python - 带有 Mobilenets 的 Tensorflow 对象检测 API 过拟合自定义多类数据集

Question

该模型过度拟合训练集并且无法泛化到测试集。

• 如何向模型的特征提取器部分添加 dropout？ (.config文件只提供了一个键值给box predictor添加dropout)

• 我可以采取哪些其他措施来最大程度地减少过度拟合？

更多详情如下:

我正在尝试在玩具动物数据集上重新训练模型检查点“ssd_mobilenet_v1_coco_11_06_2017”。有 14 个类别，每个类别有 400-600 张图像。网络以不到 30k 步的速度学习训练集。 Tensorboard .在初始训练后损失似乎仍然相当不稳定，尽管我没有足够的经验来评估这一点。

我正在通过将导出的图形应用于图像并手动检查结果来测试模型。 (我只是没有时间正确实现验证)。该模型在与训练集中的条件非常相似的情况下拍摄的照片效果很好。这些不好的测试集图像是从训练集中随机分开的，训练集是通过连续拍摄许多图像并稍微改变相机角度获得的。训练集还包括各种光照条件、背景、失真和相机位置。我估计它在 不良测试集 的大约 95% 的图像中得到了正确的类和位置。由此我得出结论，该模型非常适合训练集并且可以泛化一点。

但是，该模型在不同时间用不同相机分别拍摄的照片上表现非常差(即该测试集和训练集之间的相关性应该小得多)。我估计这个好的测试集的性能大约是 25%。由此我得出结论，该模型过度拟合且无法泛化。

我已尝试在 .config 文件中进行一些更改。

• 将特征提取器和框预测器的 l2_regularizer 权重从 0.00004 增加到 0.0001。

• 将框预测器 use_dropout 设置为 true 以启用 20% 的 dropout。

我正在使用大约 3 周前从 github 克隆的 Tensorflow 1.4 pip 安装和模型。

我使用以下参数调用 object_detection 中的 train.py:

python train.py --logtostderr --train_dir=/home/X/TrainDir/Process --pipeline_config_path=/home/X/ssd_mobilenet_v1_coco.config

我的配置文件如下:

# SSD with Mobilenet 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 {
  ssd {
    num_classes: 14
    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: true
        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: 0.0001
            }
          }
          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'
      min_depth: 16
      depth_multiplier: 1.0
      conv_hyperparams {
        activation: RELU_6,
        regularizer {
          l2_regularizer {
            weight: 0.0001
          }
        }
        initializer {
          truncated_normal_initializer {
            stddev: 0.03
            mean: 0.0
          }
        }
        batch_norm {
          train: true,
          scale: true,
          center: true,
          decay: 0.9997,
          epsilon: 0.001,
        }
      }
    }
    loss {
      classification_loss {
        weighted_sigmoid {
          anchorwise_output: true
        }
      }
      localization_loss {
        weighted_smooth_l1 {
          anchorwise_output: true
        }
      }
      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: 8
  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: "/home/X/tensorflow/models/research/object_detection/ssd_mobilenet_v1_coco_11_06_2017/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 {
    }
  }
  data_augmentation_options {
    ssd_random_crop {
    }
  }
}

train_input_reader: {
  tf_record_input_reader {
    input_path: "/home/X/TrainDir/train.record"
  }
  label_map_path: "/home/X/TrainDir/data_label_map.pbtxt"
}

eval_config: {
  num_examples: 1200
  # Note: The below line limits the evaluation process to 10 evaluations.
  # Remove the below line to evaluate indefinitely.
  max_evals: 30
}

eval_input_reader: {
  tf_record_input_reader {
    input_path: "/home/X/TrainDir/test.record"
  }
  label_map_path: "/home/X/TrainDir/data_label_map.pbtxt"
  shuffle: false
  num_readers: 1
  num_epochs: 1
}

Answer 1

经过一些技巧后，网络学得很好，并开始在良好的测试集上进行泛化。

• 我加入了每 5000 步大约 10% 的学习率衰减(这已经起到了很大帮助)。
• 我在玩具动物的训练集中添加了大约 10% 的同类真实动物图像的额外图像。这极大地提高了泛化能力。
• 进行更长时间的培训可进一步改善结果。
• 我将正则化和 box_predictor dropout 保留为原始值。

经过训练的网络在真实场景中表现良好，在全新场景和光照条件下拍摄照片时对这些动物进行在线检测。

以下内容于 06/03/2020 添加

为了响应评论中的要求，我翻出了我在这个项目中存储的配置文件(> 2 年前)。这很可能是我最终使用的最终配置，效果很好。

# SSD with Mobilenet 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 {
  ssd {
    num_classes: 14
    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: true
        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'
      min_depth: 16
      depth_multiplier: 1.0
      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,
        }
      }
    }
    loss {
      classification_loss {
        weighted_sigmoid {
          anchorwise_output: true
        }
      }
      localization_loss {
        weighted_smooth_l1 {
          anchorwise_output: true
        }
      }
      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: 8
  optimizer {
    rms_prop_optimizer: {
      learning_rate: {
        exponential_decay_learning_rate {
          initial_learning_rate: 0.004
          decay_steps: 7000
          decay_factor: 0.75
        }
      }
      momentum_optimizer_value: 0.9
      decay: 0.9
      epsilon: 1.0
    }
  }
  fine_tune_checkpoint: "/home/sander/tensorflow/models/research/object_detection/ssd_mobilenet_v1_coco_11_06_2017/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 {
    }
  }
  data_augmentation_options {
    ssd_random_crop {
    }
  }
}

train_input_reader: {
  tf_record_input_reader {
    input_path: "/home/sander/ROBOT/TrainDir/train.record"
  }
  label_map_path: "/home/sander/ROBOT/TrainDir/data_label_map.pbtxt"
}

eval_config: {
  num_examples: 1200
  # Note: The below line limits the evaluation process to 10 evaluations.
  # Remove the below line to evaluate indefinitely.
  max_evals: 30
}

eval_input_reader: {
  tf_record_input_reader {
    input_path: "/home/sander/ROBOT/TrainDir/test.record"
  }
  label_map_path: "/home/sander/ROBOT/TrainDir/data_label_map.pbtxt"
  shuffle: false
  num_readers: 1
  num_epochs: 1
}