Merged commit includes the following changes: (#8830)

320622111  by rathodv:

    Internal Change.

--

PiperOrigin-RevId: 320622111
Co-authored-by: TF Object Detection Team <no-reply@google.com>

research/object_detection/configs/tf2/center_net_hourglass104_1024x1024_coco17_tpu-32.config

+# CenterNet meta-architecture from the "Objects as Points" [2] paper with the
+# hourglass[1] backbone.
+# [1]: https://arxiv.org/abs/1603.06937
+# [2]: https://arxiv.org/abs/1904.07850
+# Trained on COCO, initialized from Extremenet Detection checkpoint
+# Train on TPU-32 v3
+#
+# Achieves 44.6 mAP on COCO17 Val
+
+
+model {
+  center_net {
+    num_classes: 90
+    feature_extractor {
+      type: "hourglass_104"
+      bgr_ordering: true
+      channel_means: [104.01362025, 114.03422265, 119.9165958 ]
+      channel_stds: [73.6027665 , 69.89082075, 70.9150767 ]
+    }
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 1024
+        max_dimension: 1024
+        pad_to_max_dimension: true
+      }
+    }
+    object_detection_task {
+      task_loss_weight: 1.0
+      offset_loss_weight: 1.0
+      scale_loss_weight: 0.1
+      localization_loss {
+        l1_localization_loss {
+        }
+      }
+    }
+    object_center_params {
+      object_center_loss_weight: 1.0
+      min_box_overlap_iou: 0.7
+      max_box_predictions: 100
+      classification_loss {
+        penalty_reduced_logistic_focal_loss {
+          alpha: 2.0
+          beta: 4.0
+        }
+      }
+    }
+  }
+}
+
+train_config: {
+
+  batch_size: 128
+  num_steps: 50000
+
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_hue {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_contrast {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_saturation {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_brightness {
+    }
+  }
+
+   data_augmentation_options {
+     random_square_crop_by_scale {
+      scale_min: 0.6
+      scale_max: 1.3
+    }
+  }
+
+  optimizer {
+    adam_optimizer: {
+      epsilon: 1e-7  # Match tf.keras.optimizers.Adam's default.
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 1e-3
+          total_steps: 50000
+          warmup_learning_rate: 2.5e-4
+          warmup_steps: 5000
+        }
+      }
+    }
+    use_moving_average: false
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/ckpt-1"
+  fine_tune_checkpoint_type: "detection"
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/center_net_hourglass104_512x512_coco17_tpu-8.config

+# CenterNet meta-architecture from the "Objects as Points" [2] paper with the
+# hourglass[1] backbone.
+# [1]: https://arxiv.org/abs/1603.06937
+# [2]: https://arxiv.org/abs/1904.07850
+# Trained on COCO, initialized from Extremenet Detection checkpoint
+# Train on TPU-8
+#
+# Achieves 41.9 mAP on COCO17 Val
+
+model {
+  center_net {
+    num_classes: 90
+    feature_extractor {
+      type: "hourglass_104"
+      bgr_ordering: true
+      channel_means: [104.01362025, 114.03422265, 119.9165958 ]
+      channel_stds: [73.6027665 , 69.89082075, 70.9150767 ]
+    }
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 512
+        max_dimension: 512
+        pad_to_max_dimension: true
+      }
+    }
+    object_detection_task {
+      task_loss_weight: 1.0
+      offset_loss_weight: 1.0
+      scale_loss_weight: 0.1
+      localization_loss {
+        l1_localization_loss {
+        }
+      }
+    }
+    object_center_params {
+      object_center_loss_weight: 1.0
+      min_box_overlap_iou: 0.7
+      max_box_predictions: 100
+      classification_loss {
+        penalty_reduced_logistic_focal_loss {
+          alpha: 2.0
+          beta: 4.0
+        }
+      }
+    }
+  }
+}
+
+train_config: {
+
+  batch_size: 128
+  num_steps: 140000
+
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+
+  data_augmentation_options {
+    random_crop_image {
+      min_aspect_ratio: 0.5
+      max_aspect_ratio: 1.7
+      random_coef: 0.25
+    }
+  }
+
+
+  data_augmentation_options {
+    random_adjust_hue {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_contrast {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_saturation {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_brightness {
+    }
+  }
+
+  data_augmentation_options {
+    random_absolute_pad_image {
+       max_height_padding: 200
+       max_width_padding: 200
+       pad_color: [0, 0, 0]
+    }
+  }
+
+  optimizer {
+    adam_optimizer: {
+      epsilon: 1e-7  # Match tf.keras.optimizers.Adam's default.
+      learning_rate: {
+        manual_step_learning_rate {
+          initial_learning_rate: 1e-3
+          schedule {
+           step: 90000
+           learning_rate: 1e-4
+          }
+          schedule {
+            step: 120000
+            learning_rate: 1e-5
+          }
+        }
+      }
+    }
+    use_moving_average: false
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/ckpt-1"
+  fine_tune_checkpoint_type: "detection"
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/center_net_resnet101_v1_fpn_512x512_coco17_tpu-8.config

+# CenterNet meta-architecture from the "Objects as Points" [1] paper
+# with the ResNet-v1-101 FPN backbone.
+# [1]: https://arxiv.org/abs/1904.07850
+
+# Train on TPU-8
+#
+# Achieves 34.18 mAP on COCO17 Val
+
+
+model {
+  center_net {
+    num_classes: 90
+    feature_extractor {
+      type: "resnet_v2_101"
+    }
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 512
+        max_dimension: 512
+        pad_to_max_dimension: true
+      }
+    }
+    object_detection_task {
+      task_loss_weight: 1.0
+      offset_loss_weight: 1.0
+      scale_loss_weight: 0.1
+      localization_loss {
+        l1_localization_loss {
+        }
+      }
+    }
+    object_center_params {
+      object_center_loss_weight: 1.0
+      min_box_overlap_iou: 0.7
+      max_box_predictions: 100
+      classification_loss {
+        penalty_reduced_logistic_focal_loss {
+          alpha: 2.0
+          beta: 4.0
+        }
+      }
+    }
+  }
+}
+
+train_config: {
+
+  batch_size: 128
+  num_steps: 140000
+
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+
+  data_augmentation_options {
+    random_crop_image {
+      min_aspect_ratio: 0.5
+      max_aspect_ratio: 1.7
+      random_coef: 0.25
+    }
+  }
+
+
+  data_augmentation_options {
+    random_adjust_hue {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_contrast {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_saturation {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_brightness {
+    }
+  }
+
+  data_augmentation_options {
+    random_absolute_pad_image {
+       max_height_padding: 200
+       max_width_padding: 200
+       pad_color: [0, 0, 0]
+    }
+  }
+
+  optimizer {
+    adam_optimizer: {
+      epsilon: 1e-7  # Match tf.keras.optimizers.Adam's default.
+      learning_rate: {
+        manual_step_learning_rate {
+          initial_learning_rate: 1e-3
+          schedule {
+           step: 90000
+           learning_rate: 1e-4
+          }
+          schedule {
+            step: 120000
+            learning_rate: 1e-5
+          }
+        }
+      }
+    }
+    use_moving_average: false
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/weights-1"
+  fine_tune_checkpoint_type: "classification"
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}
+

research/object_detection/configs/tf2/faster_rcnn_resnet101_v1_1024x1024_coco17_tpu-8.config

+# Faster R-CNN with Resnet-101 (v1),
+# w/high res inputs, long training schedule
+# Trained on COCO, initialized from Imagenet classification checkpoint
+#
+# Train on TPU-8
+#
+# Achieves 37.1 mAP on COCO17 val
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      fixed_shape_resizer {
+        width: 1024
+        height: 1024
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_resnet101_keras'
+      batch_norm_trainable: true
+    }
+    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
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+        share_box_across_classes: true
+      }
+    }
+    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
+    use_static_shapes: true
+    use_matmul_crop_and_resize: true
+    clip_anchors_to_image: true
+    use_static_balanced_label_sampler: true
+    use_matmul_gather_in_matcher: true
+  }
+}
+
+train_config: {
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  num_steps: 100000
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: .04
+          total_steps: 100000
+          warmup_learning_rate: .013333
+          warmup_steps: 2000
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet101.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_hue {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_contrast {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_saturation {
+    }
+  }
+
+  data_augmentation_options {
+     random_square_crop_by_scale {
+      scale_min: 0.6
+      scale_max: 1.3
+    }
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+  use_bfloat16: true  # works only on TPUs
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/faster_rcnn_resnet101_v1_640x640_coco17_tpu-8.config

+# Faster R-CNN with Resnet-50 (v1)
+# Trained on COCO, initialized from Imagenet classification checkpoint
+#
+# Train on TPU-8
+#
+# Achieves 31.8 mAP on COCO17 val
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 640
+        max_dimension: 640
+        pad_to_max_dimension: true
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_resnet101_keras'
+      batch_norm_trainable: true
+    }
+    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
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+        share_box_across_classes: true
+      }
+    }
+    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
+    use_static_shapes: true
+    use_matmul_crop_and_resize: true
+    clip_anchors_to_image: true
+    use_static_balanced_label_sampler: true
+    use_matmul_gather_in_matcher: true
+  }
+}
+
+train_config: {
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  num_steps: 25000
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: .04
+          total_steps: 25000
+          warmup_learning_rate: .013333
+          warmup_steps: 2000
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet101.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+  use_bfloat16: true  # works only on TPUs
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/faster_rcnn_resnet101_v1_800x1333_coco17_gpu-8.config

+# Faster R-CNN with Resnet-101 (v1),
+# Initialized from Imagenet classification checkpoint
+#
+# Train on GPU-8
+#
+# Achieves 36.6 mAP on COCO17 val
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 800
+        max_dimension: 1333
+        pad_to_max_dimension: true
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_resnet101_keras'
+    }
+    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
+        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: 16
+  num_steps: 200000
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 0.01
+          total_steps: 200000
+          warmup_learning_rate: 0.0
+          warmup_steps: 5000
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet101.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_hue {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_contrast {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_saturation {
+    }
+  }
+
+  data_augmentation_options {
+     random_square_crop_by_scale {
+      scale_min: 0.6
+      scale_max: 1.3
+    }
+  }
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/faster_rcnn_resnet152_v1_1024x1024_coco17_tpu-8.config

+# Faster R-CNN with Resnet-152 (v1)
+# w/high res inputs, long training schedule
+# Trained on COCO, initialized from Imagenet classification checkpoint
+#
+# Train on TPU-8
+#
+# Achieves 37.6 mAP on COCO17 val
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      fixed_shape_resizer {
+        width: 1024
+        height: 1024
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_resnet152_keras'
+      batch_norm_trainable: true
+    }
+    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
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+        share_box_across_classes: true
+      }
+    }
+    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
+    use_static_shapes: true
+    use_matmul_crop_and_resize: true
+    clip_anchors_to_image: true
+    use_static_balanced_label_sampler: true
+    use_matmul_gather_in_matcher: true
+  }
+}
+
+train_config: {
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  num_steps: 100000
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: .04
+          total_steps: 100000
+          warmup_learning_rate: .013333
+          warmup_steps: 2000
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet152.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_hue {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_contrast {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_saturation {
+    }
+  }
+
+  data_augmentation_options {
+     random_square_crop_by_scale {
+      scale_min: 0.6
+      scale_max: 1.3
+    }
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+  use_bfloat16: true  # works only on TPUs
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/faster_rcnn_resnet152_v1_640x640_coco17_tpu-8.config

+# Faster R-CNN with Resnet-152 (v1)
+# Trained on COCO, initialized from Imagenet classification checkpoint
+#
+# Train on TPU-8
+#
+# Achieves 32.4 mAP on COCO17 val
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 640
+        max_dimension: 640
+        pad_to_max_dimension: true
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_resnet152_keras'
+      batch_norm_trainable: true
+    }
+    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
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+        share_box_across_classes: true
+      }
+    }
+    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
+    use_static_shapes: true
+    use_matmul_crop_and_resize: true
+    clip_anchors_to_image: true
+    use_static_balanced_label_sampler: true
+    use_matmul_gather_in_matcher: true
+  }
+}
+
+train_config: {
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  num_steps: 25000
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: .04
+          total_steps: 25000
+          warmup_learning_rate: .013333
+          warmup_steps: 2000
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet152.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+  use_bfloat16: true  # works only on TPUs
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/faster_rcnn_resnet152_v1_800x1333_coco17_gpu-8.config

+# Faster R-CNN with Resnet-152 (v1),
+# Initialized from Imagenet classification checkpoint
+#
+# Train on GPU-8
+#
+# Achieves 37.3 mAP on COCO17 val
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 800
+        max_dimension: 1333
+        pad_to_max_dimension: true
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_resnet152_keras'
+    }
+    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
+        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: 16
+  num_steps: 200000
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 0.01
+          total_steps: 200000
+          warmup_learning_rate: 0.0
+          warmup_steps: 5000
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet152.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_hue {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_contrast {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_saturation {
+    }
+  }
+
+  data_augmentation_options {
+     random_square_crop_by_scale {
+      scale_min: 0.6
+      scale_max: 1.3
+    }
+  }
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/faster_rcnn_resnet50_v1_1024x1024_coco17_tpu-8.config

+# Faster R-CNN with Resnet-50 (v1),
+# w/high res inputs, long training schedule
+# Trained on COCO, initialized from Imagenet classification checkpoint
+#
+# Train on TPU-8
+#
+# Achieves 31.0 mAP on COCO17 val
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      fixed_shape_resizer {
+        width: 1024
+        height: 1024
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_resnet50_keras'
+      batch_norm_trainable: true
+    }
+    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
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+        share_box_across_classes: true
+      }
+    }
+    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
+    use_static_shapes: true
+    use_matmul_crop_and_resize: true
+    clip_anchors_to_image: true
+    use_static_balanced_label_sampler: true
+    use_matmul_gather_in_matcher: true
+  }
+}
+
+train_config: {
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  num_steps: 100000
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: .04
+          total_steps: 100000
+          warmup_learning_rate: .013333
+          warmup_steps: 2000
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet50.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_hue {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_contrast {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_saturation {
+    }
+  }
+
+  data_augmentation_options {
+     random_square_crop_by_scale {
+      scale_min: 0.6
+      scale_max: 1.3
+    }
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+  use_bfloat16: true  # works only on TPUs
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/faster_rcnn_resnet50_v1_640x640_coco17_tpu-8.config

+# Faster R-CNN with Resnet-50 (v1) with 640x640 input resolution
+# Trained on COCO, initialized from Imagenet classification checkpoint
+#
+# Train on TPU-8
+#
+# Achieves 29.3 mAP on COCO17 Val
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 640
+        max_dimension: 640
+        pad_to_max_dimension: true
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_resnet50_keras'
+      batch_norm_trainable: true
+    }
+    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
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+        share_box_across_classes: true
+      }
+    }
+    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
+    use_static_shapes: true
+    use_matmul_crop_and_resize: true
+    clip_anchors_to_image: true
+    use_static_balanced_label_sampler: true
+    use_matmul_gather_in_matcher: true
+  }
+}
+
+train_config: {
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  num_steps: 25000
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: .04
+          total_steps: 25000
+          warmup_learning_rate: .013333
+          warmup_steps: 2000
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet50.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+  use_bfloat16: true  # works only on TPUs
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/faster_rcnn_resnet50_v1_800x1333_coco17_gpu-8.config

+# Faster R-CNN with Resnet-50 (v1),
+# Initialized from Imagenet classification checkpoint
+#
+# Train on GPU-8
+#
+# Achieves 31.4 mAP on COCO17 val
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 800
+        max_dimension: 1333
+        pad_to_max_dimension: true
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_resnet50_keras'
+    }
+    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
+        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: 16
+  num_steps: 200000
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 0.01
+          total_steps: 200000
+          warmup_learning_rate: 0.0
+          warmup_steps: 5000
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet50.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_hue {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_contrast {
+    }
+  }
+
+  data_augmentation_options {
+    random_adjust_saturation {
+    }
+  }
+
+  data_augmentation_options {
+     random_square_crop_by_scale {
+      scale_min: 0.6
+      scale_max: 1.3
+    }
+  }
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/mask_rcnn_inception_resnet_v2_1024x1024_coco17_gpu-8.config

+# Mask R-CNN with Inception Resnet v2 (no atrous)
+# Sync-trained on COCO (with 8 GPUs) with batch size 16 (1024x1024 resolution)
+# Initialized from Imagenet classification checkpoint
+#
+# Train on GPU-8
+#
+# Achieves 40.4 box mAP and 35.5 mask mAP on COCO17 val
+
+model {
+  faster_rcnn {
+    number_of_stages: 3
+    num_classes: 90
+    image_resizer {
+      fixed_shape_resizer {
+        height: 1024
+        width: 1024
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_inception_resnet_v2_keras'
+    }
+    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: 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
+            }
+          }
+        }
+        mask_height: 33
+        mask_width: 33
+        mask_prediction_conv_depth: 0
+        mask_prediction_num_conv_layers: 4
+        conv_hyperparams {
+          op: CONV
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            truncated_normal_initializer {
+              stddev: 0.01
+            }
+          }
+        }
+        predict_instance_masks: true
+      }
+    }
+    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
+    resize_masks: false
+  }
+}
+
+train_config: {
+  batch_size: 16
+  num_steps: 200000
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 0.008
+          total_steps: 200000
+          warmup_learning_rate: 0.0
+          warmup_steps: 5000
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/inception_resnet_v2.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+  load_instance_masks: true
+  mask_type: PNG_MASKS
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  metrics_set: "coco_mask_metrics"
+  eval_instance_masks: true
+  use_moving_averages: false
+  batch_size: 1
+  include_metrics_per_category: true
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+  load_instance_masks: true
+  mask_type: PNG_MASKS
+}

research/object_detection/configs/tf2/ssd_efficientdet_d0_512x512_coco17_tpu-8.config

+ # SSD with EfficientNet-b0 + BiFPN feature extractor,
+# shared box predictor and focal loss (a.k.a EfficientDet-d0).
+# See EfficientDet, Tan et al, https://arxiv.org/abs/1911.09070
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from an EfficientNet-b0 checkpoint.
+#
+# Train on TPU-8
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    num_classes: 90
+    add_background_class: false
+    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
+        use_matmul_gather: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    encode_background_as_zeros: true
+    anchor_generator {
+      multiscale_anchor_generator {
+        min_level: 3
+        max_level: 7
+        anchor_scale: 4.0
+        aspect_ratios: [1.0, 2.0, 0.5]
+        scales_per_octave: 3
+      }
+    }
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 512
+        max_dimension: 512
+        pad_to_max_dimension: true
+        }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 64
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          force_use_bias: true
+          activation: SWISH
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true
+            decay: 0.99
+            epsilon: 0.001
+          }
+        }
+        num_layers_before_predictor: 3
+        kernel_size: 3
+        use_depthwise: true
+      }
+    }
+    feature_extractor {
+      type: 'ssd_efficientnet-b0_bifpn_keras'
+      bifpn {
+        min_level: 3
+        max_level: 7
+        num_iterations: 3
+        num_filters: 64
+      }
+      conv_hyperparams {
+        force_use_bias: true
+        activation: SWISH
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.99,
+          epsilon: 0.001,
+        }
+      }
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 1.5
+        }
+      }
+      localization_loss {
+        weighted_smooth_l1 {
+        }
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    normalize_loss_by_num_matches: true
+    normalize_loc_loss_by_codesize: true
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 1e-8
+        iou_threshold: 0.5
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/ckpt-0"
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 128
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  use_bfloat16: true
+  num_steps: 300000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_scale_crop_and_pad_to_square {
+      output_size: 512
+      scale_min: 0.1
+      scale_max: 2.0
+    }
+  }
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 8e-2
+          total_steps: 300000
+          warmup_learning_rate: .001
+          warmup_steps: 2500
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/ssd_efficientdet_d1_640x640_coco17_tpu-8.config

+ # SSD with EfficientNet-b1 + BiFPN feature extractor,
+# shared box predictor and focal loss (a.k.a EfficientDet-d1).
+# See EfficientDet, Tan et al, https://arxiv.org/abs/1911.09070
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from an EfficientNet-b1 checkpoint.
+#
+# Train on TPU-8
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    num_classes: 90
+    add_background_class: false
+    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
+        use_matmul_gather: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    encode_background_as_zeros: true
+    anchor_generator {
+      multiscale_anchor_generator {
+        min_level: 3
+        max_level: 7
+        anchor_scale: 4.0
+        aspect_ratios: [1.0, 2.0, 0.5]
+        scales_per_octave: 3
+      }
+    }
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 640
+        max_dimension: 640
+        pad_to_max_dimension: true
+        }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 88
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          force_use_bias: true
+          activation: SWISH
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true
+            decay: 0.99
+            epsilon: 0.001
+          }
+        }
+        num_layers_before_predictor: 3
+        kernel_size: 3
+        use_depthwise: true
+      }
+    }
+    feature_extractor {
+      type: 'ssd_efficientnet-b1_bifpn_keras'
+      bifpn {
+        min_level: 3
+        max_level: 7
+        num_iterations: 4
+        num_filters: 88
+      }
+      conv_hyperparams {
+        force_use_bias: true
+        activation: SWISH
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.99,
+          epsilon: 0.001,
+        }
+      }
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 1.5
+        }
+      }
+      localization_loss {
+        weighted_smooth_l1 {
+        }
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    normalize_loss_by_num_matches: true
+    normalize_loc_loss_by_codesize: true
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 1e-8
+        iou_threshold: 0.5
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/ckpt-0"
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 128
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  use_bfloat16: true
+  num_steps: 300000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_scale_crop_and_pad_to_square {
+      output_size: 640
+      scale_min: 0.1
+      scale_max: 2.0
+    }
+  }
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 8e-2
+          total_steps: 300000
+          warmup_learning_rate: .001
+          warmup_steps: 2500
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/ssd_efficientdet_d2_768x768_coco17_tpu-8.config

+ # SSD with EfficientNet-b2 + BiFPN feature extractor,
+# shared box predictor and focal loss (a.k.a EfficientDet-d2).
+# See EfficientDet, Tan et al, https://arxiv.org/abs/1911.09070
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from an EfficientNet-b2 checkpoint.
+#
+# Train on TPU-8
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    num_classes: 90
+    add_background_class: false
+    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
+        use_matmul_gather: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    encode_background_as_zeros: true
+    anchor_generator {
+      multiscale_anchor_generator {
+        min_level: 3
+        max_level: 7
+        anchor_scale: 4.0
+        aspect_ratios: [1.0, 2.0, 0.5]
+        scales_per_octave: 3
+      }
+    }
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 768
+        max_dimension: 768
+        pad_to_max_dimension: true
+        }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 112
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          force_use_bias: true
+          activation: SWISH
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true
+            decay: 0.99
+            epsilon: 0.001
+          }
+        }
+        num_layers_before_predictor: 3
+        kernel_size: 3
+        use_depthwise: true
+      }
+    }
+    feature_extractor {
+      type: 'ssd_efficientnet-b2_bifpn_keras'
+      bifpn {
+        min_level: 3
+        max_level: 7
+        num_iterations: 5
+        num_filters: 112
+      }
+      conv_hyperparams {
+        force_use_bias: true
+        activation: SWISH
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.99,
+          epsilon: 0.001,
+        }
+      }
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 1.5
+        }
+      }
+      localization_loss {
+        weighted_smooth_l1 {
+        }
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    normalize_loss_by_num_matches: true
+    normalize_loc_loss_by_codesize: true
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 1e-8
+        iou_threshold: 0.5
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/ckpt-0"
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 128
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  use_bfloat16: true
+  num_steps: 300000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_scale_crop_and_pad_to_square {
+      output_size: 768
+      scale_min: 0.1
+      scale_max: 2.0
+    }
+  }
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 8e-2
+          total_steps: 300000
+          warmup_learning_rate: .001
+          warmup_steps: 2500
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/ssd_efficientdet_d3_896x896_coco17_tpu-32.config

+ # SSD with EfficientNet-b3 + BiFPN feature extractor,
+# shared box predictor and focal loss (a.k.a EfficientDet-d3).
+# See EfficientDet, Tan et al, https://arxiv.org/abs/1911.09070
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from an EfficientNet-b3 checkpoint.
+#
+# Train on TPU-32
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    num_classes: 90
+    add_background_class: false
+    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
+        use_matmul_gather: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    encode_background_as_zeros: true
+    anchor_generator {
+      multiscale_anchor_generator {
+        min_level: 3
+        max_level: 7
+        anchor_scale: 4.0
+        aspect_ratios: [1.0, 2.0, 0.5]
+        scales_per_octave: 3
+      }
+    }
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 896
+        max_dimension: 896
+        pad_to_max_dimension: true
+        }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 160
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          force_use_bias: true
+          activation: SWISH
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true
+            decay: 0.99
+            epsilon: 0.001
+          }
+        }
+        num_layers_before_predictor: 4
+        kernel_size: 3
+        use_depthwise: true
+      }
+    }
+    feature_extractor {
+      type: 'ssd_efficientnet-b3_bifpn_keras'
+      bifpn {
+        min_level: 3
+        max_level: 7
+        num_iterations: 6
+        num_filters: 160
+      }
+      conv_hyperparams {
+        force_use_bias: true
+        activation: SWISH
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.99,
+          epsilon: 0.001,
+        }
+      }
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 1.5
+        }
+      }
+      localization_loss {
+        weighted_smooth_l1 {
+        }
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    normalize_loss_by_num_matches: true
+    normalize_loc_loss_by_codesize: true
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 1e-8
+        iou_threshold: 0.5
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/ckpt-0"
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 128
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  use_bfloat16: true
+  num_steps: 300000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_scale_crop_and_pad_to_square {
+      output_size: 896
+      scale_min: 0.1
+      scale_max: 2.0
+    }
+  }
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 8e-2
+          total_steps: 300000
+          warmup_learning_rate: .001
+          warmup_steps: 2500
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/ssd_efficientdet_d4_1024x1024_coco17_tpu-32.config

+ # SSD with EfficientNet-b4 + BiFPN feature extractor,
+# shared box predictor and focal loss (a.k.a EfficientDet-d4).
+# See EfficientDet, Tan et al, https://arxiv.org/abs/1911.09070
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from an EfficientNet-b4 checkpoint.
+#
+# Train on TPU-32
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    num_classes: 90
+    add_background_class: false
+    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
+        use_matmul_gather: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    encode_background_as_zeros: true
+    anchor_generator {
+      multiscale_anchor_generator {
+        min_level: 3
+        max_level: 7
+        anchor_scale: 4.0
+        aspect_ratios: [1.0, 2.0, 0.5]
+        scales_per_octave: 3
+      }
+    }
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 1024
+        max_dimension: 1024
+        pad_to_max_dimension: true
+        }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 224
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          force_use_bias: true
+          activation: SWISH
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true
+            decay: 0.99
+            epsilon: 0.001
+          }
+        }
+        num_layers_before_predictor: 4
+        kernel_size: 3
+        use_depthwise: true
+      }
+    }
+    feature_extractor {
+      type: 'ssd_efficientnet-b4_bifpn_keras'
+      bifpn {
+        min_level: 3
+        max_level: 7
+        num_iterations: 7
+        num_filters: 224
+      }
+      conv_hyperparams {
+        force_use_bias: true
+        activation: SWISH
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.99,
+          epsilon: 0.001,
+        }
+      }
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 1.5
+        }
+      }
+      localization_loss {
+        weighted_smooth_l1 {
+        }
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    normalize_loss_by_num_matches: true
+    normalize_loc_loss_by_codesize: true
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 1e-8
+        iou_threshold: 0.5
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/ckpt-0"
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 128
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  use_bfloat16: true
+  num_steps: 300000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_scale_crop_and_pad_to_square {
+      output_size: 1024
+      scale_min: 0.1
+      scale_max: 2.0
+    }
+  }
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 8e-2
+          total_steps: 300000
+          warmup_learning_rate: .001
+          warmup_steps: 2500
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/ssd_efficientdet_d5_1280x1280_coco17_tpu-32.config

+ # SSD with EfficientNet-b5 + BiFPN feature extractor,
+# shared box predictor and focal loss (a.k.a EfficientDet-d5).
+# See EfficientDet, Tan et al, https://arxiv.org/abs/1911.09070
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from an EfficientNet-b5 checkpoint.
+#
+# Train on TPU-32
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    num_classes: 90
+    add_background_class: false
+    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
+        use_matmul_gather: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    encode_background_as_zeros: true
+    anchor_generator {
+      multiscale_anchor_generator {
+        min_level: 3
+        max_level: 7
+        anchor_scale: 4.0
+        aspect_ratios: [1.0, 2.0, 0.5]
+        scales_per_octave: 3
+      }
+    }
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 1280
+        max_dimension: 1280
+        pad_to_max_dimension: true
+        }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 288
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          force_use_bias: true
+          activation: SWISH
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true
+            decay: 0.99
+            epsilon: 0.001
+          }
+        }
+        num_layers_before_predictor: 4
+        kernel_size: 3
+        use_depthwise: true
+      }
+    }
+    feature_extractor {
+      type: 'ssd_efficientnet-b5_bifpn_keras'
+      bifpn {
+        min_level: 3
+        max_level: 7
+        num_iterations: 7
+        num_filters: 288
+      }
+      conv_hyperparams {
+        force_use_bias: true
+        activation: SWISH
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.99,
+          epsilon: 0.001,
+        }
+      }
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 1.5
+        }
+      }
+      localization_loss {
+        weighted_smooth_l1 {
+        }
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    normalize_loss_by_num_matches: true
+    normalize_loc_loss_by_codesize: true
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 1e-8
+        iou_threshold: 0.5
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/ckpt-0"
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 128
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  use_bfloat16: true
+  num_steps: 300000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_scale_crop_and_pad_to_square {
+      output_size: 1280
+      scale_min: 0.1
+      scale_max: 2.0
+    }
+  }
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 8e-2
+          total_steps: 300000
+          warmup_learning_rate: .001
+          warmup_steps: 2500
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+}
+
+train_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/train2017-?????-of-00256.tfrecord"
+  }
+}
+
+eval_config: {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+  batch_size: 1;
+}
+
+eval_input_reader: {
+  label_map_path: "PATH_TO_BE_CONFIGURED/label_map.txt"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}