Merge pull request #1861 from derekjchow/master

Update directories in running_pets.md

object_detection/README.md

@@ -54,6 +54,17 @@ Extras:
       Exporting a trained model for inference</a><br>
 * <a href='g3doc/defining_your_own_model.md'>
       Defining your own model architecture</a><br>
+* <a href='g3doc/using_your_own_dataset.md'>
+      Bringing in your own dataset</a><br>
+
+## Getting Help
+
+Please report bugs to the tensorflow/models/ Github
+[issue tracker](https://github.com/tensorflow/models/issues), prefixing the
+issue name with "object_detection". To get help with issues you may encounter
+using the Tensorflow Object Detection API, create a new question on
+[StackOverflow](https://stackoverflow.com/) with the tags "tensorflow" and
+"object-detection".
 
 ## Release information
 

object_detection/g3doc/using_your_own_dataset.md

+# Preparing Inputs
+
+To use your own dataset in Tensorflow Object Detection API, you must convert it
+into the [TFRecord file format](https://www.tensorflow.org/api_guides/python/python_io#tfrecords_format_details).
+This document outlines how to write a script to generate the TFRecord file.
+
+## Label Maps
+
+Each dataset is required to have a label map associated with it. This label map
+defines a mapping from string class names to integer class Ids. The label map
+should be a `StringIntLabelMap` text protobuf. Sample label maps can be found in
+object_detection/data. Label maps should always start from id 1.
+
+## Dataset Requirements
+
+For every example in your dataset, you should have the following information:
+
+1. An RGB image for the dataset encoded as jpeg or png.
+2. A list of bounding boxes for the image. Each bounding box should contain:
+    1. A bounding box coordinates (with origin in top left corner) defined by 4
+       floating point numbers [ymin, xmin, ymax, xmax]. Note that we store the
+       _normalized_ coordinates (x / width, y / height) in the TFRecord dataset.
+    2. The class of the object in the bounding box.
+
+# Example Image
+
+Consider the following image:
+
+![Example Image](img/example_cat.jpg "Example Image")
+
+with the following label map:
+
+```
+item {
+  id: 1
+  name: 'Cat'
+}
+
+
+item {
+  id: 2
+  name: 'Dog'
+}
+```
+
+We can generate a tf.Example proto for this image using the following code:
+
+```python
+
+def create_cat_tf_example(encoded_cat_image_data):
+   """Creates a tf.Example proto from sample cat image.
+
+  Args:
+    encoded_cat_image_data: The jpg encoded data of the cat image.
+
+  Returns:
+    example: The created tf.Example.
+  """
+
+  height = 1032.0
+  width = 1200.0
+  filename = 'example_cat.jpg'
+  image_format = b'jpg'
+
+  xmins = [322.0 / 1200.0]
+  xmaxs = [1062.0 / 1200.0]
+  ymins = [174.0 / 1032.0]
+  ymaxs = [761.0 / 1032.0]
+  classes_text = ['Cat']
+  classes = [1]
+
+  tf_example = tf.train.Example(features=tf.train.Features(feature={
+      'image/height': dataset_util.int64_feature(height),
+      'image/width': dataset_util.int64_feature(width),
+      'image/filename': dataset_util.bytes_feature(filename),
+      'image/source_id': dataset_util.bytes_feature(filename),
+      'image/encoded': dataset_util.bytes_feature(encoded_image_data),
+      'image/format': dataset_util.bytes_feature(image_format),
+      'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
+      'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
+      'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
+      'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
+      'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
+      'image/object/class/label': dataset_util.int64_list_feature(classes),
+  }))
+  return tf_example
+```
+
+## Conversion Script Outline
+
+A typical conversion script will look like the following:
+
+```python
+
+import tensorflow as tf
+
+from object_detection.utils import dataset_util
+
+
+flags = tf.app.flags
+flags.DEFINE_string('output_path', '', 'Path to output TFRecord')
+FLAGS = flags.FLAGS
+
+
+def create_tf_example(example):
+  # TODO(user): Populate the following variables from your example.
+  height = None # Image height
+  width = None # Image width
+  filename = None # Filename of the image. Empty if image is not from file
+  encoded_image_data = None # Encoded image bytes
+  image_format = None # b'jpeg' or b'png'
+
+  xmins = [] # List of normalized left x coordinates in bounding box (1 per box)
+  xmaxs = [] # List of normalized right x coordinates in bounding box
+             # (1 per box)
+  ymins = [] # List of normalized top y coordinates in bounding box (1 per box)
+  ymaxs = [] # List of normalized bottom y coordinates in bounding box
+             # (1 per box)
+  classes_text = [] # List of string class name of bounding box (1 per box)
+  classes = [] # List of integer class id of bounding box (1 per box)
+
+  tf_example = tf.train.Example(features=tf.train.Features(feature={
+      'image/height': dataset_util.int64_feature(height),
+      'image/width': dataset_util.int64_feature(width),
+      'image/filename': dataset_util.bytes_feature(filename),
+      'image/source_id': dataset_util.bytes_feature(filename),
+      'image/encoded': dataset_util.bytes_feature(encoded_image_data),
+      'image/format': dataset_util.bytes_feature(image_format),
+      'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
+      'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
+      'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
+      'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
+      'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
+      'image/object/class/label': dataset_util.int64_list_feature(classes),
+  }))
+  return tf_example
+
+
+def main(_):
+  writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
+
+  # TODO(user): Write code to read in your dataset to examples variable
+
+  for example in examples:
+    tf_example = create_tf_example(example)
+    writer.write(tf_example.SerializeToString())
+
+  writer.close()
+
+
+if __name__ == '__main__':
+  tf.app.run()
+
+```
+
+Note: You may notice additional fields in some other datasets. They are
+currently unused by the API and are optional.

object_detection/utils/label_map_util.py

@@ -22,6 +22,20 @@ from google.protobuf import text_format
 from object_detection.protos import string_int_label_map_pb2
 
 
+def _validate_label_map(label_map):
+  """Checks if a label map is valid.
+
+  Args:
+    label_map: StringIntLabelMap to validate.
+
+  Raises:
+    ValueError: if label map is invalid.
+  """
+  for item in label_map.item:
+    if item.id < 1:
+      raise ValueError('Label map ids should be >= 1.')
+
+
 def create_category_index(categories):
   """Creates dictionary of COCO compatible categories keyed by category id.
 
@@ -91,7 +105,6 @@ def convert_label_map_to_categories(label_map,
   return categories
 
 
-# TODO: double check documentaion.
 def load_labelmap(path):
   """Loads label map proto.
 
@@ -107,6 +120,7 @@ def load_labelmap(path):
       text_format.Merge(label_map_string, label_map)
     except text_format.ParseError:
       label_map.ParseFromString(label_map_string)
+  _validate_label_map(label_map)
   return label_map
 
 

object_detection/utils/label_map_util_test.py

@@ -53,7 +53,29 @@ class LabelMapUtilTest(tf.test.TestCase):
     self.assertEqual(label_map_dict['dog'], 1)
     self.assertEqual(label_map_dict['cat'], 2)
 
-  def test_keep_categories_with_unique_id(self):
+  def test_load_bad_label_map(self):
+    label_map_string = """
+      item {
+        id:0
+        name:'class that should not be indexed at zero'
+      }
+      item {
+        id:2
+        name:'cat'
+      }
+      item {
+        id:1
+        name:'dog'
+      }
+    """
+    label_map_path = os.path.join(self.get_temp_dir(), 'label_map.pbtxt')
+    with tf.gfile.Open(label_map_path, 'wb') as f:
+      f.write(label_map_string)
+
+    with self.assertRaises(ValueError):
+      label_map_util.load_labelmap(label_map_path)
+
+    def test_keep_categories_with_unique_id(self):
     label_map_proto = string_int_label_map_pb2.StringIntLabelMap()
     label_map_string = """
       item {