tensorflow object_detection API: ssd_mobilenet_v1_fpn 网络使用的一些心得记录

这里慢慢记录一些自己使用的心得，

看一下配置文件

image_resizer： 将图片缩放到指定的高度宽度大小，图片缩放后尺寸越小速度要快，长宽的值是2的指数，长宽的比是1:1的情况下效果好像比较好，试了一下长宽比太大或者太小效果不太理想

model {
  ssd {
    num_classes: 90
    image_resizer {
      fixed_shape_resizer {
        height: 64
        width: 128
      }
    }
    feature_extractor {
      type: "ssd_mobilenet_v1_fpn"
      depth_multiplier: 1.0
      min_depth: 4
      conv_hyperparams {
        regularizer {
          l2_regularizer {
            weight: 3.99999989895e-05
          }
        }
        initializer {
          random_normal_initializer {
            mean: 0.0
            stddev: 0.00999999977648
          }
        }
        activation: RELU_6
        batch_norm {
          decay: 0.996999979019
          scale: true
          epsilon: 0.0010000000475
        }
      }
      override_base_feature_extractor_hyperparams: 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
        use_matmul_gather: true
      }
    }
    similarity_calculator {
      iou_similarity {
      }
    }
    box_predictor {
      weight_shared_convolutional_box_predictor {
        conv_hyperparams {
          regularizer {
            l2_regularizer {
              weight: 3.99999989895e-05
            }
          }
          initializer {
            random_normal_initializer {
              mean: 0.0
              stddev: 0.00999999977648
            }
          }
          activation: RELU_6
          batch_norm {
            decay: 0.996999979019
            scale: true
            epsilon: 0.0010000000475
          }
        }
        depth: 256
        num_layers_before_predictor: 4
        kernel_size: 3
        class_prediction_bias_init: -4.59999990463
      }
    }
    anchor_generator {
      multiscale_anchor_generator {
        min_level: 3
        max_level: 7
        anchor_scale: 4.0
        aspect_ratios: 1.0
        aspect_ratios: 2.0
        aspect_ratios: 0.5
        scales_per_octave: 2
      }
    }
    post_processing {
      batch_non_max_suppression {
        score_threshold: 0.300000011921
        iou_threshold: 0.600000023842
        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_focal {
          gamma: 2.0
          alpha: 0.25
        }
      }
      classification_weight: 1.0
      localization_weight: 1.0
    }
    encode_background_as_zeros: true
    normalize_loc_loss_by_codesize: true
    inplace_batchnorm_update: true
    freeze_batchnorm: false
  }
}
train_config {
  batch_size: 128
  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
    }
  }
  sync_replicas: false
  optimizer {
    momentum_optimizer {
      learning_rate {
        cosine_decay_learning_rate {
          learning_rate_base: 0.0799999982119
          total_steps: 12500
          warmup_learning_rate: 0.0266660004854
          warmup_steps: 1000
        }
      }
      momentum_optimizer_value: 0.899999976158
    }
    use_moving_average: false
  }
  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
  num_steps: 12500
  startup_delay_steps: 0.0
  replicas_to_aggregate: 1
  max_number_of_boxes: 100
  unpad_groundtruth_tensors: false
}
train_input_reader {
  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
  tf_record_input_reader {
    input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record-00000-of-00100"
  }
}
eval_config {
  num_examples: 8000
  metrics_set: "coco_detection_metrics"
  use_moving_averages: false
}
eval_input_reader {
  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
  shuffle: false
  num_readers: 1
  tf_record_input_reader {
    input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record-00000-of-00010"
  }
}