resovle merge conflicts

research/object_detection/dataset_tools/oid_tfrecord_creation.py

@@ -51,25 +51,25 @@ def tf_example_from_annotations_data_frame(annotations_data_frame, label_map,
   feature_map = {
       standard_fields.TfExampleFields.object_bbox_ymin:
           dataset_util.float_list_feature(
-              filtered_data_frame_boxes.YMin.as_matrix()),
+              filtered_data_frame_boxes.YMin.to_numpy()),
       standard_fields.TfExampleFields.object_bbox_xmin:
           dataset_util.float_list_feature(
-              filtered_data_frame_boxes.XMin.as_matrix()),
+              filtered_data_frame_boxes.XMin.to_numpy()),
       standard_fields.TfExampleFields.object_bbox_ymax:
           dataset_util.float_list_feature(
-              filtered_data_frame_boxes.YMax.as_matrix()),
+              filtered_data_frame_boxes.YMax.to_numpy()),
       standard_fields.TfExampleFields.object_bbox_xmax:
           dataset_util.float_list_feature(
-              filtered_data_frame_boxes.XMax.as_matrix()),
+              filtered_data_frame_boxes.XMax.to_numpy()),
       standard_fields.TfExampleFields.object_class_text:
           dataset_util.bytes_list_feature([
               six.ensure_binary(label_text)
-              for label_text in filtered_data_frame_boxes.LabelName.as_matrix()
+              for label_text in filtered_data_frame_boxes.LabelName.to_numpy()
           ]),
       standard_fields.TfExampleFields.object_class_label:
           dataset_util.int64_list_feature(
               filtered_data_frame_boxes.LabelName.map(
-                  lambda x: label_map[x]).as_matrix()),
+                  lambda x: label_map[x]).to_numpy()),
       standard_fields.TfExampleFields.filename:
           dataset_util.bytes_feature(
               six.ensure_binary('{}.jpg'.format(image_id))),
@@ -82,31 +82,31 @@ def tf_example_from_annotations_data_frame(annotations_data_frame, label_map,
   if 'IsGroupOf' in filtered_data_frame.columns:
     feature_map[standard_fields.TfExampleFields.
                 object_group_of] = dataset_util.int64_list_feature(
-                    filtered_data_frame_boxes.IsGroupOf.as_matrix().astype(int))
+                    filtered_data_frame_boxes.IsGroupOf.to_numpy().astype(int))
   if 'IsOccluded' in filtered_data_frame.columns:
     feature_map[standard_fields.TfExampleFields.
                 object_occluded] = dataset_util.int64_list_feature(
-                    filtered_data_frame_boxes.IsOccluded.as_matrix().astype(
+                    filtered_data_frame_boxes.IsOccluded.to_numpy().astype(
                         int))
   if 'IsTruncated' in filtered_data_frame.columns:
     feature_map[standard_fields.TfExampleFields.
                 object_truncated] = dataset_util.int64_list_feature(
-                    filtered_data_frame_boxes.IsTruncated.as_matrix().astype(
+                    filtered_data_frame_boxes.IsTruncated.to_numpy().astype(
                         int))
   if 'IsDepiction' in filtered_data_frame.columns:
     feature_map[standard_fields.TfExampleFields.
                 object_depiction] = dataset_util.int64_list_feature(
-                    filtered_data_frame_boxes.IsDepiction.as_matrix().astype(
+                    filtered_data_frame_boxes.IsDepiction.to_numpy().astype(
                         int))
 
   if 'ConfidenceImageLabel' in filtered_data_frame_labels.columns:
     feature_map[standard_fields.TfExampleFields.
                 image_class_label] = dataset_util.int64_list_feature(
                     filtered_data_frame_labels.LabelName.map(
-                        lambda x: label_map[x]).as_matrix())
+                        lambda x: label_map[x]).to_numpy())
     feature_map[standard_fields.TfExampleFields
                 .image_class_text] = dataset_util.bytes_list_feature([
                     six.ensure_binary(label_text) for label_text in
-                    filtered_data_frame_labels.LabelName.as_matrix()
+                    filtered_data_frame_labels.LabelName.to_numpy()
                 ]),
   return tf.train.Example(features=tf.train.Features(feature=feature_map))

research/object_detection/dataset_tools/seq_example_util_test.py

@@ -288,7 +288,7 @@ class SeqExampleUtilTest(tf.test.TestCase):
         [0.75, 1.],
         seq_feature_dict['region/bbox/xmax'].feature[0].float_list.value[:])
     self.assertAllEqual(
-        ['cat', 'frog'],
+        [b'cat', b'frog'],
         seq_feature_dict['region/label/string'].feature[0].bytes_list.value[:])
     self.assertAllClose(
         [0.],
@@ -332,7 +332,7 @@ class SeqExampleUtilTest(tf.test.TestCase):
         [0.75],
         seq_feature_dict['region/bbox/xmax'].feature[1].float_list.value[:])
     self.assertAllEqual(
-        ['cat'],
+        [b'cat'],
         seq_feature_dict['region/label/string'].feature[1].bytes_list.value[:])
     self.assertAllClose(
         [],

research/object_detection/dataset_tools/tf_record_creation_util_test.py

@@ -42,7 +42,7 @@ class OpenOutputTfrecordsTests(tf.test.TestCase):
       tf_record_path = '{}-{:05d}-of-00010'.format(
           os.path.join(tf.test.get_temp_dir(), 'test.tfrec'), idx)
       records = list(tf.python_io.tf_record_iterator(tf_record_path))
-      self.assertAllEqual(records, ['test_{}'.format(idx)])
+      self.assertAllEqual(records, ['test_{}'.format(idx).encode('utf-8')])
 
 
 if __name__ == '__main__':

research/object_detection/dockerfiles/1.15/Dockerfile → research/object_detection/dockerfiles/tf1/Dockerfile

@@ -25,20 +25,17 @@ RUN useradd -ms /bin/bash tensorflow
 USER tensorflow
 WORKDIR /home/tensorflow
 
-# Install pip dependencies
-RUN pip3 install --user absl-py
-RUN pip3 install --user contextlib2
-RUN pip3 install --user Cython
-RUN pip3 install --user jupyter
-RUN pip3 install --user matplotlib
-RUN pip3 install --user pycocotools
-RUN pip3 install --user tf-slim
-
 # Copy this version of of the model garden into the image
 COPY --chown=tensorflow . /home/tensorflow/models
 
 # Compile protobuf configs
 RUN (cd /home/tensorflow/models/research/ && protoc object_detection/protos/*.proto --python_out=.)
+WORKDIR /home/tensorflow/models/research/
+
+RUN cp object_detection/packages/tf1/setup.py ./
+ENV PATH="/home/tensorflow/.local/bin:${PATH}"
+
+RUN python -m pip install --user -U pip
+RUN python -m pip install --user .
 
-ENV PYTHONPATH $PYTHONPATH:/home/tensorflow/models/research/:/home/tensorflow/models/research/slim
 ENV TF_CPP_MIN_LOG_LEVEL 3

research/object_detection/dockerfiles/2.2/README.md → research/object_detection/dockerfiles/tf1/README.md

-# Tensorflow Object Detection on Docker
+# TensorFlow Object Detection on Docker
 
 These instructions are experimental.
 
@@ -6,6 +6,6 @@ These instructions are experimental.
 
 ```bash
 # From the root of the git repository
-docker build -f research/object_detection/dockerfiles/2.2/Dockerfile -t od .
+docker build -f research/object_detection/dockerfiles/tf1/Dockerfile -t od .
 docker run -it od
 ```

research/object_detection/dockerfiles/2.2/Dockerfile → research/object_detection/dockerfiles/tf2/Dockerfile

@@ -25,20 +25,17 @@ RUN useradd -ms /bin/bash tensorflow
 USER tensorflow
 WORKDIR /home/tensorflow
 
-# Install pip dependencies
-RUN pip3 install --user absl-py
-RUN pip3 install --user contextlib2
-RUN pip3 install --user Cython
-RUN pip3 install --user jupyter
-RUN pip3 install --user matplotlib
-RUN pip3 install --user pycocotools
-RUN pip3 install --user tf-slim
-
 # Copy this version of of the model garden into the image
 COPY --chown=tensorflow . /home/tensorflow/models
 
 # Compile protobuf configs
 RUN (cd /home/tensorflow/models/research/ && protoc object_detection/protos/*.proto --python_out=.)
+WORKDIR /home/tensorflow/models/research/
+
+RUN cp object_detection/packages/tf2/setup.py ./
+ENV PATH="/home/tensorflow/.local/bin:${PATH}"
+
+RUN python -m pip install -U pip
+RUN python -m pip install .
 
-ENV PYTHONPATH $PYTHONPATH:/home/tensorflow/models/research/:/home/tensorflow/models/research/slim
 ENV TF_CPP_MIN_LOG_LEVEL 3

research/object_detection/dockerfiles/1.15/README.md → research/object_detection/dockerfiles/tf2/README.md

-# Tensorflow Object Detection on Docker
+# TensorFlow Object Detection on Docker
 
 These instructions are experimental.
 
@@ -6,6 +6,6 @@ These instructions are experimental.
 
 ```bash
 # From the root of the git repository
-docker build -f research/object_detection/dockerfiles/1.15/Dockerfile -t od .
+docker build -f research/object_detection/dockerfiles/tf2/Dockerfile -t od .
 docker run -it od
 ```

research/object_detection/eval_util.py

@@ -552,7 +552,11 @@ def _resize_detection_masks(args):
   detection_boxes, detection_masks, image_shape = args
   detection_masks_reframed = ops.reframe_box_masks_to_image_masks(
       detection_masks, detection_boxes, image_shape[0], image_shape[1])
-  return tf.cast(tf.greater(detection_masks_reframed, 0.5), tf.uint8)
+  # If the masks are currently float, binarize them. Otherwise keep them as
+  # integers, since they have already been thresholded.
+  if detection_masks_reframed.dtype == tf.float32:
+    detection_masks_reframed = tf.greater(detection_masks_reframed, 0.5)
+  return tf.cast(detection_masks_reframed, tf.uint8)
 
 
 def _resize_groundtruth_masks(args):
@@ -570,6 +574,17 @@ def _resize_groundtruth_masks(args):
   return tf.cast(tf.squeeze(mask, 3), tf.uint8)
 
 
+def _resize_surface_coordinate_masks(args):
+  detection_boxes, surface_coords, image_shape = args
+  surface_coords_v, surface_coords_u = tf.unstack(surface_coords, axis=-1)
+  surface_coords_v_reframed = ops.reframe_box_masks_to_image_masks(
+      surface_coords_v, detection_boxes, image_shape[0], image_shape[1])
+  surface_coords_u_reframed = ops.reframe_box_masks_to_image_masks(
+      surface_coords_u, detection_boxes, image_shape[0], image_shape[1])
+  return tf.stack([surface_coords_v_reframed, surface_coords_u_reframed],
+                  axis=-1)
+
+
 def _scale_keypoint_to_absolute(args):
   keypoints, image_shape = args
   return keypoint_ops.scale(keypoints, image_shape[0], image_shape[1])
@@ -720,6 +735,12 @@ def result_dict_for_batched_example(images,
         num_keypoints] bool tensor with keypoint visibilities (Optional).
       'groundtruth_labeled_classes': [batch_size, num_classes] int64
         tensor of 1-indexed classes. (Optional)
+      'groundtruth_dp_num_points': [batch_size, max_number_of_boxes] int32
+        tensor. (Optional)
+      'groundtruth_dp_part_ids': [batch_size, max_number_of_boxes,
+        max_sampled_points] int32 tensor. (Optional)
+      'groundtruth_dp_surface_coords_list': [batch_size, max_number_of_boxes,
+        max_sampled_points, 4] float32 tensor. (Optional)
     class_agnostic: Boolean indicating whether the detections are class-agnostic
       (i.e. binary). Default False.
     scale_to_absolute: Boolean indicating whether boxes and keypoints should be
@@ -747,12 +768,16 @@ def result_dict_for_batched_example(images,
     'detection_scores': [batch_size, max_detections] float32 tensor of scores.
     'detection_classes': [batch_size, max_detections] int64 tensor of 1-indexed
       classes.
-    'detection_masks': [batch_size, max_detections, H, W] float32 tensor of
-      binarized masks, reframed to full image masks. (Optional)
+    'detection_masks': [batch_size, max_detections, H, W] uint8 tensor of
+      instance masks, reframed to full image masks. Note that these may be
+      binarized (e.g. {0, 1}), or may contain 1-indexed part labels. (Optional)
     'detection_keypoints': [batch_size, max_detections, num_keypoints, 2]
       float32 tensor containing keypoint coordinates. (Optional)
     'detection_keypoint_scores': [batch_size, max_detections, num_keypoints]
       float32 tensor containing keypoint scores. (Optional)
+    'detection_surface_coords': [batch_size, max_detection, H, W, 2] float32
+      tensor with normalized surface coordinates (e.g. DensePose UV
+      coordinates). (Optional)
     'num_detections': [batch_size] int64 tensor containing number of valid
       detections.
     'groundtruth_boxes': [batch_size, num_boxes, 4] float32 tensor of boxes, in
@@ -844,14 +869,21 @@ def result_dict_for_batched_example(images,
 
   if detection_fields.detection_masks in detections:
     detection_masks = detections[detection_fields.detection_masks]
-    # TODO(rathodv): This should be done in model's postprocess
-    # function ideally.
     output_dict[detection_fields.detection_masks] = (
         shape_utils.static_or_dynamic_map_fn(
             _resize_detection_masks,
             elems=[detection_boxes, detection_masks,
                    original_image_spatial_shapes],
             dtype=tf.uint8))
+    if detection_fields.detection_surface_coords in detections:
+      detection_surface_coords = detections[
+          detection_fields.detection_surface_coords]
+      output_dict[detection_fields.detection_surface_coords] = (
+          shape_utils.static_or_dynamic_map_fn(
+              _resize_surface_coordinate_masks,
+              elems=[detection_boxes, detection_surface_coords,
+                     original_image_spatial_shapes],
+              dtype=tf.float32))
 
   if detection_fields.detection_keypoints in detections:
     detection_keypoints = detections[detection_fields.detection_keypoints]
@@ -1074,3 +1106,8 @@ def evaluator_options_from_eval_config(eval_config):
           'recall_upper_bound': (eval_config.recall_upper_bound)
       }
   return evaluator_options
+
+
+def has_densepose(eval_dict):
+  return (fields.DetectionResultFields.detection_masks in eval_dict and
+          fields.DetectionResultFields.detection_surface_coords in eval_dict)

research/object_detection/export_tflite_ssd_graph_lib_tf1_test.py

@@ -74,6 +74,9 @@ class FakeModel(model.DetectionModel):
   def restore_map(self, checkpoint_path, from_detection_checkpoint):
     pass
 
+  def restore_from_objects(self, fine_tune_checkpoint_type):
+    pass
+
   def loss(self, prediction_dict, true_image_shapes):
     pass
 
@@ -416,7 +419,7 @@ class ExportTfliteGraphTest(tf.test.TestCase):
     tflite_graph_file = self._export_graph_with_postprocessing_op(
         pipeline_config)
     self.assertTrue(os.path.exists(tflite_graph_file))
-    mock_get.assert_called_once()
+    self.assertEqual(1, mock_get.call_count)
 
 
 if __name__ == '__main__':

research/object_detection/exporter_lib_tf2_test.py

@@ -76,6 +76,9 @@ class FakeModel(model.DetectionModel):
   def restore_map(self, checkpoint_path, fine_tune_checkpoint_type):
     pass
 
+  def restore_from_objects(self, fine_tune_checkpoint_type):
+    pass
+
   def loss(self, prediction_dict, true_image_shapes):
     pass
 

research/object_detection/exporter_tf1_test.py

@@ -105,6 +105,9 @@ class FakeModel(model.DetectionModel):
   def restore_map(self, checkpoint_path, fine_tune_checkpoint_type):
     pass
 
+  def restore_from_objects(self, fine_tune_checkpoint_type):
+    pass
+
   def loss(self, prediction_dict, true_image_shapes):
     pass
 

research/object_detection/g3doc/challenge_evaluation.md

@@ -47,7 +47,7 @@ python object_detection/dataset_tools/oid_hierarchical_labels_expansion.py \
     --annotation_type=2
 ```
 
-1.  If you are not using Tensorflow, you can run evaluation directly using your
+1.  If you are not using TensorFlow, you can run evaluation directly using your
     algorithm's output and generated ground-truth files. {value=4}
 
 After step 3 you produced the ground-truth files suitable for running 'OID
@@ -73,7 +73,7 @@ For the Object Detection Track, the participants will be ranked on:
 
 -   "OpenImagesDetectionChallenge_Precision/mAP@0.5IOU"
 
-To use evaluation within Tensorflow training, use metric name
+To use evaluation within TensorFlow training, use metric name
 `oid_challenge_detection_metrics` in the evaluation config.
 
 ## Instance Segmentation Track
@@ -130,7 +130,7 @@ python object_detection/dataset_tools/oid_hierarchical_labels_expansion.py \
     --annotation_type=1
 ```
 
-1.  If you are not using Tensorflow, you can run evaluation directly using your
+1.  If you are not using TensorFlow, you can run evaluation directly using your
     algorithm's output and generated ground-truth files. {value=4}
 
 ```

research/object_detection/g3doc/configuring_jobs.md

@@ -2,7 +2,7 @@
 
 ## Overview
 
-The Tensorflow Object Detection API uses protobuf files to configure the
+The TensorFlow Object Detection API uses protobuf files to configure the
 training and evaluation process. The schema for the training pipeline can be
 found in object_detection/protos/pipeline.proto. At a high level, the config
 file is split into 5 parts:
@@ -60,7 +60,7 @@ to a value suited for the dataset the user is training on.
 
 ## Defining Inputs
 
-The Tensorflow Object Detection API accepts inputs in the TFRecord file format.
+The TensorFlow Object Detection API accepts inputs in the TFRecord file format.
 Users must specify the locations of both the training and evaluation files.
 Additionally, users should also specify a label map, which define the mapping
 between a class id and class name. The label map should be identical between
@@ -126,24 +126,6 @@ data_augmentation_options {
 }
 ```
 
-### Model Parameter Initialization
-
-While optional, it is highly recommended that users utilize other object
-detection checkpoints. Training an object detector from scratch can take days.
-To speed up the training process, it is recommended that users re-use the
-feature extractor parameters from a pre-existing image classification or
-object detection checkpoint. `train_config` provides two fields to specify
-pre-existing checkpoints: `fine_tune_checkpoint` and
-`from_detection_checkpoint`. `fine_tune_checkpoint` should provide a path to
-the pre-existing checkpoint
-(ie:"/usr/home/username/checkpoint/model.ckpt-#####").
-`from_detection_checkpoint` is a boolean value. If false, it assumes the
-checkpoint was from an object classification checkpoint. Note that starting
-from a detection checkpoint will usually result in a faster training job than
-a classification checkpoint.
-
-The list of provided checkpoints can be found [here](detection_model_zoo.md).
-
 ### Input Preprocessing
 
 The `data_augmentation_options` in `train_config` can be used to specify

research/object_detection/g3doc/context_rcnn.md

 # Context R-CNN
 
+[![TensorFlow 1.15](https://img.shields.io/badge/TensorFlow-1.15-FF6F00?logo=tensorflow)](https://github.com/tensorflow/tensorflow/releases/tag/v1.15.0)
+
 Context R-CNN is an object detection model that uses contextual features to
 improve object detection. See https://arxiv.org/abs/1912.03538 for more details.
 
@@ -30,9 +32,12 @@ pip install apache-beam
 ```
 
 and can be run locally, or on a cluster for efficient processing of large
-amounts of data. See the
+amounts of data. Note that generate_detection_data.py and
+generate_embedding_data.py both involve running inference, and may be very slow
+to run locally. See the
 [Apache Beam documentation](https://beam.apache.org/documentation/runners/dataflow/)
-for more information.
+for more information, and Google Cloud Documentation for a tutorial on
+[running Beam jobs on DataFlow](https://cloud.google.com/dataflow/docs/quickstarts/quickstart-python).
 
 ### Generating TfRecords from a set of images and a COCO-CameraTraps style JSON
 
@@ -191,3 +196,6 @@ python export_inference_graph.py \
     --side_input_types float,int
 
 ```
+
+If you have questions about Context R-CNN, please contact
+[Sara Beery](https://beerys.github.io/).

research/object_detection/g3doc/defining_your_own_model.md

@@ -2,14 +2,14 @@
 
 In this section, we discuss some of the abstractions that we use
 for defining detection models. If you would like to define a new model
-architecture for detection and use it in the Tensorflow Detection API,
+architecture for detection and use it in the TensorFlow Detection API,
 then this section should also serve as a high level guide to the files that you
 will need to edit to get your new model working.
 
 ## DetectionModels (`object_detection/core/model.py`)
 
 In order to be trained, evaluated, and exported for serving  using our
-provided binaries, all models under the Tensorflow Object Detection API must
+provided binaries, all models under the TensorFlow Object Detection API must
 implement the `DetectionModel` interface (see the full definition in `object_detection/core/model.py`).  In particular,
 each of these models are responsible for implementing 5 functions:
 
@@ -20,7 +20,7 @@ each of these models are responsible for implementing 5 functions:
   postprocess functions.
 * `postprocess`: Convert predicted output tensors to final detections.
 * `loss`: Compute scalar loss tensors with respect to provided groundtruth.
-* `restore`: Load a checkpoint into the Tensorflow graph.
+* `restore`: Load a checkpoint into the TensorFlow graph.
 
 Given a `DetectionModel` at training time, we pass each image batch through
 the following sequence of functions to compute a loss which can be optimized via
@@ -87,7 +87,7 @@ functions:
 * `_extract_box_classifier_features`: Extract second stage Box Classifier
   features.
 * `restore_from_classification_checkpoint_fn`: Load a checkpoint into the
-  Tensorflow graph.
+  TensorFlow graph.
 
 See the `object_detection/models/faster_rcnn_resnet_v1_feature_extractor.py`
 definition as one example. Some remarks:

research/object_detection/g3doc/evaluation_protocols.md

 # Supported object detection evaluation protocols
 
-The Tensorflow Object Detection API currently supports three evaluation protocols,
+The TensorFlow Object Detection API currently supports three evaluation protocols,
 that can be configured in `EvalConfig` by setting `metrics_set` to the
 corresponding value.
 

research/object_detection/g3doc/exporting_models.md

 # Exporting a trained model for inference
 
-After your model has been trained, you should export it to a Tensorflow
+[![TensorFlow 1.15](https://img.shields.io/badge/TensorFlow-1.15-FF6F00?logo=tensorflow)](https://github.com/tensorflow/tensorflow/releases/tag/v1.15.0)
+
+After your model has been trained, you should export it to a TensorFlow
 graph proto. A checkpoint will typically consist of three files:
 
 * model.ckpt-${CHECKPOINT_NUMBER}.data-00000-of-00001

research/object_detection/g3doc/faq.md

@@ -22,6 +22,6 @@ A: Similar to BackupHandler, syncing your fork to HEAD should make it work.
 ## Q: Why can't I get the inference time as reported in model zoo?
 A: The inference time reported in model zoo is mean time of testing hundreds of
 images with an internal machine. As mentioned in
-[Tensorflow detection model zoo](detection_model_zoo.md), this speed depends
+[TensorFlow detection model zoo](tf1_detection_zoo.md), this speed depends
 highly on one's specific hardware configuration and should be treated more as
 relative timing.

research/object_detection/g3doc/installation.md

-# Installation
-
-## Dependencies
-
-Tensorflow Object Detection API depends on the following libraries:
-
-*   Protobuf 3.0.0
-*   Python-tk
-*   Pillow 1.0
-*   lxml
-*   tf-slim (https://github.com/google-research/tf-slim)
-*   slim (which is included in the "tensorflow/models/research/" checkout)
-*   Jupyter notebook
-*   Matplotlib
-*   Tensorflow (1.15.0)
-*   Cython
-*   contextlib2
-*   cocoapi
-
-For detailed steps to install Tensorflow, follow the [Tensorflow installation
-instructions](https://www.tensorflow.org/install/). A typical user can install
-Tensorflow using one of the following commands:
-
-``` bash
-# For CPU
-pip install tensorflow
-# For GPU
-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
-pip install --user Cython
-pip install --user contextlib2
-pip install --user jupyter
-pip install --user matplotlib
-pip install --user tf_slim
-```
-
-Alternatively, users can install dependencies using pip:
-
-```bash
-pip install --user Cython
-pip install --user contextlib2
-pip install --user pillow
-pip install --user lxml
-pip install --user jupyter
-pip install --user matplotlib
-pip install --user tf_slim
-```
-
-<!-- common_typos_disable -->
-**Note**: sometimes "sudo apt-get install protobuf-compiler" will install
-Protobuf 3+ versions for you and some users have issues when using 3.5.
-If that is your case, try the [manual](#Manual-protobuf-compiler-installation-and-usage) installation.
-
-## Download the tensorflow/models repository
-
-```bash
-git clone https://github.com/tensorflow/models.git
-```
-
-To use this library, you need to download this repository, whenever it says
-`<path-to-tensorflow>` it will be referring to the folder that you downloaded
-this repository into.
-
-## COCO API installation
-
-Download the
-[cocoapi](https://github.com/cocodataset/cocoapi) and
-copy the pycocotools subfolder to the tensorflow/models/research directory if
-you are interested in using COCO evaluation metrics. The default metrics are
-based on those used in Pascal VOC evaluation. To use the COCO object detection
-metrics add `metrics_set: "coco_detection_metrics"` to the `eval_config` message
-in the config file. To use the COCO instance segmentation metrics add
-`metrics_set: "coco_mask_metrics"` to the `eval_config` message in the config
-file.
-
-```bash
-git clone https://github.com/cocodataset/cocoapi.git
-cd cocoapi/PythonAPI
-make
-cp -r pycocotools <path_to_tensorflow>/models/research/
-```
-
-Alternatively, users can install `pycocotools` using pip:
-
-```bash
-pip install --user pycocotools
-```
-
-## Protobuf Compilation
-
-The Tensorflow Object Detection API uses Protobufs to configure model and
-training parameters. Before the framework can be used, the Protobuf libraries
-must be compiled. This should be done by running the following command from
-the [tensorflow/models/research/
-](https://github.com/tensorflow/models/tree/master/research/)
-directory:
-
-
-``` bash
-# From tensorflow/models/research/
-protoc object_detection/protos/*.proto --python_out=.
-```
-
-**Note**: If you're getting errors while compiling, you might be using an incompatible protobuf compiler. If that's the case, use the following manual installation
-
-## Manual protobuf-compiler installation and usage
-
-**If you are on linux:**
-
-Download and install the 3.0 release of protoc, then unzip the file.
-
-```bash
-# From tensorflow/models/research/
-wget -O protobuf.zip https://github.com/google/protobuf/releases/download/v3.0.0/protoc-3.0.0-linux-x86_64.zip
-unzip protobuf.zip
-```
-
-Run the compilation process again, but use the downloaded version of protoc
-
-```bash
-# From tensorflow/models/research/
-./bin/protoc object_detection/protos/*.proto --python_out=.
-```
-
-**If you are on MacOS:**
-
-If you have homebrew, download and install the protobuf with
-```brew install protobuf```
-
-Alternately, run:
-```PROTOC_ZIP=protoc-3.3.0-osx-x86_64.zip
-curl -OL https://github.com/google/protobuf/releases/download/v3.3.0/$PROTOC_ZIP
-sudo unzip -o $PROTOC_ZIP -d /usr/local bin/protoc
-rm -f $PROTOC_ZIP
-```
-
-Run the compilation process again:
-
-``` bash
-# From tensorflow/models/research/
-protoc object_detection/protos/*.proto --python_out=.
-```
-
-## Add Libraries to PYTHONPATH
-
-When running locally, the tensorflow/models/research/ and slim directories
-should be appended to PYTHONPATH. This can be done by running the following from
-tensorflow/models/research/:
-
-
-``` bash
-# From tensorflow/models/research/
-export PYTHONPATH=$PYTHONPATH:`pwd`:`pwd`/slim
-```
-
-Note: This command needs to run from every new terminal you start. If you wish
-to avoid running this manually, you can add it as a new line to the end of your
-~/.bashrc file, replacing \`pwd\` with the absolute path of
-tensorflow/models/research on your system. After updating ~/.bashrc file you
-can run the following command:
-
-Note: Some of the functions defined in tensorflow/models/research/slim has been
-moved to [tf-slim](https://github.com/google-research/tf-slim), so installing
-tf_slim is required now.
-
-``` bash
-source ~/.bashrc
-```
-
-# Testing the Installation
-
-You can test that you have correctly installed the Tensorflow Object Detection\
-API by running the following command:
-
-
-```bash
-# If using Tensorflow 1.X:
-python object_detection/builders/model_builder_tf1_test.py
-```