Tensorflow 对象检测 API 的正确配置设置以添加类或进行迁移学习答案

【问题标题】：Proper config settings for Tensorflow Object Detection API to add a class or do transfer learningTensorflow 对象检测 API 的正确配置设置以添加类或进行迁移学习
【发布时间】：2019-05-24 14:58:22
【问题描述】：

需要了解 Tensorflow 对象检测 API 的正确配置设置以添加类并进行迁移学习

阅读 https://github.com/tensorflow/models/issues/6479 和 Retrain Tensorflow Object detection API 后，仍然不清楚如何使用 API 进行迁移学习。

我正在寻找将类添加到经过训练的模型的正确方法。例如，SSD with Mobilenet v1

我见过的使用对象检测 API 的方法涉及进行以下更改：在管道配置文件中：

将 num_classes: 90 更改为 num_classes: 1
将 fine_tune_checkpoint: 更改为 "../yourlocalpath/model.ckpt
保持 from_detection_checkpoint：true
将 train_input_reader/input_path: 更改为 "../yourtrainimagepath/train.record"
将 train_input_reader/label_map_path 更改为 "../yourlocalpath/classes.pbtxt"
将 eval_input_reader / input_path 更改为 "../yourtestimagepath/test.rocord"
将 eval_input_reader / label_map_path 更改为 "../yourlocalpath/classes.pbtxt"

还有，

将文件："../yourlocalpath/classes.pbtxt" 更改为仅包含：

item {
id: 1
name: 'some_new_class'
}

我用 200,000 步（18 小时）训练了 600 张图像，损失了 1.5。

我在训练数据上达到了 90% 以上的准确率，但在评估上却不到 10%。这显然是过拟合。我的第一个想法是模型对于单个项目来说太复杂了。它只是记住了训练数据。我还注意到其他 90 个原始项目已不再找到。

然后我将 num_classes 更改为 91 并简单地添加物品 { 编号：91 名称：'some_new_class' } 到原来的 classes.pbtxt 文件？

我的结果没有太大改善 (20%)。（这一次我停止了大约 100,000 步的训练，但到那时学习曲线几乎变平了）。

对于这两种情况，我都选择不更改 "from_detection_checkpoint: true" 设置。因为“从检测检查点开始通常会导致比分类检查点更快的训练工作。”参考：https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/configuring_jobs.md#model-parameter-initialization

训练对象检测器以检测所有对象（旧的和新的）的正确方法是什么？

我希望当我对包含除我的新对象之外的已训练对象的图像进行预测时，所有对象都能找到。

这里是使用的配置文件。

第一个 num_classes: 1

# SSD with Mobilenet v1, configured for Oxford-IIIT Pets 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: 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'
      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 {
        }
      }
      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: 10
  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/adriansr/HoodML/Datasets/ssd_mobilenet_v1_coco_2018_01_28/model.ckpt"
  from_detection_checkpoint: true
  load_all_detection_checkpoint_vars: 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/adriansr/HoodML/Datasets/2016_USATF_Sprint_TrainingDataset/Analyze/train.record"
  }
  label_map_path: "/home/adriansr/HoodML/hoodbibod/training/classes.pbtxt"
}

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

eval_input_reader: {
  tf_record_input_reader {
    input_path: "/home/adriansr/HoodML/Datasets/2016_USATF_Sprint_TrainingDataset/Analyze/test.record"
  }
  label_map_path: "/home/adriansr/HoodML/hoodbibod/training/classes.pbtxt"
  shuffle: false
  num_readers: 1
}

第二个 num_classes: 91

# SSD with Mobilenet v1, configured for Oxford-IIIT Pets 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: 91
    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'
      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 {
        }
      }
      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: 10
  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/adriansr/HoodML/Datasets/ssd_mobilenet_v1_coco_2018_01_28/model.ckpt"
  from_detection_checkpoint: true
  load_all_detection_checkpoint_vars: 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/adriansr/HoodML/Datasets/2016_USATF_Sprint_TrainingDataset/Analyze/train.record"
  }
  label_map_path: "/home/adriansr/HoodML/hoodbibod/training/mscoco_complete_label_map_with_bib.pbtxt"
}

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

eval_input_reader: {
  tf_record_input_reader {
    input_path: "/home/adriansr/HoodML/Datasets/2016_USATF_Sprint_TrainingDataset/Analyze/test.record"
  }
  label_map_path: "/home/adriansr/HoodML/hoodbibod/training/mscoco_complete_label_map_with_bib.pbtxt"
  shuffle: false
  num_readers: 1
}

classes.pbtxt

item {
  id: 1
  name: 'Bib'
}

mscoco_complete_label_map_with_bib.pbtxt

item {
  name: "background"
  id: 0
  display_name: "background"
}
item {
  name: "/m/01g317"
  id: 1
  display_name: "person"
}
item {
  name: "/m/0199g"
  id: 2
  display_name: "bicycle"
}
item {
  name: "/m/0k4j"
  id: 3
  display_name: "car"
}
item {
  name: "/m/04_sv"
  id: 4
  display_name: "motorcycle"
}
item {
  name: "/m/05czz6l"
  id: 5
  display_name: "airplane"
}
item {
  name: "/m/01bjv"
  id: 6
  display_name: "bus"
}
item {
  name: "/m/07jdr"
  id: 7
  display_name: "train"
}
item {
  name: "/m/07r04"
  id: 8
  display_name: "truck"
}
item {
  name: "/m/019jd"
  id: 9
  display_name: "boat"
}
item {
  name: "/m/015qff"
  id: 10
  display_name: "traffic light"
}
item {
  name: "/m/01pns0"
  id: 11
  display_name: "fire hydrant"
}
item {
  name: "12"
  id: 12
  display_name: "12"
}
item {
  name: "/m/02pv19"
  id: 13
  display_name: "stop sign"
}
item {
  name: "/m/015qbp"
  id: 14
  display_name: "parking meter"
}
item {
  name: "/m/0cvnqh"
  id: 15
  display_name: "bench"
}
item {
  name: "/m/015p6"
  id: 16
  display_name: "bird"
}
item {
  name: "/m/01yrx"
  id: 17
  display_name: "cat"
}
item {
  name: "/m/0bt9lr"
  id: 18
  display_name: "dog"
}
item {
  name: "/m/03k3r"
  id: 19
  display_name: "horse"
}
item {
  name: "/m/07bgp"
  id: 20
  display_name: "sheep"
}
item {
  name: "/m/01xq0k1"
  id: 21
  display_name: "cow"
}
item {
  name: "/m/0bwd_0j"
  id: 22
  display_name: "elephant"
}
item {
  name: "/m/01dws"
  id: 23
  display_name: "bear"
}
item {
  name: "/m/0898b"
  id: 24
  display_name: "zebra"
}
item {
  name: "/m/03bk1"
  id: 25
  display_name: "giraffe"
}
item {
  name: "26"
  id: 26
  display_name: "26"
}
item {
  name: "/m/01940j"
  id: 27
  display_name: "backpack"
}
item {
  name: "/m/0hnnb"
  id: 28
  display_name: "umbrella"
}
item {
  name: "29"
  id: 29
  display_name: "29"
}
item {
  name: "30"
  id: 30
  display_name: "30"
}
item {
  name: "/m/080hkjn"
  id: 31
  display_name: "handbag"
}
item {
  name: "/m/01rkbr"
  id: 32
  display_name: "tie"
}
item {
  name: "/m/01s55n"
  id: 33
  display_name: "suitcase"
}
item {
  name: "/m/02wmf"
  id: 34
  display_name: "frisbee"
}
item {
  name: "/m/071p9"
  id: 35
  display_name: "skis"
}
item {
  name: "/m/06__v"
  id: 36
  display_name: "snowboard"
}
item {
  name: "/m/018xm"
  id: 37
  display_name: "sports ball"
}
item {
  name: "/m/02zt3"
  id: 38
  display_name: "kite"
}
item {
  name: "/m/03g8mr"
  id: 39
  display_name: "baseball bat"
}
item {
  name: "/m/03grzl"
  id: 40
  display_name: "baseball glove"
}
item {
  name: "/m/06_fw"
  id: 41
  display_name: "skateboard"
}
item {
  name: "/m/019w40"
  id: 42
  display_name: "surfboard"
}
item {
  name: "/m/0dv9c"
  id: 43
  display_name: "tennis racket"
}
item {
  name: "/m/04dr76w"
  id: 44
  display_name: "bottle"
}
item {
  name: "45"
  id: 45
  display_name: "45"
}
item {
  name: "/m/09tvcd"
  id: 46
  display_name: "wine glass"
}
item {
  name: "/m/08gqpm"
  id: 47
  display_name: "cup"
}
item {
  name: "/m/0dt3t"
  id: 48
  display_name: "fork"
}
item {
  name: "/m/04ctx"
  id: 49
  display_name: "knife"
}
item {
  name: "/m/0cmx8"
  id: 50
  display_name: "spoon"
}
item {
  name: "/m/04kkgm"
  id: 51
  display_name: "bowl"
}
item {
  name: "/m/09qck"
  id: 52
  display_name: "banana"
}
item {
  name: "/m/014j1m"
  id: 53
  display_name: "apple"
}
item {
  name: "/m/0l515"
  id: 54
  display_name: "sandwich"
}
item {
  name: "/m/0cyhj_"
  id: 55
  display_name: "orange"
}
item {
  name: "/m/0hkxq"
  id: 56
  display_name: "broccoli"
}
item {
  name: "/m/0fj52s"
  id: 57
  display_name: "carrot"
}
item {
  name: "/m/01b9xk"
  id: 58
  display_name: "hot dog"
}
item {
  name: "/m/0663v"
  id: 59
  display_name: "pizza"
}
item {
  name: "/m/0jy4k"
  id: 60
  display_name: "donut"
}
item {
  name: "/m/0fszt"
  id: 61
  display_name: "cake"
}
item {
  name: "/m/01mzpv"
  id: 62
  display_name: "chair"
}
item {
  name: "/m/02crq1"
  id: 63
  display_name: "couch"
}
item {
  name: "/m/03fp41"
  id: 64
  display_name: "potted plant"
}
item {
  name: "/m/03ssj5"
  id: 65
  display_name: "bed"
}
item {
  name: "66"
  id: 66
  display_name: "66"
}
item {
  name: "/m/04bcr3"
  id: 67
  display_name: "dining table"
}
item {
  name: "68"
  id: 68
  display_name: "68"
}
item {
  name: "69"
  id: 69
  display_name: "69"
}
item {
  name: "/m/09g1w"
  id: 70
  display_name: "toilet"
}
item {
  name: "71"
  id: 71
  display_name: "71"
}
item {
  name: "/m/07c52"
  id: 72
  display_name: "tv"
}
item {
  name: "/m/01c648"
  id: 73
  display_name: "laptop"
}
item {
  name: "/m/020lf"
  id: 74
  display_name: "mouse"
}
item {
  name: "/m/0qjjc"
  id: 75
  display_name: "remote"
}
item {
  name: "/m/01m2v"
  id: 76
  display_name: "keyboard"
}
item {
  name: "/m/050k8"
  id: 77
  display_name: "cell phone"
}
item {
  name: "/m/0fx9l"
  id: 78
  display_name: "microwave"
}
item {
  name: "/m/029bxz"
  id: 79
  display_name: "oven"
}
item {
  name: "/m/01k6s3"
  id: 80
  display_name: "toaster"
}
item {
  name: "/m/0130jx"
  id: 81
  display_name: "sink"
}
item {
  name: "/m/040b_t"
  id: 82
  display_name: "refrigerator"
}
item {
  name: "83"
  id: 83
  display_name: "83"
}
item {
  name: "/m/0bt_c3"
  id: 84
  display_name: "book"
}
item {
  name: "/m/01x3z"
  id: 85
  display_name: "clock"
}
item {
  name: "/m/02s195"
  id: 86
  display_name: "vase"
}
item {
  name: "/m/01lsmm"
  id: 87
  display_name: "scissors"
}
item {
  name: "/m/0kmg4"
  id: 88
  display_name: "teddy bear"
}
item {
  name: "/m/03wvsk"
  id: 89
  display_name: "hair drier"
}
item {
  name: "/m/012xff"
  id: 90
  display_name: "toothbrush"
}
item {
  name: "/m/bib"
  id: 91
  display_name: "bib"
}

【问题讨论】：

您所说的时代是指步数，对吗？（一个纪元是整个数据集的一个完整循环）。您能否提供用于单节培训的完整配置文件？验证准确度如何表现，它永远不会超过 10%，或者它从某个高精度下降到 10%。如果你也能提供一些训练图也更好。
@danyfang... 是的，我的意思是步骤而不是时代。我做出了改变。另外，我添加了配置文件和 .pbtxt 文件中的信息。我通过对每个数据集运行预测并简单地计算正确和不正确的数据来测量测试准确度和训练准确度。即使 tensorflow 可以给我这些值，我还是选择编写一个单独的代码，以便我可以对丢失的馈送图像进行额外处理，例如，旋转 +/- 10 度、增强对比度、扭曲等。没有太大帮助。
此外，验证准确度下降很快（两个训练案例均小于 1000 步）并在持续时间内保持在 1 到 2 之间，偶尔会降至 1 以下。我会尽快添加 Tensorboard 输出。跨度>
您的验证数据集大小是多少？在配置文件中，验证数据集大小为 1100，大于您的训练数据集大小。
在配置文件中，eval_config 文件下，num_examples 应设置为等于验证数据集大小的大小。

标签： tensorflow object-detection-api

【解决方案1】：

晚了 2 年但是...从根本上说，您无法在新课程上训练您的网络，并且它不会影响之前训练过的课程的识别准确性。通过在新对象的数据集上进行训练，并且使用仅包含该新对象的标签图，模型将仅优化以检测新对象，因为您正在更改启用旧对象检测的权重。您可以尝试将您的数据集与模型最初训练的数据集合并，并在新合并集上进行训练。除非您计划以某种方式确保新对象出现在带有旧对象标记的图像中，否则即使这样也是不够的（也许某种合成数据生成过程可能有用）。

【讨论】：