined = tf.concat([image, label], axis=2)
     image_shape = tf.shape(image)
-    combined_pad = tf.image.pad_to_bounding_box(combined, 0, 0, tf.maximum(crop_h, image_shape[0]), tf.maximum(crop_w, image_shape[1]))
-
+    combined_pad = tf.image.pad_to_bounding_box(combined, 0, 0, tf.maximum(
+        crop_h, image_shape[0]), tf.maximum(crop_w, image_shape[1]))
+
     last_image_dim = tf.shape(image)[-1]
     last_label_dim = tf.shape(label)[-1]
-    combined_crop = tf.random_crop(combined_pad, [crop_h,crop_w,4])
+    combined_crop = tf.random_crop(combined_pad, [crop_h, crop_w, 4])
     img_crop = combined_crop[:, :, :last_image_dim]
     label_crop = combined_crop[:, :, last_image_dim:]
     label_crop = label_crop + ignore_label
     label_crop = tf.cast(label_crop, dtype=tf.uint8)
-    
-    # Set static shape so that tensorflow knows shape at compile time. 
+
+    # Set static shape so that tensorflow knows shape at compile time.
     img_crop.set_shape((crop_h, crop_w, 3))
-    label_crop.set_shape((crop_h,crop_w, 1))
-    return img_crop, label_crop  
+    label_crop.set_shape((crop_h, crop_w, 1))
+    return img_crop, label_crop
+
 
 def read_labeled_image_list(data_dir, data_list):
     """Reads txt file containing paths to images and ground truth masks.
-    
+
     Args:
       data_dir: path to the directory with images and masks.
       data_list: path to the file with lines of the form '/path/to/image /path/to/mask'.
-       
+
     Returns:
       Two lists with all file names for images and masks, respectively.
     """
@@ -87,15 +102,17 @@ def read_labeled_image_list(data_dir, data_list):
     for line in f:
         try:
             image, mask = line.strip("\n").split(' ')
-        except ValueError: # Adhoc for test.
+        except ValueError:  # Adhoc for test.
             image = mask = line.strip("\n")
         images.append(data_dir + image)
         masks.append(data_dir + mask)
     return images, masks
 
-def read_images_from_disk(input_queue, input_size, random_scale, random_mirror): # optional pre-processing arguments
+
+# optional pre-processing arguments
+def read_images_from_disk(input_queue, input_size, random_scale, random_mirror):
     """Read one image and its corresponding mask with optional pre-processing.
-    
+
     Args:
       input_queue: tf queue with paths to the image and its mask.
       input_size: a tuple with (height, width) values.
@@ -104,17 +121,17 @@ def read_images_from_disk(input_queue, input_size, random_scale, random_mirror):
                     to random crop.
       random_mirror: whether to randomly mirror the images prior
                     to random crop.
-      
+
     Returns:
       Two tensors: the decoded image and its mask.
     """
 
     img_contents = tf.read_file(input_queue[0])
     label_contents = tf.read_file(input_queue[1])
-    
+
     img = tf.image.decode_jpeg(img_contents, channels=3)
-    img_r, img_g, img_b = tf.split(split_dim=2, num_split=3, value=img)
-    img = tf.cast(tf.concat(2, [img_b, img_g, img_r]), dtype=tf.float32)
+    img_r, img_g, img_b = tf.split(value=img, num_or_size_splits=3, axis=2)
+    img = tf.cast(tf.concat([img_b, img_g, img_r], axis=2), dtype=tf.float32)
     # Extract mean.
     img -= IMG_MEAN
 
@@ -132,10 +149,12 @@ def read_images_from_disk(input_queue, input_size, random_scale, random_mirror):
             img, label = image_mirroring(img, label)
 
         # Randomly crops the images and labels.
-        img, label = random_crop_and_pad_image_and_labels(img, label, h, w, IGNORE_LABEL)
+        img, label = random_crop_and_pad_image_and_labels(
+            img, label, h, w, IGNORE_LABEL)
 
     return img, label
 
+
 class ImageReader(object):
     '''Generic ImageReader which reads images and corresponding segmentation
        masks from the disk, and enqueues them into a TensorFlow queue.
@@ -144,7 +163,7 @@ class ImageReader(object):
     def __init__(self, data_dir, data_list, input_size, random_scale,
                  random_mirror, coord):
         '''Initialise an ImageReader.
-        
+
         Args:
           data_dir: path to the directory with images and masks.
           data_list: path to the file with lines of the form '/path/to/image /path/to/mask'.
@@ -157,22 +176,25 @@ def __init__(self, data_dir, data_list, input_size, random_scale,
         self.data_list = data_list
         self.input_size = input_size
         self.coord = coord
-
-        self.image_list, self.label_list = read_labeled_image_list(self.data_dir, self.data_list)
+
+        self.image_list, self.label_list = read_labeled_image_list(
+            self.data_dir, self.data_list)
         self.images = tf.convert_to_tensor(self.image_list, dtype=tf.string)
         self.labels = tf.convert_to_tensor(self.label_list, dtype=tf.string)
         self.queue = tf.train.slice_input_producer([self.images, self.labels],
-                                                   shuffle=input_size is not None) # not shuffling if it is val
-        self.image, self.label = read_images_from_disk(self.queue, self.input_size, random_scale, random_mirror) 
+                                                   shuffle=input_size is not None)  # not shuffling if it is val
+        self.image, self.label = read_images_from_disk(
+            self.queue, self.input_size, random_scale, random_mirror)
 
     def dequeue(self, num_elements):
         '''Pack images and labels into a batch.
-        
+
         Args:
           num_elements: the batch size.
-          
+
         Returns:
-          Two tensors of size (batch_size, h, w, {3, 1}) for images and masks.'''
+          Two tensors of size (batch_size, h, w, {3, 1}) for images and masks.
+        '''
         image_batch, label_batch = tf.train.batch([self.image, self.label],
                                                   num_elements)
         return image_batch, label_batch