tensorflow - tensorflow中的faster-rcnn配置文件

Question

我正在使用 Google API for object detection在 tensorflow 中训练和推断自定义数据集。

我想调整配置文件的参数以更好地适应我的样本(例如区域提议的数量、ROI bbox 的大小等)。
为此，我需要知道每个参数的作用。
不幸的是，配置文件(找到 here )没有注释或解释。
一些，例如“num classes”是不言自明的，但其他的则很棘手。

我找到了 this file有更多评论，但无法将其“翻译”为我的格式。

我想知道以下其中一项:
1. google API config文件各参数说明
或者
2.从官方的faster-rcnn'翻译'到google的API配置
或者至少
3. 对faster-rcnn的参数技术细节进行了彻底的审查(官方文章没有提供所有细节)

谢谢你的热心帮助 !

配置文件示例:

# Faster R-CNN with Resnet-101 (v1) configuration for MSCOCO Dataset.
# 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 {
  faster_rcnn {
    num_classes: 90
    image_resizer {
      keep_aspect_ratio_resizer {
    min_dimension: 600
    max_dimension: 1024
      }
    }
    feature_extractor {
      type: 'faster_rcnn_resnet101'
      first_stage_features_stride: 16
    }
    first_stage_anchor_generator {
      grid_anchor_generator {
    scales: [0.25, 0.5, 1.0, 2.0]
    aspect_ratios: [0.5, 1.0, 2.0]
    height_stride: 16
    width_stride: 16
      }
    }
    first_stage_box_predictor_conv_hyperparams {
      op: CONV
      regularizer {
    l2_regularizer {
      weight: 0.0
    }
      }
      initializer {
    truncated_normal_initializer {
      stddev: 0.01
    }
      }
    }
    first_stage_nms_score_threshold: 0.0
    first_stage_nms_iou_threshold: 0.7
    first_stage_max_proposals: 300
    first_stage_localization_loss_weight: 2.0
    first_stage_objectness_loss_weight: 1.0
    initial_crop_size: 14
    maxpool_kernel_size: 2
    maxpool_stride: 2
    second_stage_box_predictor {
      mask_rcnn_box_predictor {
    use_dropout: false
    dropout_keep_probability: 1.0
    fc_hyperparams {
      op: FC
      regularizer {
        l2_regularizer {
          weight: 0.0
        }
      }
      initializer {
        variance_scaling_initializer {
          factor: 1.0
          uniform: true
          mode: FAN_AVG
        }
      }
    }
      }
    }
    second_stage_post_processing {
      batch_non_max_suppression {
    score_threshold: 0.0
    iou_threshold: 0.6
    max_detections_per_class: 100
    max_total_detections: 300
      }
      score_converter: SOFTMAX
    }
    second_stage_localization_loss_weight: 2.0
    second_stage_classification_loss_weight: 1.0
  }
}

train_config: {
  batch_size: 1
  optimizer {
    momentum_optimizer: {
      learning_rate: {
    manual_step_learning_rate {
      initial_learning_rate: 0.0003
      schedule {
        step: 0
        learning_rate: .0003
      }
      schedule {
        step: 900000
        learning_rate: .00003
      }
      schedule {
        step: 1200000
        learning_rate: .000003
      }
    }
      }
      momentum_optimizer_value: 0.9
    }
    use_moving_average: false
  }
  gradient_clipping_by_norm: 10.0
  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
  from_detection_checkpoint: true
  # Note: The below line limits the training process to 200K steps, which we
  # empirically found to be sufficient enough to train the pets dataset. This
  # effectively bypasses the learning rate schedule (the learning rate will
  # never decay). Remove the below line to train indefinitely.
  num_steps: 200000
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
}

train_input_reader: {
  tf_record_input_reader {
    input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record"
  }
  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
}

eval_config: {
  num_examples: 8000
  # Note: The below line limits the evaluation process to 10 evaluations.
  # Remove the below line to evaluate indefinitely.
  max_evals: 10
}

eval_input_reader: {
  tf_record_input_reader {
    input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record"
  }
  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
  shuffle: false
  num_readers: 1
  num_epochs: 1
}

Answer 1

我发现了两个可以阐明配置文件的来源:
1.文件夹protos在 tensorflow github 中涵盖了所有配置选项，并对每个选项进行了一些注释。您应该检查 fast_rcnn.proto ， eval.proto 和 train.proto 以获得最常见的
2. This Algorithmia 的博客文章彻底涵盖了在 Google 的 Open Images 数据集上下载、准备和训练更快的 RCNN 的所有步骤。 2/3-way through，有一些关于配置选项的讨论。