Question

我想重新训练一个ssd_mobilenet_v1_0.75_depth_coco模型，因为我不需要所有90个类（只需要一个），而我将在ARM CPU上使用它，所以我试图它更快。

我对配置文件感到困惑。在档案中有一个文件pipeline.config，我考虑过将其与ObjectDetection Api一起使用。我有一些问题：

该配置文件中可以更改什么？
我也可以更改feature_extractor的参数吗？这部分不冻结吗，过程仅更改分类层？
如果要在具有16GB RAM的CPU上进行训练，哪些训练参数最重要？ batch_size和num_steps的任何合理值。

编辑

model {
  ssd {
    num_classes: 1
    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 {
      }
    }
    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
        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: 0.9997,
            epsilon: 0.001,
          }
        }
      }
    }
   feature_extractor {
      type: "ssd_mobilenet_v1"
      depth_multiplier: 0.75
      min_depth: 16
      conv_hyperparams {
        regularizer {
          l2_regularizer {
            weight: 3.99999989895e-05
          }
        }
        initializer {
          truncated_normal_initializer {
            mean: 0.0
            stddev: 0.0299999993294
          }
        }
        activation: RELU_6
        batch_norm {
          decay: 0.97000002861
          center: true
          scale: true
          epsilon: 0.0010000000475
          train: true
        }
      }
      override_base_feature_extractor_hyperparams: true
    }
    loss {
      classification_loss {
        weighted_sigmoid {
        }
      }
      localization_loss {
        weighted_smooth_l1 {
        }
      }
      hard_example_miner {
        num_hard_examples: 3000
        iou_threshold: 0.99
        loss_type: CLASSIFICATION
        max_negatives_per_positive: 3
        min_negatives_per_image: 0
      }
      classification_weight: 1.0
      localization_weight: 1.0
    }
    normalize_loss_by_num_matches: 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 {
  batch_size: 24
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  data_augmentation_options {
    ssd_random_crop {
    }
  }
  optimizer {
    rms_prop_optimizer: {
      learning_rate: {
        exponential_decay_learning_rate {
          initial_learning_rate: 0.004
          decay_steps: 5000
          decay_factor: 0.95
        }
      }
      momentum_optimizer_value: 0.9
      decay: 0.9
      epsilon: 1.0      
    }
    use_moving_average: false
  }
  fine_tune_checkpoint: "/content/pretrained_model/model.ckpt"
  from_detection_checkpoint: true
  load_all_detection_checkpoint_vars: false
  num_steps: 40000
}
train_input_reader {
  label_map_path: "/content/classes.pbtxt"
  tf_record_input_reader {
    input_path: "/content/gdrive/My Drive/coco_train_300.record"
  }
}
eval_config {
  num_examples: 2693
  metrics_set: "coco_detection_metrics"
  use_moving_averages: false
  num_visualizations: 20
}
eval_input_reader {
  label_map_path: "/content/classes.pbtxt"
  shuffle: false
  num_readers: 1
  tf_record_input_reader {
    input_path: "/content/gdrive/My Drive/coco_val_300.record"
  }
}

它可以学习，但是经过40k步损失仍然是5。输入数据集的大小调整为300x300。

Answer 1

我注意到您使用了：ssd_mobilenet_v1

您可以通过以下方式替换您的配置文件：

model {
  ssd {
    inplace_batchnorm_update: true
    freeze_batchnorm: false
    num_classes: 1
    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: 0.9,
            epsilon: 0.001,
          }
        }
      }
    }
    feature_extractor {
      type: 'ssd_mobilenet_v1'
      min_depth: 16
      depth_multiplier: 0.75
      conv_hyperparams {
        activation: RELU_6,
        regularizer {
          l2_regularizer {
            weight: 0.00004
          }
        }
        initializer {
          truncated_normal_initializer {
            stddev: 0.03
            mean: 0.0
          }
        }
        batch_norm {
          scale: true,
          center: true,
          decay: 0.9,
          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: "ssd_mobilenet_v1/model.ckpt"
  fine_tune_checkpoint_type: "detection"
  load_all_detection_checkpoint_vars: true
  batch_size: 128
  sync_replicas: true
  startup_delay_steps: 0
  replicas_to_aggregate: 8
  num_steps: 2000
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  data_augmentation_options {
    ssd_random_crop {
    }
  }
  optimizer {
    momentum_optimizer: {
      learning_rate: {
        cosine_decay_learning_rate {
          learning_rate_base: 0.2
          total_steps: 2000
          warmup_steps: 0
        }
      }
      momentum_optimizer_value: 0.9
    }
    use_moving_average: false
  }
  max_number_of_boxes: 100
  unpad_groundtruth_tensors: false
}

train_input_reader: {
  tf_record_input_reader {
    input_path: "data/train.record"
  }
  label_map_path: "data/object-detection.pbtxt"
}

eval_config: {
  metrics_set: "coco_detection_metrics"
  use_moving_averages: false
  num_examples: 1100
}

eval_input_reader: {
  tf_record_input_reader {
    input_path: "data/test.record"
  }
  label_map_path: "data/object-detection.pbtxt"
  shuffle: false
  num_readers: 1
}

graph_rewriter {
  quantization {
    delay: 1800
    activation_bits: 8
    weight_bits: 8
  }
}

确保使用此链接下载model.ckpt文件：

curl -O http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_0.75_depth_300x300_coco14_sync_2018_07_03.tar.gz

让我知道您的结果

Tensorflow对象检测管道和配置

1 个答案: