Merge branch 'master' of https://github.com/tensorflow/models into context_tf2

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"
+  }
+}

research/object_detection/configs/tf2/ssd_efficientdet_d6_1408x1408_coco17_tpu-32.config

+ # SSD with EfficientNet-b6 + BiFPN feature extractor,
+# shared box predictor and focal loss (a.k.a EfficientDet-d6).
+# 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-b6 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: 1408
+        max_dimension: 1408
+        pad_to_max_dimension: true
+        }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 384
+        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: 5
+        kernel_size: 3
+        use_depthwise: true
+      }
+    }
+    feature_extractor {
+      type: 'ssd_efficientnet-b6_bifpn_keras'
+      bifpn {
+        min_level: 3
+        max_level: 7
+        num_iterations: 8
+        num_filters: 384
+        # Use unweighted sum for stability.
+        combine_method: 'sum'
+      }
+      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: 1408
+      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_d7_1536x1536_coco17_tpu-32.config

+ # SSD with EfficientNet-b6 + BiFPN feature extractor,
+# shared box predictor and focal loss (a.k.a EfficientDet-d7).
+# 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-b6 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: 1536
+        max_dimension: 1536
+        pad_to_max_dimension: true
+        }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 384
+        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: 5
+        kernel_size: 3
+        use_depthwise: true
+      }
+    }
+    feature_extractor {
+      type: 'ssd_efficientnet-b6_bifpn_keras'
+      bifpn {
+        min_level: 3
+        max_level: 7
+        num_iterations: 8
+        num_filters: 384
+        # Use unweighted sum for stability.
+        combine_method: 'sum'
+      }
+      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: 1536
+      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_BEE_CONFIGURED/val2017-?????-of-00032.tfrecord"
+  }
+}

research/object_detection/configs/tf2/ssd_mobilenet_v1_fpn_640x640_coco17_tpu-8.config

+# SSD with Mobilenet v1 FPN feature extractor, shared box predictor and focal
+# loss (a.k.a Retinanet).
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from Imagenet classification checkpoint
+# Train on TPU-8
+#
+# Achieves 29.1 mAP on COCO17 Val
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    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
+        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: 2
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 640
+        width: 640
+      }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 256
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true,
+            decay: 0.997,
+            epsilon: 0.001,
+          }
+        }
+        num_layers_before_predictor: 4
+        kernel_size: 3
+      }
+    }
+    feature_extractor {
+      type: 'ssd_mobilenet_v1_fpn_keras'
+      fpn {
+        min_level: 3
+        max_level: 7
+      }
+      min_depth: 16
+      depth_multiplier: 1.0
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          random_normal_initializer {
+            stddev: 0.01
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.997,
+          epsilon: 0.001,
+        }
+      }
+      override_base_feature_extractor_hyperparams: true
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 2.0
+        }
+      }
+      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: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/mobilenet_v1.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  num_steps: 25000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_crop_image {
+      min_object_covered: 0.0
+      min_aspect_ratio: 0.75
+      max_aspect_ratio: 3.0
+      min_area: 0.75
+      max_area: 1.0
+      overlap_thresh: 0.0
+    }
+  }
+  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
+  }
+  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_mobilenet_v2_320x320_coco17_tpu-8.config

+# SSD with Mobilenet v2
+# Trained on COCO17, initialized from Imagenet classification checkpoint
+# Train on TPU-8
+#
+# Achieves 22.2 mAP on COCO17 Val
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    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
+        use_matmul_gather: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    encode_background_as_zeros: true
+    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
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            train: true,
+            scale: true,
+            center: true,
+            decay: 0.97,
+            epsilon: 0.001,
+          }
+        }
+      }
+    }
+    feature_extractor {
+      type: 'ssd_mobilenet_v2_keras'
+      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: 0.97,
+          epsilon: 0.001,
+        }
+      }
+      override_base_feature_extractor_hyperparams: true
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.75,
+          gamma: 2.0
+        }
+      }
+      localization_loss {
+        weighted_smooth_l1 {
+          delta: 1.0
+        }
+      }
+      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: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/mobilenet_v2.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 512
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  num_steps: 50000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    ssd_random_crop {
+    }
+  }
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: .8
+          total_steps: 50000
+          warmup_learning_rate: 0.13333
+          warmup_steps: 2000
+        }
+      }
+      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
+}
+
+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_mobilenet_v2_fpnlite_320x320_coco17_tpu-8.config

+# SSD with Mobilenet v2 FPN-lite (go/fpn-lite) feature extractor, shared box
+# predictor and focal loss (a mobile version of Retinanet).
+# Retinanet: see Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from Imagenet classification checkpoint
+# Train on TPU-8
+#
+# Achieves 22.2 mAP on COCO17 Val
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    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
+        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: 2
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 320
+        width: 320
+      }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 128
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true,
+            decay: 0.997,
+            epsilon: 0.001,
+          }
+        }
+        num_layers_before_predictor: 4
+        share_prediction_tower: true
+        use_depthwise: true
+        kernel_size: 3
+      }
+    }
+    feature_extractor {
+      type: 'ssd_mobilenet_v2_fpn_keras'
+      use_depthwise: true
+      fpn {
+        min_level: 3
+        max_level: 7
+        additional_layer_depth: 128
+      }
+      min_depth: 16
+      depth_multiplier: 1.0
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          random_normal_initializer {
+            stddev: 0.01
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.997,
+          epsilon: 0.001,
+        }
+      }
+      override_base_feature_extractor_hyperparams: true
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 2.0
+        }
+      }
+      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: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/mobilenet_v2.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 128
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  num_steps: 50000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_crop_image {
+      min_object_covered: 0.0
+      min_aspect_ratio: 0.75
+      max_aspect_ratio: 3.0
+      min_area: 0.75
+      max_area: 1.0
+      overlap_thresh: 0.0
+    }
+  }
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: .08
+          total_steps: 50000
+          warmup_learning_rate: .026666
+          warmup_steps: 1000
+        }
+      }
+      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
+}
+
+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_mobilenet_v2_fpnlite_640x640_coco17_tpu-8.config

+# SSD with Mobilenet v2 FPN-lite (go/fpn-lite) feature extractor, shared box
+# predictor and focal loss (a mobile version of Retinanet).
+# Retinanet: see Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from Imagenet classification checkpoint
+# Train on TPU-8
+#
+# Achieves 28.2 mAP on COCO17 Val
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    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
+        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: 2
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 640
+        width: 640
+      }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 128
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true,
+            decay: 0.997,
+            epsilon: 0.001,
+          }
+        }
+        num_layers_before_predictor: 4
+        share_prediction_tower: true
+        use_depthwise: true
+        kernel_size: 3
+      }
+    }
+    feature_extractor {
+      type: 'ssd_mobilenet_v2_fpn_keras'
+      use_depthwise: true
+      fpn {
+        min_level: 3
+        max_level: 7
+        additional_layer_depth: 128
+      }
+      min_depth: 16
+      depth_multiplier: 1.0
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          random_normal_initializer {
+            stddev: 0.01
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.997,
+          epsilon: 0.001,
+        }
+      }
+      override_base_feature_extractor_hyperparams: true
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 2.0
+        }
+      }
+      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: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/mobilenet_v2.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 128
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  num_steps: 50000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_crop_image {
+      min_object_covered: 0.0
+      min_aspect_ratio: 0.75
+      max_aspect_ratio: 3.0
+      min_area: 0.75
+      max_area: 1.0
+      overlap_thresh: 0.0
+    }
+  }
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: .08
+          total_steps: 50000
+          warmup_learning_rate: .026666
+          warmup_steps: 1000
+        }
+      }
+      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
+}
+
+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_resnet101_v1_fpn_1024x1024_coco17_tpu-8.config

+# SSD with Resnet 101 v1 FPN feature extractor, shared box predictor and focal
+# loss (a.k.a Retinanet).
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from Imagenet classification checkpoint
+# Train on TPU-8
+#
+# Achieves 39.5 mAP on COCO17 Val
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    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
+        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: 2
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 1024
+        width: 1024
+      }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 256
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.0004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true,
+            decay: 0.997,
+            epsilon: 0.001,
+          }
+        }
+        num_layers_before_predictor: 4
+        kernel_size: 3
+      }
+    }
+    feature_extractor {
+      type: 'ssd_resnet101_v1_fpn_keras'
+      fpn {
+        min_level: 3
+        max_level: 7
+      }
+      min_depth: 16
+      depth_multiplier: 1.0
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.0004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.997,
+          epsilon: 0.001,
+        }
+      }
+      override_base_feature_extractor_hyperparams: true
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 2.0
+        }
+      }
+      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: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet101.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  use_bfloat16: true
+  num_steps: 100000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_crop_image {
+      min_object_covered: 0.0
+      min_aspect_ratio: 0.75
+      max_aspect_ratio: 3.0
+      min_area: 0.75
+      max_area: 1.0
+      overlap_thresh: 0.0
+    }
+  }
+  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
+  }
+  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
+}
+
+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_resnet101_v1_fpn_640x640_coco17_tpu-8.config

+# SSD with Resnet 101 v1 FPN feature extractor, shared box predictor and focal
+# loss (a.k.a Retinanet).
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from Imagenet classification checkpoint
+# Train on TPU-8
+#
+# Achieves 35.4 mAP on COCO17 Val
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    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
+        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: 2
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 640
+        width: 640
+      }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 256
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.0004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true,
+            decay: 0.997,
+            epsilon: 0.001,
+          }
+        }
+        num_layers_before_predictor: 4
+        kernel_size: 3
+      }
+    }
+    feature_extractor {
+      type: 'ssd_resnet101_v1_fpn_keras'
+      fpn {
+        min_level: 3
+        max_level: 7
+      }
+      min_depth: 16
+      depth_multiplier: 1.0
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.0004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.997,
+          epsilon: 0.001,
+        }
+      }
+      override_base_feature_extractor_hyperparams: true
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 2.0
+        }
+      }
+      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: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet101.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  use_bfloat16: true
+  num_steps: 25000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_crop_image {
+      min_object_covered: 0.0
+      min_aspect_ratio: 0.75
+      max_aspect_ratio: 3.0
+      min_area: 0.75
+      max_area: 1.0
+      overlap_thresh: 0.0
+    }
+  }
+  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
+  }
+  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
+}
+
+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_resnet152_v1_fpn_1024x1024_coco17_tpu-8.config

+# SSD with Resnet 152 v1 FPN feature extractor, shared box predictor and focal
+# loss (a.k.a Retinanet).
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from Imagenet classification checkpoint
+# Train on TPU-8
+#
+# Achieves 39.6 mAP on COCO17 Val
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    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
+        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: 2
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 1024
+        width: 1024
+      }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 256
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.0004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true,
+            decay: 0.997,
+            epsilon: 0.001,
+          }
+        }
+        num_layers_before_predictor: 4
+        kernel_size: 3
+      }
+    }
+    feature_extractor {
+      type: 'ssd_resnet152_v1_fpn_keras'
+      fpn {
+        min_level: 3
+        max_level: 7
+      }
+      min_depth: 16
+      depth_multiplier: 1.0
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.0004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.997,
+          epsilon: 0.001,
+        }
+      }
+      override_base_feature_extractor_hyperparams: true
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 2.0
+        }
+      }
+      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: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet152.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  use_bfloat16: true
+  num_steps: 100000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_crop_image {
+      min_object_covered: 0.0
+      min_aspect_ratio: 0.75
+      max_aspect_ratio: 3.0
+      min_area: 0.75
+      max_area: 1.0
+      overlap_thresh: 0.0
+    }
+  }
+  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
+  }
+  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
+}
+
+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_resnet152_v1_fpn_640x640_coco17_tpu-8.config

+# SSD with Resnet 152 v1 FPN feature extractor, shared box predictor and focal
+# loss (a.k.a Retinanet).
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from Imagenet classification checkpoint
+# Train on TPU-8
+#
+# Achieves 35.6 mAP on COCO17 Val
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    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
+        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: 2
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 640
+        width: 640
+      }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 256
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.0004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true,
+            decay: 0.997,
+            epsilon: 0.001,
+          }
+        }
+        num_layers_before_predictor: 4
+        kernel_size: 3
+      }
+    }
+    feature_extractor {
+      type: 'ssd_resnet152_v1_fpn_keras'
+      fpn {
+        min_level: 3
+        max_level: 7
+      }
+      min_depth: 16
+      depth_multiplier: 1.0
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.0004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.997,
+          epsilon: 0.001,
+        }
+      }
+      override_base_feature_extractor_hyperparams: true
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 2.0
+        }
+      }
+      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: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet152.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  use_bfloat16: true
+  num_steps: 25000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_crop_image {
+      min_object_covered: 0.0
+      min_aspect_ratio: 0.75
+      max_aspect_ratio: 3.0
+      min_area: 0.75
+      max_area: 1.0
+      overlap_thresh: 0.0
+    }
+  }
+  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
+  }
+  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
+}
+
+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_resnet50_v1_fpn_1024x1024_coco17_tpu-8.config

+# SSD with Resnet 50 v1 FPN feature extractor, shared box predictor and focal
+# loss (a.k.a Retinanet).
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from Imagenet classification checkpoint
+# Train on TPU-8
+#
+# Achieves 38.3 mAP on COCO17 Val
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    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
+        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: 2
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 1024
+        width: 1024
+      }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 256
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.0004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true,
+            decay: 0.997,
+            epsilon: 0.001,
+          }
+        }
+        num_layers_before_predictor: 4
+        kernel_size: 3
+      }
+    }
+    feature_extractor {
+      type: 'ssd_resnet50_v1_fpn_keras'
+      fpn {
+        min_level: 3
+        max_level: 7
+      }
+      min_depth: 16
+      depth_multiplier: 1.0
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.0004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.997,
+          epsilon: 0.001,
+        }
+      }
+      override_base_feature_extractor_hyperparams: true
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 2.0
+        }
+      }
+      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: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet50.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  use_bfloat16: true
+  num_steps: 100000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_crop_image {
+      min_object_covered: 0.0
+      min_aspect_ratio: 0.75
+      max_aspect_ratio: 3.0
+      min_area: 0.75
+      max_area: 1.0
+      overlap_thresh: 0.0
+    }
+  }
+  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
+  }
+  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
+}
+
+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_resnet50_v1_fpn_640x640_coco17_tpu-8.config

+# SSD with Resnet 50 v1 FPN feature extractor, shared box predictor and focal
+# loss (a.k.a Retinanet).
+# See Lin et al, https://arxiv.org/abs/1708.02002
+# Trained on COCO, initialized from Imagenet classification checkpoint
+# Train on TPU-8
+#
+# Achieves 34.3 mAP on COCO17 Val
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    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
+        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: 2
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 640
+        width: 640
+      }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        depth: 256
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.0004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.01
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            scale: true,
+            decay: 0.997,
+            epsilon: 0.001,
+          }
+        }
+        num_layers_before_predictor: 4
+        kernel_size: 3
+      }
+    }
+    feature_extractor {
+      type: 'ssd_resnet50_v1_fpn_keras'
+      fpn {
+        min_level: 3
+        max_level: 7
+      }
+      min_depth: 16
+      depth_multiplier: 1.0
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.0004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          scale: true,
+          decay: 0.997,
+          epsilon: 0.001,
+        }
+      }
+      override_base_feature_extractor_hyperparams: true
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.25
+          gamma: 2.0
+        }
+      }
+      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: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  fine_tune_checkpoint_version: V2
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/resnet50.ckpt-1"
+  fine_tune_checkpoint_type: "classification"
+  batch_size: 64
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 8
+  use_bfloat16: true
+  num_steps: 25000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_crop_image {
+      min_object_covered: 0.0
+      min_aspect_ratio: 0.75
+      max_aspect_ratio: 3.0
+      min_area: 0.75
+      max_area: 1.0
+      overlap_thresh: 0.0
+    }
+  }
+  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
+  }
+  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
+}
+
+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/core/box_predictor.py

@@ -134,7 +134,7 @@ class BoxPredictor(object):
     pass
 
 
-class KerasBoxPredictor(tf.keras.Model):
+class KerasBoxPredictor(tf.keras.layers.Layer):
   """Keras-based BoxPredictor."""
 
   def __init__(self, is_training, num_classes, freeze_batchnorm,

research/object_detection/core/densepose_ops.py

@@ -42,9 +42,6 @@ PART_NAMES = [
     b'left_face',
 ]
 
-_SRC_PATH = ('google3/third_party/tensorflow_models/object_detection/'
-             'dataset_tools/densepose')
-
 
 def scale(dp_surface_coords, y_scale, x_scale, scope=None):
   """Scales DensePose coordinates in y and x dimensions.
@@ -266,10 +263,14 @@ class DensePoseHorizontalFlip(object):
   def __init__(self):
     """Constructor."""
 
-    uv_symmetry_transforms_path = os.path.join(
-        tf.resource_loader.get_data_files_path(), '..', 'dataset_tools',
-        'densepose', 'UV_symmetry_transforms.mat')
-    data = scipy.io.loadmat(uv_symmetry_transforms_path)
+    path = os.path.dirname(os.path.abspath(__file__))
+    uv_symmetry_transforms_path = tf.resource_loader.get_path_to_datafile(
+        os.path.join(path, '..', 'dataset_tools', 'densepose',
+                     'UV_symmetry_transforms.mat'))
+    tf.logging.info('Loading DensePose symmetry transforms file from {}'.format(
+        uv_symmetry_transforms_path))
+    with tf.io.gfile.GFile(uv_symmetry_transforms_path, 'rb') as f:
+      data = scipy.io.loadmat(f)
 
     # Create lookup maps which indicate how a VU coordinate changes after a
     # horizontal flip.