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/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/g3doc/challenge_evaluation.md

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

research/object_detection/g3doc/configuring_jobs.md

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

research/object_detection/g3doc/context_rcnn.md

 # Context R-CNN
 
+[![TensorFlow 1.15](https://img.shields.io/badge/TensorFlow-1.15-FF6F00?logo=tensorflow)](https://github.com/tensorflow/tensorflow/releases/tag/v1.15.0)
+
 Context R-CNN is an object detection model that uses contextual features to
 improve object detection. See https://arxiv.org/abs/1912.03538 for more details.
 

research/object_detection/g3doc/defining_your_own_model.md

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

research/object_detection/g3doc/evaluation_protocols.md

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

research/object_detection/g3doc/exporting_models.md

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

research/object_detection/g3doc/faq.md

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