context_rcnn_camera_trap.config

# Context R-CNN unit test configuration using sequence example sample data with
# context_features created from the Snapshot Serengeti Dataset and stored in
# snapshot_serengeti_sequence_examples.record.
# This model uses attention into contextual features within the Faster R-CNN
# object detection framework to improve object detection performance.
# See https://arxiv.org/abs/1912.03538 for more information.

model {
  faster_rcnn {
    num_classes: 48
    image_resizer {
      fixed_shape_resizer {
        height: 640
        width: 640
      }
    }
    feature_extractor {
      type: "faster_rcnn_resnet101"
      first_stage_features_stride: 16
      batch_norm_trainable: true
    }
    first_stage_anchor_generator {
      grid_anchor_generator {
        height_stride: 16
        width_stride: 16
        scales: 0.25
        scales: 0.5
        scales: 1.0
        scales: 2.0
        aspect_ratios: 0.5
        aspect_ratios: 1.0
        aspect_ratios: 2.0
      }
    }
    first_stage_box_predictor_conv_hyperparams {
      op: CONV
      regularizer {
        l2_regularizer {
          weight: 0.0
        }
      }
      initializer {
        truncated_normal_initializer {
          stddev: 0.00999999977648
        }
      }
    }
    first_stage_nms_score_threshold: 0.0
    first_stage_nms_iou_threshold: 0.699999988079
    first_stage_max_proposals: 300
    first_stage_localization_loss_weight: 2.0
    first_stage_objectness_loss_weight: 1.0
    initial_crop_size: 14
    maxpool_kernel_size: 2
    maxpool_stride: 2
    second_stage_box_predictor {
      mask_rcnn_box_predictor {
        fc_hyperparams {
          op: FC
          regularizer {
            l2_regularizer {
              weight: 0.0
            }
          }
          initializer {
            variance_scaling_initializer {
              factor: 1.0
              uniform: true
              mode: FAN_AVG
            }
          }
        }
        use_dropout: false
        dropout_keep_probability: 1.0
        share_box_across_classes: true
      }
    }
    second_stage_post_processing {
      batch_non_max_suppression {
        score_threshold: 0.0
        iou_threshold: 0.600000023842
        max_detections_per_class: 100
        max_total_detections: 300
      }
      score_converter: SOFTMAX
    }
    second_stage_localization_loss_weight: 2.0
    second_stage_classification_loss_weight: 1.0
    use_matmul_crop_and_resize: true
    clip_anchors_to_image: true
    use_matmul_gather_in_matcher: true
    use_static_balanced_label_sampler: true
    use_static_shapes: true
    context_config {
      max_num_context_features: 2000
      context_feature_length: 2057
    }
  }
}
train_config {
  batch_size: 1
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  sync_replicas: true
  optimizer {
    momentum_optimizer {
      learning_rate {
        manual_step_learning_rate {
          initial_learning_rate: 0.0
          schedule {
            step: 2000
            learning_rate: 0.00200000009499
          }
          schedule {
            step: 200000
            learning_rate: 0.000199999994948
          }
          schedule {
            step: 300000
            learning_rate: 1.99999994948e-05
          }
          warmup: true
        }
      }
      momentum_optimizer_value: 0.899999976158
    }
    use_moving_average: false
  }
  gradient_clipping_by_norm: 10.0
  num_steps: 500000
  replicas_to_aggregate: 8
  max_number_of_boxes: 100
  unpad_groundtruth_tensors: false
}
train_input_reader {
  label_map_path: ""
  tf_record_input_reader {
    input_path: ""
  }
  load_context_features: true
  input_type: TF_SEQUENCE_EXAMPLE
}
eval_config {
  max_evals: 50
  metrics_set: "coco_detection_metrics"
  use_moving_averages: false
  batch_size: 1
}
eval_input_reader {
  label_map_path: ""
  shuffle: false
  num_epochs: 1
  tf_record_input_reader {
    input_path: ""
  }
  load_context_features: true
  input_type: TF_SEQUENCE_EXAMPLE
}