Object detection changes: (#7208)

257914648  by lzc:

    Internal changes

--
257525973  by Zhichao Lu:

    Fixes bug that silently prevents checkpoints from loading when training w/ eager + functions. Also sets up scripts to run training.

--
257296614  by Zhichao Lu:

    Adding detection_features to model outputs

--
257234565  by Zhichao Lu:

    Fix wrong order of `classes_with_max_scores` in class-agnostic NMS caused by
    sorting in partitioned-NMS.

--
257232002  by ronnyvotel:

    Supporting `filter_nonoverlapping` option in np_box_list_ops.clip_to_window().

--
257198282  by Zhichao Lu:

    Adding the focal loss and l1 loss from the Objects as Points paper.

--
257089535  by Zhichao Lu:

    Create Keras based ssd + resnetv1 + fpn.

--
257087407  by Zhichao Lu:

    Make object_detection/data_decoders Python3-compatible.

--
257004582  by Zhichao Lu:

    Updates _decode_raw_data_into_masks_and_boxes to the latest binary masks-to-string encoding fo...

research/object_detection/utils/test_utils.py

@@ -14,7 +14,13 @@
 # ==============================================================================
 
 """Contains functions which are convenient for unit testing."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
 import numpy as np
+from six.moves import range
+from six.moves import zip
 import tensorflow as tf
 
 from object_detection.core import anchor_generator

research/object_detection/utils/test_utils_test.py

@@ -15,6 +15,10 @@
 
 """Tests for object_detection.utils.test_utils."""
 
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
 import numpy as np
 import tensorflow as tf
 

research/object_detection/utils/variables_helper.py

@@ -15,6 +15,11 @@
 
 """Helper functions for manipulating collections of variables during training.
 """
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
 import logging
 import re
 
@@ -44,7 +49,7 @@ def filter_variables(variables, filter_regex_list, invert=False):
     a list of filtered variables.
   """
   kept_vars = []
-  variables_to_ignore_patterns = list(filter(None, filter_regex_list))
+  variables_to_ignore_patterns = list([fre for fre in filter_regex_list if fre])
   for var in variables:
     add = True
     for pattern in variables_to_ignore_patterns:
@@ -151,5 +156,24 @@ def get_variables_available_in_checkpoint(variables,
       logging.warning('Variable [%s] is not available in checkpoint',
                       variable_name)
   if isinstance(variables, list):
-    return vars_in_ckpt.values()
+    return list(vars_in_ckpt.values())
   return vars_in_ckpt
+
+
+def get_global_variables_safely():
+  """If not executing eagerly, returns tf.global_variables().
+
+  Raises a ValueError if eager execution is enabled,
+  because the variables are not tracked when executing eagerly.
+
+  If executing eagerly, use a Keras model's .variables property instead.
+
+  Returns:
+    The result of tf.global_variables()
+  """
+  with tf.init_scope():
+    if tf.executing_eagerly():
+      raise ValueError("Global variables collection is not tracked when "
+                       "executing eagerly. Use a Keras model's `.variables` "
+                       "attribute instead.")
+  return tf.global_variables()

research/object_detection/utils/variables_helper_test.py

@@ -14,6 +14,11 @@
 # ==============================================================================
 
 """Tests for object_detection.utils.variables_helper."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
 import os
 
 import tensorflow as tf
@@ -204,7 +209,7 @@ class GetVariablesAvailableInCheckpointTest(tf.test.TestCase):
           graph2_variables_dict, checkpoint_path)
 
     self.assertTrue(isinstance(out_variables, dict))
-    self.assertItemsEqual(out_variables.keys(), ['ckpt_weights'])
+    self.assertItemsEqual(list(out_variables.keys()), ['ckpt_weights'])
     self.assertTrue(out_variables['ckpt_weights'].op.name == 'weights')
 
   def test_return_variables_with_correct_sizes(self):

research/object_detection/utils/visualization_utils.py

@@ -19,6 +19,10 @@ 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.
 
 """
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
 import abc
 import collections
 # Set headless-friendly backend.
@@ -30,6 +34,8 @@ import PIL.ImageColor as ImageColor
 import PIL.ImageDraw as ImageDraw
 import PIL.ImageFont as ImageFont
 import six
+from six.moves import range
+from six.moves import zip
 import tensorflow as tf
 
 from object_detection.core import standard_fields as fields
@@ -771,7 +777,7 @@ def visualize_boxes_and_labels_on_image_array(
         display_str = ''
         if not skip_labels:
           if not agnostic_mode:
-            if classes[i] in category_index.keys():
+            if classes[i] in six.viewkeys(category_index):
               class_name = category_index[classes[i]]['name']
             else:
               class_name = 'N/A'
@@ -894,7 +900,7 @@ def add_hist_image_summary(values, bins, name):
   tf.summary.image(name, hist_plot)
 
 
-class EvalMetricOpsVisualization(object):
+class EvalMetricOpsVisualization(six.with_metaclass(abc.ABCMeta, object)):
   """Abstract base class responsible for visualizations during evaluation.
 
   Currently, summary images are not run during evaluation. One way to produce
@@ -903,7 +909,6 @@ class EvalMetricOpsVisualization(object):
   responsible for accruing images (with overlaid detections and groundtruth)
   and returning a dictionary that can be passed to `eval_metric_ops`.
   """
-  __metaclass__ = abc.ABCMeta
 
   def __init__(self,
                category_index,

research/object_detection/utils/visualization_utils_test.py

@@ -14,11 +14,17 @@
 # ==============================================================================
 
 """Tests for object_detection.utils.visualization_utils."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
 import logging
 import os
 
 import numpy as np
 import PIL.Image as Image
+import six
+from six.moves import range
 import tensorflow as tf
 
 from object_detection.core import standard_fields as fields
@@ -387,12 +393,12 @@ class VisualizationUtilsTest(tf.test.TestCase):
             groundtruth_classes
     }
     metric_ops = eval_metric_ops.get_estimator_eval_metric_ops(eval_dict)
-    _, update_op = metric_ops[metric_ops.keys()[0]]
+    _, update_op = metric_ops[next(six.iterkeys(metric_ops))]
 
     with self.test_session() as sess:
       sess.run(tf.global_variables_initializer())
       value_ops = {}
-      for key, (value_op, _) in metric_ops.iteritems():
+      for key, (value_op, _) in six.iteritems(metric_ops):
         value_ops[key] = value_op
 
       # First run enough update steps to surpass `max_examples_to_draw`.
@@ -413,7 +419,7 @@ class VisualizationUtilsTest(tf.test.TestCase):
                                    [6 + i, 7 + i, 3], [6 + i, 7 + i, 3]]
             })
       value_ops_out = sess.run(value_ops)
-      for key, value_op in value_ops_out.iteritems():
+      for key, value_op in six.iteritems(value_ops_out):
         self.assertNotEqual('', value_op)
 
       # Now run fewer update steps than `max_examples_to_draw`. A single value
@@ -437,7 +443,7 @@ class VisualizationUtilsTest(tf.test.TestCase):
             })
       value_ops_out = sess.run(value_ops)
       self.assertEqual(
-          '',
+          six.b(''),
           value_ops_out[metric_op_base + '/' + str(max_examples_to_draw - 1)])
 
 

research/object_detection/utils/vrd_evaluation.py

@@ -27,10 +27,16 @@ Note1: groundtruth should be inserted before evaluation.
 Note2: This module operates on numpy boxes and box lists.
 """
 
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
 from abc import abstractmethod
 import collections
 import logging
 import numpy as np
+import six
+from six.moves import range
 
 from object_detection.core import standard_fields
 from object_detection.utils import metrics
@@ -179,7 +185,7 @@ class VRDDetectionEvaluator(object_detection_evaluation.DetectionEvaluator):
           datatype label_data_type above).
     """
     if image_id not in self._image_ids:
-      logging.warn('No groundtruth for the image with id %s.', image_id)
+      logging.warning('No groundtruth for the image with id %s.', image_id)
       # Since for the correct work of evaluator it is assumed that groundtruth
       # is inserted first we make sure to break the code if is it not the case.
       self._image_ids.update([image_id])
@@ -252,12 +258,12 @@ class VRDDetectionEvaluator(object_detection_evaluation.DetectionEvaluator):
             recall_100,
     }
     if relationships:
-      for key, average_precision in average_precisions.iteritems():
+      for key, average_precision in six.iteritems(average_precisions):
         vrd_metrics[self._metric_prefix + 'AP@{}IOU/{}'.format(
             self._matching_iou_threshold,
             relationships[key])] = average_precision
     else:
-      for key, average_precision in average_precisions.iteritems():
+      for key, average_precision in six.iteritems(average_precisions):
         vrd_metrics[self._metric_prefix + 'AP@{}IOU/{}'.format(
             self._matching_iou_threshold, key)] = average_precision
 
@@ -352,7 +358,7 @@ class VRDPhraseDetectionEvaluator(VRDDetectionEvaluator):
         where the named bounding box is computed as an enclosing bounding box
         of all bounding boxes of the i-th input structure.
     """
-    first_box_key = groundtruth_box_tuples.dtype.fields.keys()[0]
+    first_box_key = next(six.iterkeys(groundtruth_box_tuples.dtype.fields))
     miny = groundtruth_box_tuples[first_box_key][:, 0]
     minx = groundtruth_box_tuples[first_box_key][:, 1]
     maxy = groundtruth_box_tuples[first_box_key][:, 2]
@@ -388,7 +394,7 @@ class VRDPhraseDetectionEvaluator(VRDDetectionEvaluator):
         where the named bounding box is computed as an enclosing bounding box
         of all bounding boxes of the i-th input structure.
     """
-    first_box_key = detections_box_tuples.dtype.fields.keys()[0]
+    first_box_key = next(six.iterkeys(detections_box_tuples.dtype.fields))
     miny = detections_box_tuples[first_box_key][:, 0]
     minx = detections_box_tuples[first_box_key][:, 1]
     maxy = detections_box_tuples[first_box_key][:, 2]
@@ -459,7 +465,7 @@ class _VRDDetectionEvaluation(object):
           possibly additional classes.
     """
     if image_key in self._groundtruth_box_tuples:
-      logging.warn(
+      logging.warning(
           'image %s has already been added to the ground truth database.',
           image_key)
       return
@@ -536,7 +542,7 @@ class _VRDDetectionEvaluation(object):
         median_rank@100: median rank computed on 100 top-scoring samples.
     """
     if self._num_gt_instances == 0:
-      logging.warn('No ground truth instances')
+      logging.warning('No ground truth instances')
 
     if not self._scores:
       scores = np.array([], dtype=float)
@@ -546,8 +552,8 @@ class _VRDDetectionEvaluation(object):
       tp_fp_labels = np.concatenate(self._tp_fp_labels)
       relation_field_values = np.concatenate(self._relation_field_values)
 
-    for relation_field_value, _ in (
-        self._num_gt_instances_per_relationship.iteritems()):
+    for relation_field_value, _ in (six.iteritems(
+        self._num_gt_instances_per_relationship)):
       precisions, recalls = metrics.compute_precision_recall(
           scores[relation_field_values == relation_field_value],
           tp_fp_labels[relation_field_values == relation_field_value],
@@ -556,7 +562,8 @@ class _VRDDetectionEvaluation(object):
           relation_field_value] = metrics.compute_average_precision(
               precisions, recalls)
 
-    self._mean_average_precision = np.mean(self._average_precisions.values())
+    self._mean_average_precision = np.mean(
+        list(self._average_precisions.values()))
 
     self._precisions, self._recalls = metrics.compute_precision_recall(
         scores, tp_fp_labels, self._num_gt_instances)

research/object_detection/utils/vrd_evaluation_test.py

@@ -14,6 +14,10 @@
 # ==============================================================================
 """Tests for tensorflow_models.object_detection.utils.vrd_evaluation."""
 
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
 import numpy as np
 import tensorflow as tf