Merged commit includes the following changes:

187187978  by Zhichao Lu:

    Only updating hyperparameters if they have non-null values.

--
187097690  by Zhichao Lu:

    Rewrite some conditions a bit more clearly.

--
187085190  by Zhichao Lu:

    More informative error message.

--
186935376  by Zhichao Lu:

    Added option to evaluator.evaluate to use custom evaluator objects.

--
186808249  by Zhichao Lu:

    Fix documentation re: number of stages.

--
186775014  by Zhichao Lu:

    Change anchor generator interface to return a list of BoxLists containing anchors for different feature map layers.

--
186729028  by Zhichao Lu:

    Minor fixes to object detection.

--
186723716  by Zhichao Lu:

    Fix tf_example_decoder.py initailization issue.

--
186668505  by Zhichao Lu:

    Remove unused import.

--
186475361  by Zhichao Lu:

    Update the box predictor interface to return list of predictions - one from each feature map - instead of stacking them into one large tensor.

--
186410844  by Zhich...

research/object_detection/g3doc/installation.md

@@ -4,15 +4,14 @@
 
 Tensorflow Object Detection API depends on the following libraries:
 
-* Protobuf 2.6
-* Python-tk
-* Pillow 1.0
-* lxml
-* tf Slim (which is included in the "tensorflow/models/research/" checkout)
-* Jupyter notebook
-* Matplotlib
-* Tensorflow
-* cocoapi
+*   Protobuf 2.6
+*   Pillow 1.0
+*   lxml
+*   tf Slim (which is included in the "tensorflow/models/research/" checkout)
+*   Jupyter notebook
+*   Matplotlib
+*   Tensorflow
+*   cocoapi
 
 For detailed steps to install Tensorflow, follow the [Tensorflow installation
 instructions](https://www.tensorflow.org/install/). A typical user can install
@@ -28,7 +27,7 @@ pip install tensorflow-gpu
 The remaining libraries can be installed on Ubuntu 16.04 using via apt-get:
 
 ``` bash
-sudo apt-get install protobuf-compiler python-pil python-lxml python-tk
+sudo apt-get install protobuf-compiler python-pil python-lxml
 sudo pip install jupyter
 sudo pip install matplotlib
 ```

research/object_detection/g3doc/using_your_own_dataset.md

@@ -103,7 +103,7 @@ FLAGS = flags.FLAGS
 
 
 def create_tf_example(example):
-  # TODO: Populate the following variables from your 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
@@ -139,7 +139,7 @@ def create_tf_example(example):
 def main(_):
   writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
 
-  # TODO: Write code to read in your dataset to examples variable
+  # TODO(user): Write code to read in your dataset to examples variable
 
   for example in examples:
     tf_example = create_tf_example(example)

research/object_detection/inference/BUILD

-# Tensorflow Object Detection API: main runnables.
-
-package(
-    default_visibility = ["//visibility:public"],
-)
-
-licenses(["notice"])
-
-# Apache 2.0
-
-py_library(
-    name = "detection_inference",
-    srcs = ["detection_inference.py"],
-    deps = [
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/core:standard_fields",
-    ],
-)
-
-py_test(
-    name = "detection_inference_test",
-    srcs = ["detection_inference_test.py"],
-    deps = [
-        ":detection_inference",
-        "//PIL:pil",
-        "//numpy",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/core:standard_fields",
-        "//tensorflow/models/research/object_detection/utils:dataset_util",
-    ],
-)
-
-py_binary(
-    name = "infer_detections",
-    srcs = ["infer_detections.py"],
-    deps = [
-        ":detection_inference",
-        "//tensorflow",
-    ],
-)

research/object_detection/inference/detection_inference_test.py

@@ -17,7 +17,6 @@ r"""Tests for detection_inference.py."""
 import os
 import StringIO
 
-
 import numpy as np
 from PIL import Image
 import tensorflow as tf

research/object_detection/inputs_test.py

@@ -34,7 +34,7 @@ FLAGS = tf.flags.FLAGS
 
 def _get_configs_for_model(model_name):
   """Returns configurations for model."""
-  # TODO: Make sure these tests work fine outside google3.
+  # TODO(ronnyvotel): Make sure these tests work fine outside google3.
   fname = os.path.join(
       FLAGS.test_srcdir,
       ('google3/third_party/tensorflow_models/'

research/object_detection/matchers/BUILD

-# Tensorflow Object Detection API: Matcher implementations.
-
-package(
-    default_visibility = ["//visibility:public"],
-)
-
-licenses(["notice"])
-
-# Apache 2.0
-py_library(
-    name = "argmax_matcher",
-    srcs = [
-        "argmax_matcher.py",
-    ],
-    deps = [
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/core:matcher",
-        "//tensorflow/models/research/object_detection/utils:shape_utils",
-    ],
-)
-
-py_test(
-    name = "argmax_matcher_test",
-    srcs = ["argmax_matcher_test.py"],
-    deps = [
-        ":argmax_matcher",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/utils:test_case",
-    ],
-)
-
-py_library(
-    name = "bipartite_matcher",
-    srcs = [
-        "bipartite_matcher.py",
-    ],
-    deps = [
-        "//tensorflow",
-        "//tensorflow/contrib/image:image_py",
-        "//tensorflow/models/research/object_detection/core:matcher",
-    ],
-)
-
-py_test(
-    name = "bipartite_matcher_test",
-    srcs = [
-        "bipartite_matcher_test.py",
-    ],
-    deps = [
-        ":bipartite_matcher",
-        "//tensorflow",
-    ],
-)

research/object_detection/matchers/bipartite_matcher.py

@@ -38,7 +38,7 @@ class GreedyBipartiteMatcher(matcher.Matcher):
   def _match(self, similarity_matrix, num_valid_rows=-1):
     """Bipartite matches a collection rows and columns. A greedy bi-partite.
 
-    TODO: Add num_valid_columns options to match only that many columns
+    TODO(rathodv): Add num_valid_columns options to match only that many columns
     with all the rows.
 
     Args:

research/object_detection/meta_architectures/BUILD

-# Tensorflow Object Detection API: Meta-architectures.
-
-package(
-    default_visibility = ["//visibility:public"],
-)
-
-licenses(["notice"])
-
-# Apache 2.0
-
-py_library(
-    name = "ssd_meta_arch",
-    srcs = ["ssd_meta_arch.py"],
-    deps = [
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/core:box_list",
-        "//tensorflow/models/research/object_detection/core:box_predictor",
-        "//tensorflow/models/research/object_detection/core:model",
-        "//tensorflow/models/research/object_detection/core:target_assigner",
-        "//tensorflow/models/research/object_detection/utils:ops",
-        "//tensorflow/models/research/object_detection/utils:shape_utils",
-        "//tensorflow/models/research/object_detection/utils:test_case",
-        "//tensorflow/models/research/object_detection/utils:visualization_utils",
-    ],
-)
-
-py_test(
-    name = "ssd_meta_arch_test",
-    srcs = ["ssd_meta_arch_test.py"],
-    deps = [
-        ":ssd_meta_arch",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/core:anchor_generator",
-        "//tensorflow/models/research/object_detection/core:box_list",
-        "//tensorflow/models/research/object_detection/core:losses",
-        "//tensorflow/models/research/object_detection/core:post_processing",
-        "//tensorflow/models/research/object_detection/core:region_similarity_calculator",
-        "//tensorflow/models/research/object_detection/utils:test_utils",
-    ],
-)
-
-py_library(
-    name = "faster_rcnn_meta_arch",
-    srcs = [
-        "faster_rcnn_meta_arch.py",
-    ],
-    deps = [
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/anchor_generators:grid_anchor_generator",
-        "//tensorflow/models/research/object_detection/core:balanced_positive_negative_sampler",
-        "//tensorflow/models/research/object_detection/core:box_list",
-        "//tensorflow/models/research/object_detection/core:box_list_ops",
-        "//tensorflow/models/research/object_detection/core:box_predictor",
-        "//tensorflow/models/research/object_detection/core:losses",
-        "//tensorflow/models/research/object_detection/core:model",
-        "//tensorflow/models/research/object_detection/core:post_processing",
-        "//tensorflow/models/research/object_detection/core:standard_fields",
-        "//tensorflow/models/research/object_detection/core:target_assigner",
-        "//tensorflow/models/research/object_detection/utils:ops",
-        "//tensorflow/models/research/object_detection/utils:shape_utils",
-    ],
-)
-
-py_library(
-    name = "faster_rcnn_meta_arch_test_lib",
-    srcs = [
-        "faster_rcnn_meta_arch_test_lib.py",
-    ],
-    deps = [
-        ":faster_rcnn_meta_arch",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/anchor_generators:grid_anchor_generator",
-        "//tensorflow/models/research/object_detection/builders:box_predictor_builder",
-        "//tensorflow/models/research/object_detection/builders:hyperparams_builder",
-        "//tensorflow/models/research/object_detection/builders:post_processing_builder",
-        "//tensorflow/models/research/object_detection/core:losses",
-        "//tensorflow/models/research/object_detection/protos:box_predictor_py_pb2",
-        "//tensorflow/models/research/object_detection/protos:hyperparams_py_pb2",
-        "//tensorflow/models/research/object_detection/protos:post_processing_py_pb2",
-    ],
-)
-
-py_test(
-    name = "faster_rcnn_meta_arch_test",
-    srcs = ["faster_rcnn_meta_arch_test.py"],
-    deps = [
-        ":faster_rcnn_meta_arch_test_lib",
-    ],
-)
-
-py_library(
-    name = "rfcn_meta_arch",
-    srcs = ["rfcn_meta_arch.py"],
-    deps = [
-        ":faster_rcnn_meta_arch",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/core:box_predictor",
-        "//tensorflow/models/research/object_detection/utils:ops",
-    ],
-)
-
-py_test(
-    name = "rfcn_meta_arch_test",
-    srcs = ["rfcn_meta_arch_test.py"],
-    deps = [
-        ":faster_rcnn_meta_arch_test_lib",
-        ":rfcn_meta_arch",
-        "//tensorflow",
-    ],
-)

research/object_detection/meta_architectures/faster_rcnn_meta_arch.py

@@ -365,7 +365,7 @@ class FasterRCNNMetaArch(model.DetectionModel):
       ValueError: If first_stage_anchor_generator is not of type
         grid_anchor_generator.GridAnchorGenerator.
     """
-    # TODO: add_summaries is currently unused. Respect that directive
+    # TODO(rathodv): add_summaries is currently unused. Respect that directive
     # in the future.
     super(FasterRCNNMetaArch, self).__init__(num_classes=num_classes)
 
@@ -597,7 +597,7 @@ class FasterRCNNMetaArch(model.DetectionModel):
           `num_anchors` can differ depending on whether the model is created in
           training or inference mode.
 
-        (and if number_of_stages=1):
+        (and if number_of_stages > 1):
         7) refined_box_encodings: a 3-D tensor with shape
           [total_num_proposals, num_classes, 4] representing predicted
           (final) refined box encodings, where
@@ -910,8 +910,9 @@ class FasterRCNNMetaArch(model.DetectionModel):
         preprocessed_inputs, scope=self.first_stage_feature_extractor_scope)
 
     feature_map_shape = tf.shape(rpn_features_to_crop)
-    anchors = self._first_stage_anchor_generator.generate(
-        [(feature_map_shape[1], feature_map_shape[2])])
+    anchors = box_list_ops.concatenate(
+        self._first_stage_anchor_generator.generate([(feature_map_shape[1],
+                                                      feature_map_shape[2])]))
     with slim.arg_scope(self._first_stage_box_predictor_arg_scope):
       kernel_size = self._first_stage_box_predictor_kernel_size
       rpn_box_predictor_features = slim.conv2d(
@@ -957,9 +958,11 @@ class FasterRCNNMetaArch(model.DetectionModel):
         num_anchors_per_location,
         scope=self.first_stage_box_predictor_scope)
 
-    box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
-    objectness_predictions_with_background = box_predictions[
-        box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
+    box_encodings = tf.concat(
+        box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
+    objectness_predictions_with_background = tf.concat(
+        box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
+        axis=1)
     return (tf.squeeze(box_encodings, axis=2),
             objectness_predictions_with_background)
 
@@ -1796,7 +1799,7 @@ class FasterRCNNMetaArch(model.DetectionModel):
 
         # Create a new target assigner that matches the proposals to groundtruth
         # and returns the mask targets.
-        # TODO: Move `unmatched_cls_target` from constructor to assign
+        # TODO(rathodv): Move `unmatched_cls_target` from constructor to assign
         # function. This will enable reuse of a single target assigner for both
         # class targets and mask targets.
         mask_target_assigner = target_assigner.create_target_assigner(

research/object_detection/meta_architectures/faster_rcnn_meta_arch_test_lib.py

@@ -745,7 +745,7 @@ class FasterRCNNMetaArchTestBase(tf.test.TestCase):
       preprocessed_inputs, _ = model.preprocess(image_placeholder)
       self.assertAllEqual(preprocessed_inputs.shape.as_list(), image_shape)
 
-  # TODO: Split test into two - with and without masks.
+  # TODO(rathodv): Split test into two - with and without masks.
   def test_loss_first_stage_only_mode(self):
     model = self._build_model(
         is_training=True, number_of_stages=1, second_stage_batch_size=6)
@@ -797,7 +797,7 @@ class FasterRCNNMetaArchTestBase(tf.test.TestCase):
       self.assertTrue('second_stage_localization_loss' not in loss_dict_out)
       self.assertTrue('second_stage_classification_loss' not in loss_dict_out)
 
-  # TODO: Split test into two - with and without masks.
+  # TODO(rathodv): Split test into two - with and without masks.
   def test_loss_full(self):
     model = self._build_model(
         is_training=True, number_of_stages=2, second_stage_batch_size=6)

research/object_detection/meta_architectures/rfcn_meta_arch.py

@@ -164,7 +164,7 @@ class RFCNMetaArch(faster_rcnn_meta_arch.FasterRCNNMetaArch):
       ValueError: If first_stage_anchor_generator is not of type
         grid_anchor_generator.GridAnchorGenerator.
     """
-    # TODO: add_summaries is currently unused. Respect that directive
+    # TODO(rathodv): add_summaries is currently unused. Respect that directive
     # in the future.
     super(RFCNMetaArch, self).__init__(
         is_training,
@@ -275,9 +275,11 @@ class RFCNMetaArch(faster_rcnn_meta_arch.FasterRCNNMetaArch):
         scope=self.second_stage_box_predictor_scope,
         proposal_boxes=proposal_boxes_normalized)
     refined_box_encodings = tf.squeeze(
-        box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
+        tf.concat(box_predictions[box_predictor.BOX_ENCODINGS], axis=1), axis=1)
     class_predictions_with_background = tf.squeeze(
-        box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
+        tf.concat(
+            box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
+            axis=1),
         axis=1)
 
     absolute_proposal_boxes = ops.normalized_to_image_coordinates(

research/object_detection/meta_architectures/ssd_meta_arch.py

@@ -23,6 +23,7 @@ import re
 import tensorflow as tf
 
 from object_detection.core import box_list
+from object_detection.core import box_list_ops
 from object_detection.core import model
 from object_detection.core import standard_fields as fields
 from object_detection.core import target_assigner
@@ -122,6 +123,7 @@ class SSDMetaArch(model.DetectionModel):
                matcher,
                region_similarity_calculator,
                encode_background_as_zeros,
+               negative_class_weight,
                image_resizer_fn,
                non_max_suppression_fn,
                score_conversion_fn,
@@ -131,7 +133,8 @@ class SSDMetaArch(model.DetectionModel):
                localization_loss_weight,
                normalize_loss_by_num_matches,
                hard_example_miner,
-               add_summaries=True):
+               add_summaries=True,
+               normalize_loc_loss_by_codesize=False):
     """SSDMetaArch Constructor.
 
     TODO(rathodv,jonathanhuang): group NMS parameters + score converter into
@@ -151,6 +154,7 @@ class SSDMetaArch(model.DetectionModel):
       encode_background_as_zeros: boolean determining whether background
         targets are to be encoded as an all zeros vector or a one-hot
         vector (where background is the 0th class).
+      negative_class_weight: Weight for confidence loss of negative anchors.
       image_resizer_fn: a callable for image resizing.  This callable always
         takes a rank-3 image tensor (corresponding to a single image) and
         returns a rank-3 image tensor, possibly with new spatial dimensions and
@@ -175,6 +179,8 @@ class SSDMetaArch(model.DetectionModel):
       hard_example_miner: a losses.HardExampleMiner object (can be None)
       add_summaries: boolean (default: True) controlling whether summary ops
         should be added to tensorflow graph.
+      normalize_loc_loss_by_codesize: whether to normalize localization loss
+        by code size of the box encoder.
     """
     super(SSDMetaArch, self).__init__(num_classes=box_predictor.num_classes)
     self._is_training = is_training
@@ -191,7 +197,7 @@ class SSDMetaArch(model.DetectionModel):
     self._matcher = matcher
     self._region_similarity_calculator = region_similarity_calculator
 
-    # TODO: handle agnostic mode and positive/negative class
+    # TODO(jonathanhuang): handle agnostic mode
     # weights
     unmatched_cls_target = None
     unmatched_cls_target = tf.constant([1] + self.num_classes * [0],
@@ -204,7 +210,7 @@ class SSDMetaArch(model.DetectionModel):
         self._region_similarity_calculator,
         self._matcher,
         self._box_coder,
-        negative_class_weight=1.0,
+        negative_class_weight=negative_class_weight,
         unmatched_cls_target=unmatched_cls_target)
 
     self._classification_loss = classification_loss
@@ -212,6 +218,7 @@ class SSDMetaArch(model.DetectionModel):
     self._classification_loss_weight = classification_loss_weight
     self._localization_loss_weight = localization_loss_weight
     self._normalize_loss_by_num_matches = normalize_loss_by_num_matches
+    self._normalize_loc_loss_by_codesize = normalize_loc_loss_by_codesize
     self._hard_example_miner = hard_example_miner
 
     self._image_resizer_fn = image_resizer_fn
@@ -254,7 +261,7 @@ class SSDMetaArch(model.DetectionModel):
     if inputs.dtype is not tf.float32:
       raise ValueError('`preprocess` expects a tf.float32 tensor')
     with tf.name_scope('Preprocessor'):
-      # TODO: revisit whether to always use batch size as
+      # TODO(jonathanhuang): revisit whether to always use batch size as
       # the number of parallel iterations vs allow for dynamic batching.
       outputs = shape_utils.static_or_dynamic_map_fn(
           self._image_resizer_fn,
@@ -344,15 +351,17 @@ class SSDMetaArch(model.DetectionModel):
     feature_map_spatial_dims = self._get_feature_map_spatial_dims(feature_maps)
     image_shape = shape_utils.combined_static_and_dynamic_shape(
         preprocessed_inputs)
-    self._anchors = self._anchor_generator.generate(
-        feature_map_spatial_dims,
-        im_height=image_shape[1],
-        im_width=image_shape[2])
+    self._anchors = box_list_ops.concatenate(
+        self._anchor_generator.generate(
+            feature_map_spatial_dims,
+            im_height=image_shape[1],
+            im_width=image_shape[2]))
     prediction_dict = self._box_predictor.predict(
         feature_maps, self._anchor_generator.num_anchors_per_location())
-    box_encodings = tf.squeeze(prediction_dict['box_encodings'], axis=2)
-    class_predictions_with_background = prediction_dict[
-        'class_predictions_with_background']
+    box_encodings = tf.squeeze(
+        tf.concat(prediction_dict['box_encodings'], axis=1), axis=2)
+    class_predictions_with_background = tf.concat(
+        prediction_dict['class_predictions_with_background'], axis=1)
     predictions_dict = {
         'preprocessed_inputs': preprocessed_inputs,
         'box_encodings': box_encodings,
@@ -530,8 +539,11 @@ class SSDMetaArch(model.DetectionModel):
                                 1.0)
 
       with tf.name_scope('localization_loss'):
-        localization_loss = ((self._localization_loss_weight / normalizer) *
-                             localization_loss)
+        localization_loss_normalizer = normalizer
+        if self._normalize_loc_loss_by_codesize:
+          localization_loss_normalizer *= self._box_coder.code_size
+        localization_loss = ((self._localization_loss_weight / (
+            localization_loss_normalizer)) * localization_loss)
       with tf.name_scope('classification_loss'):
         classification_loss = ((self._classification_loss_weight / normalizer) *
                                classification_loss)

research/object_detection/meta_architectures/ssd_meta_arch_test.py

@@ -61,12 +61,12 @@ class MockAnchorGenerator2x2(anchor_generator.AnchorGenerator):
     return [1]
 
   def _generate(self, feature_map_shape_list, im_height, im_width):
-    return box_list.BoxList(
+    return [box_list.BoxList(
         tf.constant([[0, 0, .5, .5],
                      [0, .5, .5, 1],
                      [.5, 0, 1, .5],
                      [1., 1., 1.5, 1.5]  # Anchor that is outside clip_window.
-                    ], tf.float32))
+                    ], tf.float32))]
 
   def num_anchors(self):
     return 4
@@ -74,7 +74,8 @@ class MockAnchorGenerator2x2(anchor_generator.AnchorGenerator):
 
 class SsdMetaArchTest(test_case.TestCase):
 
-  def _create_model(self, apply_hard_mining=True):
+  def _create_model(self, apply_hard_mining=True,
+                    normalize_loc_loss_by_codesize=False):
     is_training = False
     num_classes = 1
     mock_anchor_generator = MockAnchorGenerator2x2()
@@ -98,6 +99,7 @@ class SsdMetaArchTest(test_case.TestCase):
         max_total_size=5)
     classification_loss_weight = 1.0
     localization_loss_weight = 1.0
+    negative_class_weight = 1.0
     normalize_loss_by_num_matches = False
 
     hard_example_miner = None
@@ -111,10 +113,11 @@ class SsdMetaArchTest(test_case.TestCase):
     model = ssd_meta_arch.SSDMetaArch(
         is_training, mock_anchor_generator, mock_box_predictor, mock_box_coder,
         fake_feature_extractor, mock_matcher, region_similarity_calculator,
-        encode_background_as_zeros, image_resizer_fn, non_max_suppression_fn,
-        tf.identity, classification_loss, localization_loss,
-        classification_loss_weight, localization_loss_weight,
-        normalize_loss_by_num_matches, hard_example_miner, add_summaries=False)
+        encode_background_as_zeros, negative_class_weight, image_resizer_fn,
+        non_max_suppression_fn, tf.identity, classification_loss,
+        localization_loss, classification_loss_weight, localization_loss_weight,
+        normalize_loss_by_num_matches, hard_example_miner, add_summaries=False,
+        normalize_loc_loss_by_codesize=normalize_loc_loss_by_codesize)
     return model, num_classes, mock_anchor_generator.num_anchors(), code_size
 
   def test_preprocess_preserves_shapes_with_dynamic_input_image(self):
@@ -287,6 +290,37 @@ class SsdMetaArchTest(test_case.TestCase):
     self.assertAllClose(localization_loss, expected_localization_loss)
     self.assertAllClose(classification_loss, expected_classification_loss)
 
+  def test_loss_results_are_correct_with_normalize_by_codesize_true(self):
+
+    with tf.Graph().as_default():
+      _, _, _, _ = self._create_model()
+    def graph_fn(preprocessed_tensor, groundtruth_boxes1, groundtruth_boxes2,
+                 groundtruth_classes1, groundtruth_classes2):
+      groundtruth_boxes_list = [groundtruth_boxes1, groundtruth_boxes2]
+      groundtruth_classes_list = [groundtruth_classes1, groundtruth_classes2]
+      model, _, _, _ = self._create_model(apply_hard_mining=False,
+                                          normalize_loc_loss_by_codesize=True)
+      model.provide_groundtruth(groundtruth_boxes_list,
+                                groundtruth_classes_list)
+      prediction_dict = model.predict(preprocessed_tensor,
+                                      true_image_shapes=None)
+      loss_dict = model.loss(prediction_dict, true_image_shapes=None)
+      return (loss_dict['localization_loss'],)
+
+    batch_size = 2
+    preprocessed_input = np.random.rand(batch_size, 2, 2, 3).astype(np.float32)
+    groundtruth_boxes1 = np.array([[0, 0, 1, 1]], dtype=np.float32)
+    groundtruth_boxes2 = np.array([[0, 0, 1, 1]], dtype=np.float32)
+    groundtruth_classes1 = np.array([[1]], dtype=np.float32)
+    groundtruth_classes2 = np.array([[1]], dtype=np.float32)
+    expected_localization_loss = 0.5 / 4
+    localization_loss = self.execute(graph_fn, [preprocessed_input,
+                                                groundtruth_boxes1,
+                                                groundtruth_boxes2,
+                                                groundtruth_classes1,
+                                                groundtruth_classes2])
+    self.assertAllClose(localization_loss, expected_localization_loss)
+
   def test_loss_results_are_correct_with_hard_example_mining(self):
 
     with tf.Graph().as_default():

research/object_detection/metrics/BUILD

-# Tensorflow Object Detection API: main runnables.
-
-package(
-    default_visibility = ["//visibility:public"],
-)
-
-licenses(["notice"])
-
-# Apache 2.0
-
-py_library(
-    name = "coco_tools",
-    srcs = [
-        "coco_tools.py",
-    ],
-    deps = [
-        "//file/localfile",
-        "//file/placer",
-        "//pycocotools",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/utils:json_utils",
-    ],
-)
-
-py_test(
-    name = "coco_tools_test",
-    srcs = [
-        "coco_tools_test.py",
-    ],
-    deps = [
-        ":coco_tools",
-        "//testing/pybase",
-        "//numpy",
-    ],
-)
-
-py_library(
-    name = "coco_evaluation",
-    srcs = [
-        "coco_evaluation.py",
-    ],
-    deps = [
-        ":coco_tools",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/core:standard_fields",
-        "//tensorflow/models/research/object_detection/utils:object_detection_evaluation",
-    ],
-)
-
-py_test(
-    name = "coco_evaluation_test",
-    srcs = [
-        "coco_evaluation_test.py",
-    ],
-    deps = [
-        ":coco_evaluation",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/core:standard_fields",
-    ],
-)
-
-py_binary(
-    name = "offline_eval_map_corloc",
-    srcs = [
-        "offline_eval_map_corloc.py",
-    ],
-    deps = [
-        ":tf_example_parser",
-        "//tensorflow/models/research/object_detection:evaluator",
-        "//tensorflow/models/research/object_detection/builders:input_reader_builder",
-        "//tensorflow/models/research/object_detection/core:standard_fields",
-        "//tensorflow/models/research/object_detection/utils:config_util",
-        "//tensorflow/models/research/object_detection/utils:label_map_util",
-    ],
-)
-
-py_test(
-    name = "offline_eval_map_corloc_test",
-    srcs = [
-        "offline_eval_map_corloc_test.py",
-    ],
-    deps = [
-        ":offline_eval_map_corloc",
-        "//tensorflow",
-    ],
-)
-
-py_library(
-    name = "tf_example_parser",
-    srcs = ["tf_example_parser.py"],
-    deps = [
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/core:data_parser",
-        "//tensorflow/models/research/object_detection/core:standard_fields",
-    ],
-)
-
-py_test(
-    name = "tf_example_parser_test",
-    srcs = ["tf_example_parser_test.py"],
-    deps = [
-        ":tf_example_parser",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/core:standard_fields",
-    ],
-)

research/object_detection/metrics/coco_tools.py

@@ -17,7 +17,7 @@
 Note that nothing in this file is tensorflow related and thus cannot
 be called directly as a slim metric, for example.
 
-TODO: wrap as a slim metric in metrics.py
+TODO(jonathanhuang): wrap as a slim metric in metrics.py
 
 
 Usage example: given a set of images with ids in the list image_ids
@@ -339,7 +339,7 @@ def ExportSingleImageGroundtruthToCoco(image_id,
 
   In the exported result, "area" fields are always set to the area of the
   groundtruth bounding box and "iscrowd" fields are always set to 0.
-  TODO: pass in "iscrowd" array for evaluating on COCO dataset.
+  TODO(jonathanhuang): pass in "iscrowd" array for evaluating on COCO dataset.
 
   Args:
     image_id: a unique image identifier either of type integer or string.
@@ -416,7 +416,7 @@ def ExportGroundtruthToCOCO(image_ids,
 
   In the exported result, "area" fields are always set to the area of the
   groundtruth bounding box and "iscrowd" fields are always set to 0.
-  TODO: pass in "iscrowd" array for evaluating on COCO dataset.
+  TODO(jonathanhuang): pass in "iscrowd" array for evaluating on COCO dataset.
 
   Args:
     image_ids: a list of unique image identifier either of type integer or

research/object_detection/model.py

@@ -319,9 +319,11 @@ def create_model_fn(detection_model_fn, configs, hparams, use_tpu=False):
       else:
         category_index = label_map_util.create_category_index_from_labelmap(
             eval_input_config.label_map_path)
-      detection_and_groundtruth = vis_utils.draw_side_by_side_evaluation_image(
-          eval_dict, category_index, max_boxes_to_draw=20, min_score_thresh=0.2)
       if not use_tpu:
+        detection_and_groundtruth = (
+            vis_utils.draw_side_by_side_evaluation_image(
+                eval_dict, category_index, max_boxes_to_draw=20,
+                min_score_thresh=0.2))
         tf.summary.image('Detections_Left_Groundtruth_Right',
                          detection_and_groundtruth)
 
@@ -424,11 +426,11 @@ def populate_experiment(run_config,
   eval_config = configs['eval_config']
   eval_input_config = configs['eval_input_config']
 
-  if train_steps is None:
-    train_steps = train_config.num_steps if train_config.num_steps else None
+  if train_steps is None and train_config.num_steps:
+    train_steps = train_config.num_steps
 
-  if eval_steps is None:
-    eval_steps = eval_config.num_examples if eval_config.num_examples else None
+  if eval_steps is None and eval_config.num_examples:
+    eval_steps = eval_config.num_examples
 
   detection_model_fn = functools.partial(
       model_builder.build, model_config=model_config)

research/object_detection/model_tpu.py

@@ -77,6 +77,10 @@ tf.flags.DEFINE_integer('min_eval_interval_secs', 180,
 tf.flags.DEFINE_integer(
     'eval_timeout_secs', None,
     'Maximum seconds between checkpoints before evaluation terminates.')
+tf.flags.DEFINE_string('hparams_overrides', None, 'Comma-separated list of '
+                       'hyperparameters to override defaults.')
+tf.flags.DEFINE_boolean('eval_training_data', False,
+                        'If training data should be evaluated for this job.')
 
 FLAGS = tf.flags.FLAGS
 
@@ -122,7 +126,10 @@ def create_estimator(run_config,
   Returns:
     Estimator: A estimator object used for training and evaluation
     train_input_fn: Input function for the training loop
-    eval_input_fn: Input function for the evaluation run
+    eval_validation_input_fn: Input function to run for evaluation on
+      validation data.
+    eval_training_input_fn: Input function to run for evaluation on
+      training data.
     train_steps: Number of training steps either from arg `train_steps` or
       `TrainConfig` proto
     eval_steps: Number of evaluation steps either from arg `eval_steps` or
@@ -141,15 +148,17 @@ def create_estimator(run_config,
   train_input_config = configs['train_input_config']
   eval_config = configs['eval_config']
   eval_input_config = configs['eval_input_config']
+  if FLAGS.eval_training_data:
+    eval_input_config = configs['train_input_config']
 
   if params is None:
     params = {}
 
-  if train_steps is None:
-    train_steps = train_config.num_steps if train_config.num_steps else None
+  if train_steps is None and train_config.num_steps:
+    train_steps = train_config.num_steps
 
-  if eval_steps is None:
-    eval_steps = eval_config.num_examples if eval_config.num_examples else None
+  if eval_steps is None and eval_config.num_examples:
+    eval_steps = eval_config.num_examples
 
   detection_model_fn = functools.partial(
       model_builder.build, model_config=model_config)
@@ -159,10 +168,14 @@ def create_estimator(run_config,
       train_config=train_config,
       train_input_config=train_input_config,
       model_config=model_config)
-  eval_input_fn = inputs.create_eval_input_fn(
+  eval_validation_input_fn = inputs.create_eval_input_fn(
       eval_config=eval_config,
       eval_input_config=eval_input_config,
       model_config=model_config)
+  eval_training_input_fn = inputs.create_eval_input_fn(
+      eval_config=eval_config,
+      eval_input_config=train_input_config,
+      model_config=model_config)
 
   estimator = tpu_estimator.TPUEstimator(
       model_fn=model_fn_creator(detection_model_fn, configs, hparams,
@@ -173,7 +186,8 @@ def create_estimator(run_config,
       use_tpu=use_tpu,
       config=run_config,
       params=params)
-  return estimator, train_input_fn, eval_input_fn, train_steps, eval_steps
+  return (estimator, train_input_fn, eval_validation_input_fn,
+          eval_training_input_fn, train_steps, eval_steps)
 
 
 def main(unused_argv):
@@ -204,24 +218,27 @@ def main(unused_argv):
           iterations_per_loop=FLAGS.iterations_per_loop,
           num_shards=FLAGS.num_shards))
   params = {}
-  estimator, train_input_fn, eval_input_fn, train_steps, eval_steps = (
-      create_estimator(
-          config,
-          model_hparams.create_hparams(),
-          FLAGS.pipeline_config_path,
-          train_steps=FLAGS.num_train_steps,
-          eval_steps=FLAGS.num_eval_steps,
-          train_batch_size=FLAGS.train_batch_size,
-          use_tpu=FLAGS.use_tpu,
-          num_shards=FLAGS.num_shards,
-          params=params))
+  (estimator, train_input_fn, eval_validation_input_fn, eval_training_input_fn,
+   train_steps, eval_steps) = (
+       create_estimator(
+           config,
+           model_hparams.create_hparams(
+               hparams_overrides=FLAGS.hparams_overrides),
+           FLAGS.pipeline_config_path,
+           train_steps=FLAGS.num_train_steps,
+           eval_steps=FLAGS.num_eval_steps,
+           train_batch_size=FLAGS.train_batch_size,
+           use_tpu=FLAGS.use_tpu,
+           num_shards=FLAGS.num_shards,
+           params=params))
 
   if FLAGS.mode in ['train', 'train_and_eval']:
     estimator.train(input_fn=train_input_fn, max_steps=train_steps)
 
   if FLAGS.mode == 'train_and_eval':
     # Eval one time.
-    eval_results = estimator.evaluate(input_fn=eval_input_fn, steps=eval_steps)
+    eval_results = estimator.evaluate(
+        input_fn=eval_validation_input_fn, steps=eval_steps)
     tf.logging.info('Eval results: %s' % eval_results)
 
   # Continuously evaluating.
@@ -239,11 +256,18 @@ def main(unused_argv):
         timeout_fn=terminate_eval):
 
       tf.logging.info('Starting to evaluate.')
+      if FLAGS.eval_training_data:
+        name = 'training_data'
+        input_fn = eval_training_input_fn
+      else:
+        name = 'validation_data'
+        input_fn = eval_validation_input_fn
       try:
         eval_results = estimator.evaluate(
-            input_fn=eval_input_fn,
+            input_fn=input_fn,
             steps=eval_steps,
-            checkpoint_path=ckpt)
+            checkpoint_path=ckpt,
+            name=name)
         tf.logging.info('Eval results: %s' % eval_results)
 
         # Terminate eval job when final checkpoint is reached

research/object_detection/models/BUILD

-# Tensorflow Object Detection API: Models.
-
-package(
-    default_visibility = ["//visibility:public"],
-)
-
-licenses(["notice"])
-
-# Apache 2.0
-
-py_library(
-    name = "feature_map_generators",
-    srcs = [
-        "feature_map_generators.py",
-    ],
-    deps = [
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/utils:ops",
-    ],
-)
-
-py_test(
-    name = "feature_map_generators_test",
-    srcs = [
-        "feature_map_generators_test.py",
-    ],
-    deps = [
-        ":feature_map_generators",
-        "//tensorflow",
-    ],
-)
-
-py_library(
-    name = "ssd_feature_extractor_test",
-    srcs = [
-        "ssd_feature_extractor_test.py",
-    ],
-    deps = [
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/utils:test_case",
-    ],
-)
-
-py_library(
-    name = "ssd_inception_v2_feature_extractor",
-    srcs = [
-        "ssd_inception_v2_feature_extractor.py",
-    ],
-    deps = [
-        ":feature_map_generators",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/meta_architectures:ssd_meta_arch",
-        "//tensorflow/models/research/object_detection/utils:ops",
-        "//tensorflow/models/research/object_detection/utils:shape_utils",
-        "//third_party/tensorflow_models/slim:inception_v2",
-    ],
-)
-
-py_library(
-    name = "ssd_inception_v3_feature_extractor",
-    srcs = [
-        "ssd_inception_v3_feature_extractor.py",
-    ],
-    deps = [
-        ":feature_map_generators",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/meta_architectures:ssd_meta_arch",
-        "//tensorflow/models/research/object_detection/utils:ops",
-        "//tensorflow/models/research/object_detection/utils:shape_utils",
-        "//third_party/tensorflow_models/slim:inception_v3",
-    ],
-)
-
-py_library(
-    name = "ssd_mobilenet_v1_feature_extractor",
-    srcs = ["ssd_mobilenet_v1_feature_extractor.py"],
-    deps = [
-        ":feature_map_generators",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/meta_architectures:ssd_meta_arch",
-        "//tensorflow/models/research/object_detection/utils:ops",
-        "//tensorflow/models/research/object_detection/utils:shape_utils",
-        "//third_party/tensorflow_models/slim:mobilenet_v1",
-    ],
-)
-
-py_library(
-    name = "embedded_ssd_mobilenet_v1_feature_extractor",
-    srcs = ["embedded_ssd_mobilenet_v1_feature_extractor.py"],
-    deps = [
-        ":feature_map_generators",
-        ":ssd_mobilenet_v1_feature_extractor",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/utils:ops",
-        "//third_party/tensorflow_models/slim:mobilenet_v1",
-    ],
-)
-
-py_library(
-    name = "ssd_resnet_v1_fpn_feature_extractor",
-    srcs = ["ssd_resnet_v1_fpn_feature_extractor.py"],
-    deps = [
-        ":feature_map_generators",
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/meta_architectures:ssd_meta_arch",
-        "//tensorflow/models/research/object_detection/utils:ops",
-        "//tensorflow/models/research/object_detection/utils:shape_utils",
-        "//third_party/tensorflow_models/slim:resnet_v1",
-    ],
-)
-
-py_library(
-    name = "ssd_resnet_v1_fpn_feature_extractor_testbase",
-    srcs = ["ssd_resnet_v1_fpn_feature_extractor_testbase.py"],
-    deps = [
-        "//tensorflow/models/research/object_detection/models:ssd_feature_extractor_test",
-    ],
-)
-
-py_test(
-    name = "ssd_resnet_v1_fpn_feature_extractor_test",
-    timeout = "long",
-    srcs = ["ssd_resnet_v1_fpn_feature_extractor_test.py"],
-    deps = [
-        ":ssd_resnet_v1_fpn_feature_extractor",
-        ":ssd_resnet_v1_fpn_feature_extractor_testbase",
-        "//tensorflow",
-    ],
-)
-
-py_test(
-    name = "ssd_inception_v2_feature_extractor_test",
-    srcs = [
-        "ssd_inception_v2_feature_extractor_test.py",
-    ],
-    deps = [
-        ":ssd_feature_extractor_test",
-        ":ssd_inception_v2_feature_extractor",
-        "//tensorflow",
-    ],
-)
-
-py_test(
-    name = "ssd_inception_v3_feature_extractor_test",
-    srcs = [
-        "ssd_inception_v3_feature_extractor_test.py",
-    ],
-    deps = [
-        ":ssd_feature_extractor_test",
-        ":ssd_inception_v3_feature_extractor",
-        "//tensorflow",
-    ],
-)
-
-py_test(
-    name = "ssd_mobilenet_v1_feature_extractor_test",
-    srcs = ["ssd_mobilenet_v1_feature_extractor_test.py"],
-    deps = [
-        ":ssd_feature_extractor_test",
-        ":ssd_mobilenet_v1_feature_extractor",
-        "//tensorflow",
-    ],
-)
-
-py_test(
-    name = "embedded_ssd_mobilenet_v1_feature_extractor_test",
-    srcs = ["embedded_ssd_mobilenet_v1_feature_extractor_test.py"],
-    deps = [
-        ":embedded_ssd_mobilenet_v1_feature_extractor",
-        ":ssd_feature_extractor_test",
-        "//tensorflow",
-    ],
-)
-
-py_test(
-    name = "faster_rcnn_nas_feature_extractor_test",
-    srcs = [
-        "faster_rcnn_nas_feature_extractor_test.py",
-    ],
-    deps = [
-        ":faster_rcnn_nas_feature_extractor",
-        "//tensorflow",
-    ],
-)
-
-py_library(
-    name = "faster_rcnn_nas_feature_extractor",
-    srcs = [
-        "faster_rcnn_nas_feature_extractor.py",
-    ],
-    deps = [
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/meta_architectures:faster_rcnn_meta_arch",
-        "//third_party/tensorflow_models/slim:nasnet",
-    ],
-)
-
-py_library(
-    name = "faster_rcnn_inception_resnet_v2_feature_extractor",
-    srcs = [
-        "faster_rcnn_inception_resnet_v2_feature_extractor.py",
-    ],
-    deps = [
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/meta_architectures:faster_rcnn_meta_arch",
-        "//third_party/tensorflow_models/slim:inception_resnet_v2",
-    ],
-)
-
-py_test(
-    name = "faster_rcnn_inception_resnet_v2_feature_extractor_test",
-    srcs = [
-        "faster_rcnn_inception_resnet_v2_feature_extractor_test.py",
-    ],
-    deps = [
-        ":faster_rcnn_inception_resnet_v2_feature_extractor",
-        "//tensorflow",
-    ],
-)
-
-py_library(
-    name = "faster_rcnn_inception_v2_feature_extractor",
-    srcs = [
-        "faster_rcnn_inception_v2_feature_extractor.py",
-    ],
-    deps = [
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/meta_architectures:faster_rcnn_meta_arch",
-        "//third_party/tensorflow_models/slim:inception_v2",
-    ],
-)
-
-py_test(
-    name = "faster_rcnn_inception_v2_feature_extractor_test",
-    srcs = [
-        "faster_rcnn_inception_v2_feature_extractor_test.py",
-    ],
-    deps = [
-        ":faster_rcnn_inception_v2_feature_extractor",
-        "//tensorflow",
-    ],
-)
-
-py_library(
-    name = "faster_rcnn_resnet_v1_feature_extractor",
-    srcs = [
-        "faster_rcnn_resnet_v1_feature_extractor.py",
-    ],
-    deps = [
-        "//tensorflow",
-        "//tensorflow/models/research/object_detection/meta_architectures:faster_rcnn_meta_arch",
-        "//third_party/tensorflow_models/slim:resnet_utils",
-        "//third_party/tensorflow_models/slim:resnet_v1",
-    ],
-)
-
-py_test(
-    name = "faster_rcnn_resnet_v1_feature_extractor_test",
-    srcs = [
-        "faster_rcnn_resnet_v1_feature_extractor_test.py",
-    ],
-    deps = [
-        ":faster_rcnn_resnet_v1_feature_extractor",
-        "//tensorflow",
-    ],
-)

research/object_detection/models/faster_rcnn_nas_feature_extractor.py

@@ -108,7 +108,7 @@ def _build_nasnet_base(hidden_previous,
   return net
 
 
-# TODO: Only fixed_shape_resizer is currently supported for NASNet
+# TODO(shlens): Only fixed_shape_resizer is currently supported for NASNet
 # featurization. The reason for this is that nasnet.py only supports
 # inputs with fully known shapes. We need to update nasnet.py to handle
 # shapes not known at compile time.

research/object_detection/models/faster_rcnn_resnet_v1_feature_extractor.py

@@ -111,7 +111,7 @@ class FasterRCNNResnetV1FeatureExtractor(
 
     with tf.control_dependencies([shape_assert]):
       # Disables batchnorm for fine-tuning with smaller batch sizes.
-      # TODO: Figure out if it is needed when image
+      # TODO(chensun): Figure out if it is needed when image
       # batch size is bigger.
       with slim.arg_scope(
           resnet_utils.resnet_arg_scope(