Python 带有Mobilenets的Tensorflow对象检测API超过了自定义多类数据集

该模型过度拟合训练集，无法推广到测试集。

• 如何向模型的特征提取部分添加辍学？（该.config文件仅提供一个键值，用于向框预测器添加退出）

• 我还可以采取哪些其他措施来减少过度装配

以下详细信息：

我试图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，每个类中有400-600个图像。网络以不到30k的步骤学习训练集。虽然我没有足够的经验来评估这一点，但在最初的训练之后，损失似乎仍然很不稳定

我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地实施验证）。该模型可以很好地处理在与训练集中的照片非常相似的条件下拍摄的照片。这些糟糕的测试集图像是从训练集中随机抽取的，训练集是通过连续拍摄多张图像而获得的，相机角度略有变化。训练集还包括各种照明条件、背景、失真和摄像机位置。我估计它从坏的测试集中大约95%的图像中获得了正确的类和位置。由此，我得出结论，该模型非常适合训练集，并且可以稍微推广

但是，该模型在不同时间使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，该模型过于拟合，无法推广

我已尝试在.config文件中进行一些更改

• 将特征提取器和长方体预测器的l2_正则化器权重从0.00004增加到0.0001

• 设置框预测器

  使用_dropout

  至

  true

  以启用20%的退出

我使用的是Tensorflow 1.4 pip安装和从github克隆的模型，这些模型是大约3周前的

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

我的配置文件如下所示：

# 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
}

---

您是否尝试过设置验证集，并在使用部分训练模型进行训练的同时自动运行评估？如果验证精度尚未收敛，那么您可能只需要对模型进行更长时间的训练

其他需要注意的事项：在“好”和“坏”测试集之间还有其他区别吗？例如分辨率/纵横比。您是否正确地遵循了培训期间执行的所有预处理步骤？例如，数据标准化、使用相同算法调整大小等

---

编辑：我查看了你的张力板截图，你认为网络为什么学习了你的训练集？看来损失并没有真正趋同。另外一件你应该做的事情是设置一个调度程序，以减少你的学习除以10，比如说每40K步，在学习了一些特征之后，你的梯度下降可能会出现收敛困难，因为你从未改变起始值的学习率，而且对于训练中的那个时间点来说，它可能太大了

在一些技巧之后，网络学得很好，并开始在好的测试集上推广

• 我把每5000步的学习率衰减10%计算在内（这已经帮了不少忙）
• 我在玩具动物的训练集中增加了10%的同类真实动物的额外图像。这大大改进了推广
• 长期培训进一步改善了结果
• 我将正则化和box_预测值保留为其原始值

经过训练的网络在真实场景中表现良好，在线检测这些动物，同时在全新的场景和照明条件下拍摄照片

以下内容于2020年3月6日添加

为了响应评论中的请求，我挖出了与此项目一起存储的配置文件（>2年前）。这很可能是我最终使用的配置，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
}

---

谢谢你的建议，安德里亚。我不久前就完成了这方面的工作，应该更新这篇文章。我按照您的建议实施了学习率衰减，并进行了更长时间的培训，这当然有所帮助。有关更多详细信息，请参阅我的问题答案。谢谢更新。所以你最终不必增加l2正则化或使用辍学？@AlexU:你能在这里帮助我吗：你能上传你更新的配置文件（作为回答）来帮助你解决问题吗？@SaurabhChauhan我已经用配置文件更新了上面的答案，我相信这是最后一个。我希望配置文件中的细节和一般答案能帮助您的网络正常工作。太好了，谢谢！你能告诉我在增加体重衰减（和辍学）之前和增加体重衰减（和辍学）之后的损失是多少吗？您在准确性和损失方面有多大改进？