Merge pull request #3293 from pkulzc/master

Internal changes of object_detection 

research/object_detection/samples/configs/faster_rcnn_inception_resnet_v2_atrous_coco.config

@@ -143,5 +143,4 @@ eval_input_reader: {
   label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
   shuffle: false
   num_readers: 1
-  num_epochs: 1
 }

research/object_detection/samples/configs/faster_rcnn_inception_resnet_v2_atrous_cosine_lr_coco.config

+# Faster R-CNN with Inception Resnet v2, Atrous version, with Cosine
+# Learning Rate schedule.
+# Trained on COCO, initialized from Imagenet classification checkpoint
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 600
+        max_dimension: 1024
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_inception_resnet_v2'
+      first_stage_features_stride: 8
+    }
+    first_stage_anchor_generator {
+      grid_anchor_generator {
+        scales: [0.25, 0.5, 1.0, 2.0]
+        aspect_ratios: [0.5, 1.0, 2.0]
+        height_stride: 8
+        width_stride: 8
+      }
+    }
+    first_stage_atrous_rate: 2
+    first_stage_box_predictor_conv_hyperparams {
+      op: CONV
+      regularizer {
+        l2_regularizer {
+          weight: 0.0
+        }
+      }
+      initializer {
+        truncated_normal_initializer {
+          stddev: 0.01
+        }
+      }
+    }
+    first_stage_nms_score_threshold: 0.0
+    first_stage_nms_iou_threshold: 0.7
+    first_stage_max_proposals: 300
+    first_stage_localization_loss_weight: 2.0
+    first_stage_objectness_loss_weight: 1.0
+    initial_crop_size: 17
+    maxpool_kernel_size: 1
+    maxpool_stride: 1
+    second_stage_box_predictor {
+      mask_rcnn_box_predictor {
+        use_dropout: false
+        dropout_keep_probability: 1.0
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+      }
+    }
+    second_stage_post_processing {
+      batch_non_max_suppression {
+        score_threshold: 0.0
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SOFTMAX
+    }
+    second_stage_localization_loss_weight: 2.0
+    second_stage_classification_loss_weight: 1.0
+  }
+}
+
+train_config: {
+  batch_size: 1
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 0.0006
+          total_steps: 1200000
+          warmup_learning_rate: 0.00006
+          warmup_steps: 20000
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+}
+
+eval_config: {
+  num_examples: 8000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}

research/object_detection/samples/configs/faster_rcnn_nas_coco.config

@@ -8,7 +8,7 @@ model {
   faster_rcnn {
     num_classes: 90
     image_resizer {
-      # 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.
@@ -43,7 +43,7 @@ model {
     }
     first_stage_nms_score_threshold: 0.0
     first_stage_nms_iou_threshold: 0.7
-    first_stage_max_proposals: 50
+    first_stage_max_proposals: 500
     first_stage_localization_loss_weight: 2.0
     first_stage_objectness_loss_weight: 1.0
     initial_crop_size: 17
@@ -131,7 +131,6 @@ train_input_reader: {
 }
 
 eval_config: {
-  metrics_set: "pascal_voc_metrics"
   num_examples: 8000
   # Note: The below line limits the evaluation process to 10 evaluations.
   # Remove the below line to evaluate indefinitely.
@@ -144,5 +143,4 @@ eval_input_reader: {
   label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
   shuffle: false
   num_readers: 1
-  num_epochs: 1
 }

research/object_detection/samples/configs/faster_rcnn_resnet101_atrous_coco.config

+# Faster R-CNN with Resnet-101 (v1), Atrous version
+# Trained on COCO, initialized from Imagenet classification checkpoint
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 600
+        max_dimension: 1024
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_resnet101'
+      first_stage_features_stride: 8
+    }
+    first_stage_anchor_generator {
+      grid_anchor_generator {
+        scales: [0.25, 0.5, 1.0, 2.0]
+        aspect_ratios: [0.5, 1.0, 2.0]
+        height_stride: 8
+        width_stride: 8
+      }
+    }
+    first_stage_atrous_rate: 2
+    first_stage_box_predictor_conv_hyperparams {
+      op: CONV
+      regularizer {
+        l2_regularizer {
+          weight: 0.0
+        }
+      }
+      initializer {
+        truncated_normal_initializer {
+          stddev: 0.01
+        }
+      }
+    }
+    first_stage_nms_score_threshold: 0.0
+    first_stage_nms_iou_threshold: 0.7
+    first_stage_max_proposals: 300
+    first_stage_localization_loss_weight: 2.0
+    first_stage_objectness_loss_weight: 1.0
+    initial_crop_size: 14
+    maxpool_kernel_size: 2
+    maxpool_stride: 2
+    second_stage_box_predictor {
+      mask_rcnn_box_predictor {
+        use_dropout: false
+        dropout_keep_probability: 1.0
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+      }
+    }
+    second_stage_post_processing {
+      batch_non_max_suppression {
+        score_threshold: 0.0
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 300
+      }
+      score_converter: SOFTMAX
+    }
+    second_stage_localization_loss_weight: 2.0
+    second_stage_classification_loss_weight: 1.0
+  }
+}
+
+train_config: {
+  batch_size: 1
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        manual_step_learning_rate {
+          initial_learning_rate: 0.0003
+          schedule {
+            step: 0
+            learning_rate: .0003
+          }
+          schedule {
+            step: 900000
+            learning_rate: .00003
+          }
+          schedule {
+            step: 1200000
+            learning_rate: .000003
+          }
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+}
+
+eval_config: {
+  num_examples: 8000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}

research/object_detection/samples/configs/faster_rcnn_resnet101_coco.config

-# Faster R-CNN with Resnet-101 (v1) configuration for MSCOCO Dataset.
+# Faster R-CNN with Resnet-101 (v1), configuration for MSCOCO Dataset.
 # Users should configure the fine_tune_checkpoint field in the train config as
 # well as the label_map_path and input_path fields in the train_input_reader and
 # eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
@@ -109,11 +109,6 @@ train_config: {
   gradient_clipping_by_norm: 10.0
   fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
   from_detection_checkpoint: true
-  # Note: The below line limits the training process to 200K steps, which we
-  # empirically found to be sufficient enough to train the pets dataset. This
-  # effectively bypasses the learning rate schedule (the learning rate will
-  # never decay). Remove the below line to train indefinitely.
-  num_steps: 200000
   data_augmentation_options {
     random_horizontal_flip {
     }
@@ -141,5 +136,4 @@ eval_input_reader: {
   label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
   shuffle: false
   num_readers: 1
-  num_epochs: 1
 }

research/object_detection/samples/configs/faster_rcnn_resnet152_coco.config

@@ -141,5 +141,4 @@ eval_input_reader: {
   label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
   shuffle: false
   num_readers: 1
-  num_epochs: 1
 }

research/object_detection/samples/configs/faster_rcnn_resnet50_coco.config

@@ -141,5 +141,4 @@ eval_input_reader: {
   label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
   shuffle: false
   num_readers: 1
-  num_epochs: 1
 }

research/object_detection/samples/configs/mask_rcnn_inception_resnet_v2_atrous_coco.config

+# Mask R-CNN with Inception Resnet v2, Atrous version
+# Configured for MSCOCO Dataset.
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 800
+        max_dimension: 1365
+      }
+    }
+    number_of_stages: 3
+    feature_extractor {
+      type: 'faster_rcnn_inception_resnet_v2'
+      first_stage_features_stride: 8
+    }
+    first_stage_anchor_generator {
+      grid_anchor_generator {
+        scales: [0.25, 0.5, 1.0, 2.0]
+        aspect_ratios: [0.5, 1.0, 2.0]
+        height_stride: 8
+        width_stride: 8
+      }
+    }
+    first_stage_atrous_rate: 2
+    first_stage_box_predictor_conv_hyperparams {
+      op: CONV
+      regularizer {
+        l2_regularizer {
+          weight: 0.0
+        }
+      }
+      initializer {
+        truncated_normal_initializer {
+          stddev: 0.01
+        }
+      }
+    }
+    first_stage_nms_score_threshold: 0.0
+    first_stage_nms_iou_threshold: 0.7
+    first_stage_max_proposals: 300
+    first_stage_localization_loss_weight: 2.0
+    first_stage_objectness_loss_weight: 1.0
+    initial_crop_size: 17
+    maxpool_kernel_size: 1
+    maxpool_stride: 1
+    second_stage_box_predictor {
+      mask_rcnn_box_predictor {
+        use_dropout: false
+        dropout_keep_probability: 1.0
+        predict_instance_masks: true
+        mask_height: 33
+        mask_width: 33
+        mask_prediction_conv_depth: 0
+        mask_prediction_num_conv_layers: 4
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+        conv_hyperparams {
+          op: CONV
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            truncated_normal_initializer {
+              stddev: 0.01
+            }
+          }
+        }
+      }
+    }
+    second_stage_post_processing {
+      batch_non_max_suppression {
+        score_threshold: 0.0
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SOFTMAX
+    }
+    second_stage_localization_loss_weight: 2.0
+    second_stage_classification_loss_weight: 1.0
+    second_stage_mask_prediction_loss_weight: 4.0
+  }
+}
+
+train_config: {
+  batch_size: 1
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        manual_step_learning_rate {
+          initial_learning_rate: 0.0003
+          schedule {
+            step: 0
+            learning_rate: .0003
+          }
+          schedule {
+            step: 900000
+            learning_rate: .00003
+          }
+          schedule {
+            step: 1200000
+            learning_rate: .000003
+          }
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
+  from_detection_checkpoint: true
+  # Note: The below line limits the training process to 200K steps, which we
+  # empirically found to be sufficient enough to train the pets dataset. This
+  # effectively bypasses the learning rate schedule (the learning rate will
+  # never decay). Remove the below line to train indefinitely.
+  num_steps: 200000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+}
+
+eval_config: {
+  num_examples: 8000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}

research/object_detection/samples/configs/mask_rcnn_inception_v2_coco.config

+# Mask R-CNN with Inception V2
+# Configured for MSCOCO Dataset.
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 800
+        max_dimension: 1365
+      }
+    }
+    number_of_stages: 3
+    feature_extractor {
+      type: 'faster_rcnn_inception_v2'
+      first_stage_features_stride: 16
+    }
+    first_stage_anchor_generator {
+      grid_anchor_generator {
+        scales: [0.25, 0.5, 1.0, 2.0]
+        aspect_ratios: [0.5, 1.0, 2.0]
+        height_stride: 16
+        width_stride: 16
+      }
+    }
+    first_stage_box_predictor_conv_hyperparams {
+      op: CONV
+      regularizer {
+        l2_regularizer {
+          weight: 0.0
+        }
+      }
+      initializer {
+        truncated_normal_initializer {
+          stddev: 0.01
+        }
+      }
+    }
+    first_stage_nms_score_threshold: 0.0
+    first_stage_nms_iou_threshold: 0.7
+    first_stage_max_proposals: 300
+    first_stage_localization_loss_weight: 2.0
+    first_stage_objectness_loss_weight: 1.0
+    initial_crop_size: 14
+    maxpool_kernel_size: 2
+    maxpool_stride: 2
+    second_stage_box_predictor {
+      mask_rcnn_box_predictor {
+        use_dropout: false
+        dropout_keep_probability: 1.0
+        predict_instance_masks: true
+        mask_height: 15
+        mask_width: 15
+        mask_prediction_conv_depth: 0
+        mask_prediction_num_conv_layers: 2
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+        conv_hyperparams {
+          op: CONV
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            truncated_normal_initializer {
+              stddev: 0.01
+            }
+          }
+        }
+      }
+    }
+    second_stage_post_processing {
+      batch_non_max_suppression {
+        score_threshold: 0.0
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 300
+      }
+      score_converter: SOFTMAX
+    }
+    second_stage_localization_loss_weight: 2.0
+    second_stage_classification_loss_weight: 1.0
+    second_stage_mask_prediction_loss_weight: 4.0
+  }
+}
+
+train_config: {
+  batch_size: 1
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        manual_step_learning_rate {
+          initial_learning_rate: 0.0002
+          schedule {
+            step: 0
+            learning_rate: .0002
+          }
+          schedule {
+            step: 900000
+            learning_rate: .00002
+          }
+          schedule {
+            step: 1200000
+            learning_rate: .000002
+          }
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
+  from_detection_checkpoint: true
+  # Note: The below line limits the training process to 200K steps, which we
+  # empirically found to be sufficient enough to train the pets dataset. This
+  # effectively bypasses the learning rate schedule (the learning rate will
+  # never decay). Remove the below line to train indefinitely.
+  num_steps: 200000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+}
+
+eval_config: {
+  num_examples: 8000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}

research/object_detection/samples/configs/mask_rcnn_resnet101_atrous_coco.config

+# Mask R-CNN with Resnet-101 (v1), Atrous version
+# Configured for MSCOCO Dataset.
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 800
+        max_dimension: 1365
+      }
+    }
+    number_of_stages: 3
+    feature_extractor {
+      type: 'faster_rcnn_resnet101'
+      first_stage_features_stride: 8
+    }
+    first_stage_anchor_generator {
+      grid_anchor_generator {
+        scales: [0.25, 0.5, 1.0, 2.0]
+        aspect_ratios: [0.5, 1.0, 2.0]
+        height_stride: 8
+        width_stride: 8
+      }
+    }
+    first_stage_atrous_rate: 2
+    first_stage_box_predictor_conv_hyperparams {
+      op: CONV
+      regularizer {
+        l2_regularizer {
+          weight: 0.0
+        }
+      }
+      initializer {
+        truncated_normal_initializer {
+          stddev: 0.01
+        }
+      }
+    }
+    first_stage_nms_score_threshold: 0.0
+    first_stage_nms_iou_threshold: 0.7
+    first_stage_max_proposals: 300
+    first_stage_localization_loss_weight: 2.0
+    first_stage_objectness_loss_weight: 1.0
+    initial_crop_size: 14
+    maxpool_kernel_size: 2
+    maxpool_stride: 2
+    second_stage_box_predictor {
+      mask_rcnn_box_predictor {
+        use_dropout: false
+        dropout_keep_probability: 1.0
+        predict_instance_masks: true
+        mask_height: 33
+        mask_width: 33
+        mask_prediction_conv_depth: 0
+        mask_prediction_num_conv_layers: 4
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+        conv_hyperparams {
+          op: CONV
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            truncated_normal_initializer {
+              stddev: 0.01
+            }
+          }
+        }
+      }
+    }
+    second_stage_post_processing {
+      batch_non_max_suppression {
+        score_threshold: 0.0
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 300
+      }
+      score_converter: SOFTMAX
+    }
+    second_stage_localization_loss_weight: 2.0
+    second_stage_classification_loss_weight: 1.0
+    second_stage_mask_prediction_loss_weight: 4.0
+  }
+}
+
+train_config: {
+  batch_size: 1
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        manual_step_learning_rate {
+          initial_learning_rate: 0.0003
+          schedule {
+            step: 0
+            learning_rate: .0003
+          }
+          schedule {
+            step: 900000
+            learning_rate: .00003
+          }
+          schedule {
+            step: 1200000
+            learning_rate: .000003
+          }
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
+  from_detection_checkpoint: true
+  # Note: The below line limits the training process to 200K steps, which we
+  # empirically found to be sufficient enough to train the pets dataset. This
+  # effectively bypasses the learning rate schedule (the learning rate will
+  # never decay). Remove the below line to train indefinitely.
+  num_steps: 200000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+}
+
+eval_config: {
+  num_examples: 8000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}

research/object_detection/samples/configs/mask_rcnn_resnet101_pets.config

+# Mask R-CNN with Resnet-101 (v1) configured for the Oxford-IIIT Pet Dataset.
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+
+model {
+  faster_rcnn {
+    num_classes: 37
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 600
+        max_dimension: 1024
+      }
+    }
+    number_of_stages: 3
+    feature_extractor {
+      type: 'faster_rcnn_resnet101'
+      first_stage_features_stride: 16
+    }
+    first_stage_anchor_generator {
+      grid_anchor_generator {
+        scales: [0.25, 0.5, 1.0, 2.0]
+        aspect_ratios: [0.5, 1.0, 2.0]
+        height_stride: 16
+        width_stride: 16
+      }
+    }
+    first_stage_box_predictor_conv_hyperparams {
+      op: CONV
+      regularizer {
+        l2_regularizer {
+          weight: 0.0
+        }
+      }
+      initializer {
+        truncated_normal_initializer {
+          stddev: 0.01
+        }
+      }
+    }
+    first_stage_nms_score_threshold: 0.0
+    first_stage_nms_iou_threshold: 0.7
+    first_stage_max_proposals: 300
+    first_stage_localization_loss_weight: 2.0
+    first_stage_objectness_loss_weight: 1.0
+    initial_crop_size: 14
+    maxpool_kernel_size: 2
+    maxpool_stride: 2
+    second_stage_box_predictor {
+      mask_rcnn_box_predictor {
+        use_dropout: false
+        dropout_keep_probability: 1.0
+        predict_instance_masks: true
+        conv_hyperparams {
+          op: CONV
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            truncated_normal_initializer {
+              stddev: 0.01
+            }
+          }
+        }
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+      }
+    }
+    second_stage_post_processing {
+      batch_non_max_suppression {
+        score_threshold: 0.0
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 300
+      }
+      score_converter: SOFTMAX
+    }
+    second_stage_localization_loss_weight: 2.0
+    second_stage_classification_loss_weight: 1.0
+  }
+}
+
+train_config: {
+  batch_size: 1
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        manual_step_learning_rate {
+          initial_learning_rate: 0.0007
+          schedule {
+            step: 0
+            learning_rate: 0.0007
+          }
+          schedule {
+            step: 15000
+            learning_rate: 0.00007
+          }
+          schedule {
+            step: 30000
+            learning_rate: 0.000007
+          }
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
+  from_detection_checkpoint: true
+  # Note: The below line limits the training process to 200K steps, which we
+  # empirically found to be sufficient enough to train the pets dataset. This
+  # effectively bypasses the learning rate schedule (the learning rate will
+  # never decay). Remove the below line to train indefinitely.
+  num_steps: 200000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/pet_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/pet_label_map.pbtxt"
+}
+
+eval_config: {
+  num_examples: 2000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/pet_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/pet_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}

research/object_detection/samples/configs/mask_rcnn_resnet50_atrous_coco.config

+# Mask R-CNN with Resnet-50 (v1), Atrous version
+# Configured for MSCOCO Dataset.
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 800
+        max_dimension: 1365
+      }
+    }
+    number_of_stages: 3
+    feature_extractor {
+      type: 'faster_rcnn_resnet50'
+      first_stage_features_stride: 8
+    }
+    first_stage_anchor_generator {
+      grid_anchor_generator {
+        scales: [0.25, 0.5, 1.0, 2.0]
+        aspect_ratios: [0.5, 1.0, 2.0]
+        height_stride: 8
+        width_stride: 8
+      }
+    }
+    first_stage_atrous_rate: 2
+    first_stage_box_predictor_conv_hyperparams {
+      op: CONV
+      regularizer {
+        l2_regularizer {
+          weight: 0.0
+        }
+      }
+      initializer {
+        truncated_normal_initializer {
+          stddev: 0.01
+        }
+      }
+    }
+    first_stage_nms_score_threshold: 0.0
+    first_stage_nms_iou_threshold: 0.7
+    first_stage_max_proposals: 300
+    first_stage_localization_loss_weight: 2.0
+    first_stage_objectness_loss_weight: 1.0
+    initial_crop_size: 14
+    maxpool_kernel_size: 2
+    maxpool_stride: 2
+    second_stage_box_predictor {
+      mask_rcnn_box_predictor {
+        use_dropout: false
+        dropout_keep_probability: 1.0
+        predict_instance_masks: true
+        mask_height: 33
+        mask_width: 33
+        mask_prediction_conv_depth: 0
+        mask_prediction_num_conv_layers: 4
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+        conv_hyperparams {
+          op: CONV
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            truncated_normal_initializer {
+              stddev: 0.01
+            }
+          }
+        }
+      }
+    }
+    second_stage_post_processing {
+      batch_non_max_suppression {
+        score_threshold: 0.0
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 300
+      }
+      score_converter: SOFTMAX
+    }
+    second_stage_localization_loss_weight: 2.0
+    second_stage_classification_loss_weight: 1.0
+    second_stage_mask_prediction_loss_weight: 4.0
+  }
+}
+
+train_config: {
+  batch_size: 1
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        manual_step_learning_rate {
+          initial_learning_rate: 0.0003
+          schedule {
+            step: 0
+            learning_rate: .0003
+          }
+          schedule {
+            step: 900000
+            learning_rate: .00003
+          }
+          schedule {
+            step: 1200000
+            learning_rate: .000003
+          }
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
+  from_detection_checkpoint: true
+  # Note: The below line limits the training process to 200K steps, which we
+  # empirically found to be sufficient enough to train the pets dataset. This
+  # effectively bypasses the learning rate schedule (the learning rate will
+  # never decay). Remove the below line to train indefinitely.
+  num_steps: 200000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+}
+
+eval_config: {
+  num_examples: 8000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}

research/object_detection/samples/configs/rfcn_resnet101_coco.config

@@ -138,5 +138,4 @@ eval_input_reader: {
   label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
   shuffle: false
   num_readers: 1
-  num_epochs: 1
 }

research/object_detection/samples/configs/ssd_inception_v2_coco.config

@@ -102,12 +102,10 @@ model {
     loss {
       classification_loss {
         weighted_sigmoid {
-          anchorwise_output: true
         }
       }
       localization_loss {
         weighted_smooth_l1 {
-          anchorwise_output: true
         }
       }
       hard_example_miner {
@@ -187,5 +185,4 @@ eval_input_reader: {
   label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
   shuffle: false
   num_readers: 1
-  num_epochs: 1
 }

research/object_detection/samples/configs/ssd_inception_v2_pets.config

@@ -102,12 +102,10 @@ model {
     loss {
       classification_loss {
         weighted_sigmoid {
-          anchorwise_output: true
         }
       }
       localization_loss {
         weighted_smooth_l1 {
-          anchorwise_output: true
         }
       }
       hard_example_miner {

research/object_detection/samples/configs/ssd_inception_v3_pets.config

+# SSD with Inception v2 configured for Oxford-IIIT Pets Dataset.
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+
+model {
+  ssd {
+    num_classes: 37
+    box_coder {
+      faster_rcnn_box_coder {
+        y_scale: 10.0
+        x_scale: 10.0
+        height_scale: 5.0
+        width_scale: 5.0
+      }
+    }
+    matcher {
+      argmax_matcher {
+        matched_threshold: 0.5
+        unmatched_threshold: 0.5
+        ignore_thresholds: false
+        negatives_lower_than_unmatched: true
+        force_match_for_each_row: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    anchor_generator {
+      ssd_anchor_generator {
+        num_layers: 6
+        min_scale: 0.2
+        max_scale: 0.95
+        aspect_ratios: 1.0
+        aspect_ratios: 2.0
+        aspect_ratios: 0.5
+        aspect_ratios: 3.0
+        aspect_ratios: 0.3333
+        reduce_boxes_in_lowest_layer: true
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 300
+        width: 300
+      }
+    }
+    box_predictor {
+      convolutional_box_predictor {
+        min_depth: 0
+        max_depth: 0
+        num_layers_before_predictor: 0
+        use_dropout: false
+        dropout_keep_probability: 0.8
+        kernel_size: 3
+        box_code_size: 4
+        apply_sigmoid_to_scores: false
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            truncated_normal_initializer {
+              stddev: 0.03
+              mean: 0.0
+            }
+          }
+        }
+      }
+    }
+    feature_extractor {
+      type: 'ssd_inception_v3'
+      min_depth: 16
+      depth_multiplier: 1.0
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.1
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          train: true,
+          scale: true,
+          center: true,
+          decay: 0.9997,
+          epsilon: 0.01,
+        }
+      }
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid {
+        }
+      }
+      localization_loss {
+        weighted_smooth_l1 {
+        }
+      }
+      hard_example_miner {
+        num_hard_examples: 3000
+        iou_threshold: 0.99
+        loss_type: CLASSIFICATION
+        max_negatives_per_positive: 3
+        min_negatives_per_image: 0
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    normalize_loss_by_num_matches: true
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 1e-8
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  batch_size: 24
+  optimizer {
+    rms_prop_optimizer: {
+      learning_rate: {
+        exponential_decay_learning_rate {
+          initial_learning_rate: 0.004
+          decay_steps: 800720
+          decay_factor: 0.95
+        }
+      }
+      momentum_optimizer_value: 0.9
+      decay: 0.9
+      epsilon: 1.0
+    }
+  }
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
+  from_detection_checkpoint: true
+  # Note: The below line limits the training process to 200K steps, which we
+  # empirically found to be sufficient enough to train the pets dataset. This
+  # effectively bypasses the learning rate schedule (the learning rate will
+  # never decay). Remove the below line to train indefinitely.
+  num_steps: 200000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    ssd_random_crop {
+    }
+  }
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/pet_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/pet_label_map.pbtxt"
+}
+
+eval_config: {
+  num_examples: 2000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/pet_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/pet_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}

research/object_detection/samples/configs/ssd_mobilenet_v1_coco.config

@@ -108,12 +108,10 @@ model {
     loss {
       classification_loss {
         weighted_sigmoid {
-          anchorwise_output: true
         }
       }
       localization_loss {
         weighted_smooth_l1 {
-          anchorwise_output: true
         }
       }
       hard_example_miner {
@@ -193,5 +191,4 @@ eval_input_reader: {
   label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
   shuffle: false
   num_readers: 1
-  num_epochs: 1
 }

research/object_detection/samples/configs/ssd_mobilenet_v1_focal_loss_coco.config

+# SSD with Mobilenet v1 configuration for MSCOCO Dataset.
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+# TPU-compatible
+
+model {
+  ssd {
+    num_classes: 90
+    box_coder {
+      faster_rcnn_box_coder {
+        y_scale: 10.0
+        x_scale: 10.0
+        height_scale: 5.0
+        width_scale: 5.0
+      }
+    }
+    matcher {
+      argmax_matcher {
+        matched_threshold: 0.5
+        unmatched_threshold: 0.5
+        ignore_thresholds: false
+        negatives_lower_than_unmatched: true
+        force_match_for_each_row: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    anchor_generator {
+      ssd_anchor_generator {
+        num_layers: 6
+        min_scale: 0.2
+        max_scale: 0.95
+        aspect_ratios: 1.0
+        aspect_ratios: 2.0
+        aspect_ratios: 0.5
+        aspect_ratios: 3.0
+        aspect_ratios: 0.3333
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 300
+        width: 300
+      }
+    }
+    box_predictor {
+      convolutional_box_predictor {
+        min_depth: 0
+        max_depth: 0
+        num_layers_before_predictor: 0
+        use_dropout: false
+        dropout_keep_probability: 0.8
+        kernel_size: 1
+        box_code_size: 4
+        apply_sigmoid_to_scores: false
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            truncated_normal_initializer {
+              stddev: 0.03
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            train: true,
+            scale: true,
+            center: true,
+            decay: 0.9997,
+            epsilon: 0.001,
+          }
+        }
+      }
+    }
+    feature_extractor {
+      type: 'ssd_mobilenet_v1'
+      min_depth: 16
+      depth_multiplier: 1.0
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          train: true,
+          scale: true,
+          center: true,
+          decay: 0.9997,
+          epsilon: 0.001,
+        }
+      }
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.75
+          gamma: 2.0
+        }
+      }
+      localization_loss {
+        weighted_smooth_l1 {
+        }
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    normalize_loss_by_num_matches: true
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 1e-8
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  batch_size: 24
+  optimizer {
+    rms_prop_optimizer: {
+      learning_rate: {
+        exponential_decay_learning_rate {
+          initial_learning_rate: 0.004
+          decay_steps: 800720
+          decay_factor: 0.95
+        }
+      }
+      momentum_optimizer_value: 0.9
+      decay: 0.9
+      epsilon: 1.0
+    }
+  }
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
+  from_detection_checkpoint: true
+  # Note: The below line limits the training process to 200K steps, which we
+  # empirically found to be sufficient enough to train the pets dataset. This
+  # effectively bypasses the learning rate schedule (the learning rate will
+  # never decay). Remove the below line to train indefinitely.
+  num_steps: 200000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    ssd_random_crop {
+    }
+  }
+  max_number_of_boxes: 50
+  unpad_groundtruth_tensors: false
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+}
+
+eval_config: {
+  num_examples: 8000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}

research/object_detection/samples/configs/ssd_mobilenet_v1_focal_loss_pets.config

+# SSD with Mobilenet v1, configured for Oxford-IIIT Pets Dataset.
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+# TPU-compatible
+
+model {
+  ssd {
+    num_classes: 37
+    box_coder {
+      faster_rcnn_box_coder {
+        y_scale: 10.0
+        x_scale: 10.0
+        height_scale: 5.0
+        width_scale: 5.0
+      }
+    }
+    matcher {
+      argmax_matcher {
+        matched_threshold: 0.5
+        unmatched_threshold: 0.5
+        ignore_thresholds: false
+        negatives_lower_than_unmatched: true
+        force_match_for_each_row: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    anchor_generator {
+      ssd_anchor_generator {
+        num_layers: 6
+        min_scale: 0.2
+        max_scale: 0.95
+        aspect_ratios: 1.0
+        aspect_ratios: 2.0
+        aspect_ratios: 0.5
+        aspect_ratios: 3.0
+        aspect_ratios: 0.3333
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 300
+        width: 300
+      }
+    }
+    box_predictor {
+      convolutional_box_predictor {
+        min_depth: 0
+        max_depth: 0
+        num_layers_before_predictor: 0
+        use_dropout: false
+        dropout_keep_probability: 0.8
+        kernel_size: 1
+        box_code_size: 4
+        apply_sigmoid_to_scores: false
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            truncated_normal_initializer {
+              stddev: 0.03
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            train: true,
+            scale: true,
+            center: true,
+            decay: 0.9997,
+            epsilon: 0.001,
+          }
+        }
+      }
+    }
+    feature_extractor {
+      type: 'ssd_mobilenet_v1'
+      min_depth: 16
+      depth_multiplier: 1.0
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          train: true,
+          scale: true,
+          center: true,
+          decay: 0.9997,
+          epsilon: 0.001,
+        }
+      }
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.75
+          gamma: 2.0
+        }
+      }
+      localization_loss {
+        weighted_smooth_l1 {
+        }
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    normalize_loss_by_num_matches: true
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 1e-8
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  batch_size: 24
+  optimizer {
+    rms_prop_optimizer: {
+      learning_rate: {
+        exponential_decay_learning_rate {
+          initial_learning_rate: 0.004
+          decay_steps: 800720
+          decay_factor: 0.95
+        }
+      }
+      momentum_optimizer_value: 0.9
+      decay: 0.9
+      epsilon: 1.0
+    }
+  }
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
+  from_detection_checkpoint: true
+  # Note: The below line limits the training process to 200K steps, which we
+  # empirically found to be sufficient enough to train the pets dataset. This
+  # effectively bypasses the learning rate schedule (the learning rate will
+  # never decay). Remove the below line to train indefinitely.
+  num_steps: 200000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    ssd_random_crop {
+    }
+  }
+  max_number_of_boxes: 50
+  unpad_groundtruth_tensors: false
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/pet_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/pet_label_map.pbtxt"
+}
+
+eval_config: {
+  num_examples: 2000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/pet_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/pet_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}