tensorflow/models

# Quantized trained SSD with Mobilenet v2 on Open Images v4.
# Non-face boxes are dropped during training and non-face groundtruth boxes are
# ignored when evaluating.
#
# Users should configure the fine_tune_checkpoint field in the train config as
# well as the label_map_path and input_path fields in the train_input_reader and
# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
# should be configured.

model {
  ssd {
    num_classes: 1
    image_resizer {
      fixed_shape_resizer {
        height: 320
        width: 320
      }
    }
    feature_extractor {
      type: "ssd_mobilenet_v2"
      depth_multiplier: 1.0
      min_depth: 16
      conv_hyperparams {
        regularizer {
          l2_regularizer {
            weight: 4.0e-05
          }
        }
        initializer {
          truncated_normal_initializer {
            mean: 0.0
            stddev: 0.03
          }
        }
        activation: RELU_6
        batch_norm {
          decay: 0.9997
          center: true
          scale: true
          epsilon: 0.001
          train: true
        }
      }
      pad_to_multiple: 32
      use_explicit_padding: true
    }
    box_coder {
      faster_rcnn_box_coder {
        y_scale: 10.0
        x_scale: 10.0
        height_scale: 5.0
        width_scale: 5.0
      }
    }
    matcher {
      argmax_matcher {
        matched_threshold: 0.5
        unmatched_threshold: 0.5
        ignore_thresholds: false
        negatives_lower_than_unmatched: true
        force_match_for_each_row: true
      }
    }
    similarity_calculator {
      iou_similarity {
      }
    }
    box_predictor {
      convolutional_box_predictor {
        conv_hyperparams {
          regularizer {
            l2_regularizer {
              weight: 4.0e-05
            }
          }
          initializer {
            truncated_normal_initializer {
              mean: 0.0
              stddev: 0.03
            }
          }
          activation: RELU_6
          batch_norm {
            decay: 0.9997
            center: true
            scale: true
            epsilon: 0.001
            train: true
          }
        }
        min_depth: 0
        max_depth: 0
        num_layers_before_predictor: 0
        use_dropout: false
        kernel_size: 3
        box_code_size: 4
        apply_sigmoid_to_scores: false
      }
    }
    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
        height_stride: 16
        height_stride: 32
        height_stride: 64
        height_stride: 128
        height_stride: 256
        height_stride: 512
        width_stride: 16
        width_stride: 32
        width_stride: 64
        width_stride: 128
        width_stride: 256
        width_stride: 512
      }
    }
    post_processing {
      batch_non_max_suppression {
        score_threshold: 1.0e-08
        iou_threshold: 0.5
        max_detections_per_class: 100
        max_total_detections: 100
      }
      score_converter: SIGMOID
    }
    normalize_loss_by_num_matches: true
    loss {
      localization_loss {
        weighted_smooth_l1 {
        }
      }
      classification_loss {
        weighted_sigmoid {
        }
      }
      hard_example_miner {
        num_hard_examples: 3000
        iou_threshold: 0.99
        loss_type: CLASSIFICATION
        max_negatives_per_positive: 3
        min_negatives_per_image: 10
      }
      classification_weight: 1.0
      localization_weight: 1.0
    }
  }
}
train_config {
  batch_size: 32
  data_augmentation_options {
    random_horizontal_flip {
      keypoint_flip_permutation: 1
      keypoint_flip_permutation: 0
      keypoint_flip_permutation: 2
      keypoint_flip_permutation: 3
      keypoint_flip_permutation: 5
      keypoint_flip_permutation: 4
    }
  }
  data_augmentation_options {
    ssd_random_crop_fixed_aspect_ratio {
    }
  }
  optimizer {
    rms_prop_optimizer {
      learning_rate {
        exponential_decay_learning_rate {
          initial_learning_rate: 0.004
          decay_steps: 800720
          decay_factor: 0.95
        }
      }
      momentum_optimizer_value: 0.9
      decay: 0.9
      epsilon: 1.0
    }
  }
  fine_tune_checkpoint: ""
}
train_input_reader {
  label_map_path: "PATH_TO_BE_CONFIGURED/face_label_map.pbtxt"
  tf_record_input_reader {
    input_path: "PATH_TO_BE_CONFIGURED/face_train.record-?????-of-00100"
  }
}
eval_config {
  metrics_set: "coco_detection_metrics"
  use_moving_averages: true
}
eval_input_reader {
  label_map_path: "PATH_TO_BE_CONFIGURED/face_label_map.pbtxt"
  shuffle: false
  num_readers: 1
  tf_record_input_reader {
    input_path: "PATH_TO_BE_CONFIGURED/face_val.record-?????-of-00010"
  }
}
graph_rewriter {
  quantization {
    delay: 500000
    weight_bits: 8
    activation_bits: 8
  }
}