Merged commit includes the following changes:

223075771  by lzc:

    Bring in external fixes.

--
222919755  by ronnyvotel:

    Bug fix in faster r-cnn model builder. Was previously using `inplace_batchnorm_update` for `reuse_weights`.

--
222885680  by Zhichao Lu:

    Use the result_dict_for_batched_example in models_lib
    Also fixes the visualization size on when eval is on GPU

--
222883648  by Zhichao Lu:

    Fix _unmatched_class_label for the _add_background_class == False case in ssd_meta_arch.py.

--
222836663  by Zhichao Lu:

    Adding support for visualizing grayscale images. Without this change, the images are black-red instead of grayscale.

--
222501978  by Zhichao Lu:

    Fix a bug that caused convert_to_grayscale flag not to be respected.

--
222432846  by richardmunoz:

    Fix mapping of groundtruth_confidences from shape [num_boxes] to [num_boxes, num_classes] when the input contains the groundtruth_confidences field.

--
221725755  by richardmunoz:

    Internal change.

--
221458536  by Zhichao Lu:

    Fix saver defer build bug in object detection train codepath.

--
221391590  by Zhichao Lu:

    Add support for group normalization in the object detection API. Just adding MobileNet-v1 SSD currently. This may serve as a road map for other models that wish to support group normalization as an option.

--
221367993  by Zhichao Lu:

    Bug fixes (1) Make RandomPadImage work, (2) Fix keep_checkpoint_every_n_hours.

--
221266403  by rathodv:

    Use detection boxes as proposals to compute correct mask loss in eval jobs.

--
220845934  by lzc:

    Internal change.

--
220778850  by Zhichao Lu:

    Incorporating existing metrics into Estimator framework.
    Should restore:
    -oid_challenge_detection_metrics
    -pascal_voc_detection_metrics
    -weighted_pascal_voc_detection_metrics
    -pascal_voc_instance_segmentation_metrics
    -weighted_pascal_voc_instance_segmentation_metrics
    -oid_V2_detection_metrics

--
220370391  by alirezafathi:

    Adding precision and recall to the metrics.

--
220321268  by Zhichao Lu:

    Allow the option of setting max_examples_to_draw to zero.

--
220193337  by Zhichao Lu:

    This CL fixes a bug where the Keras convolutional box predictor was applying heads in the non-deterministic dict order. The consequence of this bug was that variables were created in non-deterministic orders. This in turn led different workers in a multi-gpu training setup to have slightly different graphs which had variables assigned to mismatched parameter servers. As a result, roughly half of all workers were unable to initialize and did no work, and training time was slowed down approximately 2x.

--
220136508  by huizhongc:

    Add weight equalization loss to SSD meta arch.

--
220125875  by pengchong:

    Rename label_scores to label_weights

--
219730108  by Zhichao Lu:

    Add description of detection_keypoints in postprocessed_tensors to docstring.

--
219577519  by pengchong:

    Support parsing the class confidences and training using them.

--
219547611  by lzc:

    Stop using static shapes in GPU eval jobs.

--
219536476  by Zhichao Lu:

    Migrate TensorFlow Lite out of tensorflow/contrib

    This change moves //tensorflow/contrib/lite to //tensorflow/lite in preparation
    for TensorFlow 2.0's deprecation of contrib/. If you refer to TF Lite build
    targets or headers, you will need to update them manually. If you use TF Lite
    from the TensorFlow python package, "tf.contrib.lite" now points to "tf.lite".
    Please update your imports as soon as possible.

    For more details, see https://groups.google.com/a/tensorflow.org/forum/#!topic/tflite/iIIXOTOFvwQ

    @angersson and @aselle are conducting this migration. Please contact them if
    you have any further questions.

--
219190083  by Zhichao Lu:

    Add a second expected_loss_weights function using an alternative expectation calculation compared to previous. Integrate this op into ssd_meta_arch and losses builder. Affects files that use losses_builder.build to handle the returning of an additional element.

--
218924451  by pengchong:

    Add a new way to assign training targets using groundtruth confidences.

--
218760524  by chowdhery:

    Modify export script to add option for regular NMS in TFLite post-processing op.

--

PiperOrigin-RevId: 223075771

Author: pkulzc

research/object_detection/builders/box_predictor_builder.py

@@ -16,7 +16,6 @@
 """Function to build box predictor from configuration."""
 
 import collections
-from absl import logging
 import tensorflow as tf
 from object_detection.predictors import convolutional_box_predictor
 from object_detection.predictors import convolutional_keras_box_predictor
@@ -26,7 +25,6 @@
 from object_detection.predictors.heads import class_head
 from object_detection.predictors.heads import keras_box_head
 from object_detection.predictors.heads import keras_class_head
-from object_detection.predictors.heads import keras_mask_head
 from object_detection.predictors.heads import mask_head
 from object_detection.protos import box_predictor_pb2
 
@@ -44,8 +42,7 @@ def build_convolutional_box_predictor(is_training,
                                       apply_sigmoid_to_scores=False,
                                       add_background_class=True,
                                       class_prediction_bias_init=0.0,
-                                      use_depthwise=False,
-                                      mask_head_config=None):
+                                      use_depthwise=False,):
   """Builds the ConvolutionalBoxPredictor from the arguments.
 
   Args:
@@ -80,8 +77,6 @@ def build_convolutional_box_predictor(is_training,
       conv2d layer before class prediction.
     use_depthwise: Whether to use depthwise convolutions for prediction
       steps. Default is False.
-    mask_head_config: An optional MaskHead object containing configs for mask
-      head construction.
 
   Returns:
     A ConvolutionalBoxPredictor class.
@@ -101,21 +96,6 @@ def build_convolutional_box_predictor(is_training,
       class_prediction_bias_init=class_prediction_bias_init,
       use_depthwise=use_depthwise)
   other_heads = {}
-  if mask_head_config is not None:
-    if not mask_head_config.masks_are_class_agnostic:
-      logging.warning('Note that class specific mask prediction for SSD '
-                      'models is memory consuming.')
-    other_heads[convolutional_box_predictor.MASK_PREDICTIONS] = (
-        mask_head.ConvolutionalMaskHead(
-            is_training=is_training,
-            num_classes=num_classes,
-            use_dropout=use_dropout,
-            dropout_keep_prob=dropout_keep_prob,
-            kernel_size=kernel_size,
-            use_depthwise=use_depthwise,
-            mask_height=mask_head_config.mask_height,
-            mask_width=mask_head_config.mask_width,
-            masks_are_class_agnostic=mask_head_config.masks_are_class_agnostic))
   return convolutional_box_predictor.ConvolutionalBoxPredictor(
       is_training=is_training,
       num_classes=num_classes,
@@ -144,7 +124,6 @@ def build_convolutional_keras_box_predictor(is_training,
                                             add_background_class=True,
                                             class_prediction_bias_init=0.0,
                                             use_depthwise=False,
-                                            mask_head_config=None,
                                             name='BoxPredictor'):
   """Builds the Keras ConvolutionalBoxPredictor from the arguments.
 
@@ -189,8 +168,6 @@ def build_convolutional_keras_box_predictor(is_training,
       conv2d layer before class prediction.
     use_depthwise: Whether to use depthwise convolutions for prediction
       steps. Default is False.
-    mask_head_config: An optional MaskHead object containing configs for mask
-      head construction.
     name: A string name scope to assign to the box predictor. If `None`, Keras
       will auto-generate one from the class name.
 
@@ -199,11 +176,7 @@ def build_convolutional_keras_box_predictor(is_training,
   """
   box_prediction_heads = []
   class_prediction_heads = []
-  mask_prediction_heads = []
   other_heads = {}
-  if mask_head_config is not None:
-    other_heads[convolutional_box_predictor.MASK_PREDICTIONS] = \
-      mask_prediction_heads
 
   for stack_index, num_predictions_per_location in enumerate(
       num_predictions_per_location_list):
@@ -231,26 +204,6 @@ def build_convolutional_keras_box_predictor(is_training,
             class_prediction_bias_init=class_prediction_bias_init,
             use_depthwise=use_depthwise,
             name='ConvolutionalClassHead_%d' % stack_index))
-    if mask_head_config is not None:
-      if not mask_head_config.masks_are_class_agnostic:
-        logging.warning('Note that class specific mask prediction for SSD '
-                        'models is memory consuming.')
-      mask_prediction_heads.append(
-          keras_mask_head.ConvolutionalMaskHead(
-              is_training=is_training,
-              num_classes=num_classes,
-              use_dropout=use_dropout,
-              dropout_keep_prob=dropout_keep_prob,
-              kernel_size=kernel_size,
-              conv_hyperparams=conv_hyperparams,
-              freeze_batchnorm=freeze_batchnorm,
-              num_predictions_per_location=num_predictions_per_location,
-              use_depthwise=use_depthwise,
-              mask_height=mask_head_config.mask_height,
-              mask_width=mask_head_config.mask_width,
-              masks_are_class_agnostic=mask_head_config.
-              masks_are_class_agnostic,
-              name='ConvolutionalMaskHead_%d' % stack_index))
 
   return convolutional_keras_box_predictor.ConvolutionalBoxPredictor(
       is_training=is_training,
@@ -282,7 +235,6 @@ def build_weight_shared_convolutional_box_predictor(
     share_prediction_tower=False,
     apply_batch_norm=True,
     use_depthwise=False,
-    mask_head_config=None,
     score_converter_fn=tf.identity,
     box_encodings_clip_range=None):
   """Builds and returns a WeightSharedConvolutionalBoxPredictor class.
@@ -310,8 +262,6 @@ def build_weight_shared_convolutional_box_predictor(
     apply_batch_norm: Whether to apply batch normalization to conv layers in
       this predictor.
     use_depthwise: Whether to use depthwise separable conv2d instead of conv2d.
-    mask_head_config: An optional MaskHead object containing configs for mask
-      head construction.
     score_converter_fn: Callable score converter to perform elementwise op on
       class scores.
     box_encodings_clip_range: Min and max values for clipping the box_encodings.
@@ -335,19 +285,6 @@ class scores.
           use_depthwise=use_depthwise,
           score_converter_fn=score_converter_fn))
   other_heads = {}
-  if mask_head_config is not None:
-    if not mask_head_config.masks_are_class_agnostic:
-      logging.warning('Note that class specific mask prediction for SSD '
-                      'models is memory consuming.')
-    other_heads[convolutional_box_predictor.MASK_PREDICTIONS] = (
-        mask_head.WeightSharedConvolutionalMaskHead(
-            num_classes=num_classes,
-            kernel_size=kernel_size,
-            use_dropout=use_dropout,
-            dropout_keep_prob=dropout_keep_prob,
-            mask_height=mask_head_config.mask_height,
-            mask_width=mask_head_config.mask_width,
-            masks_are_class_agnostic=mask_head_config.masks_are_class_agnostic))
   return convolutional_box_predictor.WeightSharedConvolutionalBoxPredictor(
       is_training=is_training,
       num_classes=num_classes,
@@ -520,9 +457,6 @@ def build(argscope_fn, box_predictor_config, is_training, num_classes,
     config_box_predictor = box_predictor_config.convolutional_box_predictor
     conv_hyperparams_fn = argscope_fn(config_box_predictor.conv_hyperparams,
                                       is_training)
-    mask_head_config = (
-        config_box_predictor.mask_head
-        if config_box_predictor.HasField('mask_head') else None)
     return build_convolutional_box_predictor(
         is_training=is_training,
         num_classes=num_classes,
@@ -539,8 +473,7 @@ def build(argscope_fn, box_predictor_config, is_training, num_classes,
         apply_sigmoid_to_scores=config_box_predictor.apply_sigmoid_to_scores,
         class_prediction_bias_init=(
             config_box_predictor.class_prediction_bias_init),
-        use_depthwise=config_box_predictor.use_depthwise,
-        mask_head_config=mask_head_config)
+        use_depthwise=config_box_predictor.use_depthwise)
 
   if  box_predictor_oneof == 'weight_shared_convolutional_box_predictor':
     config_box_predictor = (
@@ -549,9 +482,6 @@ def build(argscope_fn, box_predictor_config, is_training, num_classes,
                                       is_training)
     apply_batch_norm = config_box_predictor.conv_hyperparams.HasField(
         'batch_norm')
-    mask_head_config = (
-        config_box_predictor.mask_head
-        if config_box_predictor.HasField('mask_head') else None)
     # During training phase, logits are used to compute the loss. Only apply
     # sigmoid at inference to make the inference graph TPU friendly.
     score_converter_fn = build_score_converter(
@@ -581,7 +511,6 @@ def build(argscope_fn, box_predictor_config, is_training, num_classes,
         share_prediction_tower=config_box_predictor.share_prediction_tower,
         apply_batch_norm=apply_batch_norm,
         use_depthwise=config_box_predictor.use_depthwise,
-        mask_head_config=mask_head_config,
         score_converter_fn=score_converter_fn,
         box_encodings_clip_range=box_encodings_clip_range)
 
@@ -680,10 +609,6 @@ def build_keras(conv_hyperparams_fn, freeze_batchnorm, inplace_batchnorm_update,
     config_box_predictor = box_predictor_config.convolutional_box_predictor
     conv_hyperparams = conv_hyperparams_fn(
         config_box_predictor.conv_hyperparams)
-
-    mask_head_config = (
-        config_box_predictor.mask_head
-        if config_box_predictor.HasField('mask_head') else None)
     return build_convolutional_keras_box_predictor(
         is_training=is_training,
         num_classes=num_classes,
@@ -702,8 +627,7 @@ def build_keras(conv_hyperparams_fn, freeze_batchnorm, inplace_batchnorm_update,
         max_depth=config_box_predictor.max_depth,
         class_prediction_bias_init=(
             config_box_predictor.class_prediction_bias_init),
-        use_depthwise=config_box_predictor.use_depthwise,
-        mask_head_config=mask_head_config)
+        use_depthwise=config_box_predictor.use_depthwise)
 
   raise ValueError(
       'Unknown box predictor for Keras: {}'.format(box_predictor_oneof))

research/object_detection/builders/box_predictor_builder_test.py

@@ -21,9 +21,7 @@
 from google.protobuf import text_format
 from object_detection.builders import box_predictor_builder
 from object_detection.builders import hyperparams_builder
-from object_detection.predictors import convolutional_box_predictor
 from object_detection.predictors import mask_rcnn_box_predictor
-from object_detection.predictors.heads import mask_head
 from object_detection.protos import box_predictor_pb2
 from object_detection.protos import hyperparams_pb2
 
@@ -161,73 +159,6 @@ def test_construct_default_conv_box_predictor(self):
     self.assertTrue(box_predictor._is_training)
     self.assertFalse(class_head._use_depthwise)
 
-  def test_construct_default_conv_box_predictor_with_default_mask_head(self):
-    box_predictor_text_proto = """
-      convolutional_box_predictor {
-        mask_head {
-        }
-        conv_hyperparams {
-          regularizer {
-            l1_regularizer {
-            }
-          }
-          initializer {
-            truncated_normal_initializer {
-            }
-          }
-        }
-      }"""
-    box_predictor_proto = box_predictor_pb2.BoxPredictor()
-    text_format.Merge(box_predictor_text_proto, box_predictor_proto)
-    box_predictor = box_predictor_builder.build(
-        argscope_fn=hyperparams_builder.build,
-        box_predictor_config=box_predictor_proto,
-        is_training=True,
-        num_classes=90)
-    self.assertTrue(convolutional_box_predictor.MASK_PREDICTIONS in
-                    box_predictor._other_heads)
-    mask_prediction_head = (
-        box_predictor._other_heads[convolutional_box_predictor.MASK_PREDICTIONS]
-    )
-    self.assertEqual(mask_prediction_head._mask_height, 15)
-    self.assertEqual(mask_prediction_head._mask_width, 15)
-    self.assertTrue(mask_prediction_head._masks_are_class_agnostic)
-
-  def test_construct_default_conv_box_predictor_with_custom_mask_head(self):
-    box_predictor_text_proto = """
-      convolutional_box_predictor {
-        mask_head {
-          mask_height: 7
-          mask_width: 7
-          masks_are_class_agnostic: false
-        }
-        conv_hyperparams {
-          regularizer {
-            l1_regularizer {
-            }
-          }
-          initializer {
-            truncated_normal_initializer {
-            }
-          }
-        }
-      }"""
-    box_predictor_proto = box_predictor_pb2.BoxPredictor()
-    text_format.Merge(box_predictor_text_proto, box_predictor_proto)
-    box_predictor = box_predictor_builder.build(
-        argscope_fn=hyperparams_builder.build,
-        box_predictor_config=box_predictor_proto,
-        is_training=True,
-        num_classes=90)
-    self.assertTrue(convolutional_box_predictor.MASK_PREDICTIONS in
-                    box_predictor._other_heads)
-    mask_prediction_head = (
-        box_predictor._other_heads[convolutional_box_predictor.MASK_PREDICTIONS]
-    )
-    self.assertEqual(mask_prediction_head._mask_height, 7)
-    self.assertEqual(mask_prediction_head._mask_width, 7)
-    self.assertFalse(mask_prediction_head._masks_are_class_agnostic)
-
 
 class WeightSharedConvolutionalBoxPredictorBuilderTest(tf.test.TestCase):
 
@@ -421,79 +352,6 @@ def test_construct_default_conv_box_predictor_with_batch_norm(self):
     self.assertTrue(box_predictor._is_training)
     self.assertEqual(box_predictor._apply_batch_norm, True)
 
-  def test_construct_weight_shared_predictor_with_default_mask_head(self):
-    box_predictor_text_proto = """
-      weight_shared_convolutional_box_predictor {
-        mask_head {
-        }
-        conv_hyperparams {
-          regularizer {
-            l1_regularizer {
-            }
-          }
-          initializer {
-            truncated_normal_initializer {
-            }
-          }
-        }
-      }"""
-    box_predictor_proto = box_predictor_pb2.BoxPredictor()
-    text_format.Merge(box_predictor_text_proto, box_predictor_proto)
-    box_predictor = box_predictor_builder.build(
-        argscope_fn=hyperparams_builder.build,
-        box_predictor_config=box_predictor_proto,
-        is_training=True,
-        num_classes=90)
-    self.assertTrue(convolutional_box_predictor.MASK_PREDICTIONS in
-                    box_predictor._other_heads)
-    weight_shared_convolutional_mask_head = (
-        box_predictor._other_heads[convolutional_box_predictor.MASK_PREDICTIONS]
-    )
-    self.assertIsInstance(weight_shared_convolutional_mask_head,
-                          mask_head.WeightSharedConvolutionalMaskHead)
-    self.assertEqual(weight_shared_convolutional_mask_head._mask_height, 15)
-    self.assertEqual(weight_shared_convolutional_mask_head._mask_width, 15)
-    self.assertTrue(
-        weight_shared_convolutional_mask_head._masks_are_class_agnostic)
-
-  def test_construct_weight_shared_predictor_with_custom_mask_head(self):
-    box_predictor_text_proto = """
-      weight_shared_convolutional_box_predictor {
-        mask_head {
-          mask_height: 7
-          mask_width: 7
-          masks_are_class_agnostic: false
-        }
-        conv_hyperparams {
-          regularizer {
-            l1_regularizer {
-            }
-          }
-          initializer {
-            truncated_normal_initializer {
-            }
-          }
-        }
-      }"""
-    box_predictor_proto = box_predictor_pb2.BoxPredictor()
-    text_format.Merge(box_predictor_text_proto, box_predictor_proto)
-    box_predictor = box_predictor_builder.build(
-        argscope_fn=hyperparams_builder.build,
-        box_predictor_config=box_predictor_proto,
-        is_training=True,
-        num_classes=90)
-    self.assertTrue(convolutional_box_predictor.MASK_PREDICTIONS in
-                    box_predictor._other_heads)
-    weight_shared_convolutional_mask_head = (
-        box_predictor._other_heads[convolutional_box_predictor.MASK_PREDICTIONS]
-    )
-    self.assertIsInstance(weight_shared_convolutional_mask_head,
-                          mask_head.WeightSharedConvolutionalMaskHead)
-    self.assertEqual(weight_shared_convolutional_mask_head._mask_height, 7)
-    self.assertEqual(weight_shared_convolutional_mask_head._mask_width, 7)
-    self.assertFalse(
-        weight_shared_convolutional_mask_head._masks_are_class_agnostic)
-
 
 class MaskRCNNBoxPredictorBuilderTest(tf.test.TestCase):