keypoint_map_dict[kp_config.keypoint_class_name]流: label_map_item = Tensorflow：'item‘

Question

遵循本教程，我尝试使用Tensorflow进行对象检测：https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/index.html现在我已经接近尾声，需要运行我的pipeline.config了。当我运行此命令时，我得到以下错误：

model_builder.py", line 844, in keypoint_proto_to_params label_map_item = keypoint_map_dict[kp_config.keypoint_class_name] KeyError: 'item'

我的pipeline.config文件如下所示：

# hourglass[1] backbone. This config achieves an mAP of 41.92 +/- 0.16 on
# COCO 17 (averaged over 5 runs). This config is TPU compatible.
# [1]: https://arxiv.org/abs/1603.06937
# [2]: https://arxiv.org/abs/1904.07850

model {
  center_net {
    num_classes: 5
    feature_extractor {
      type: "hourglass_104"
      bgr_ordering: true
      channel_means: [104.01362025, 114.03422265, 119.9165958 ]
      channel_stds: [73.6027665 , 69.89082075, 70.9150767 ]
    }
    image_resizer {
      keep_aspect_ratio_resizer {
        min_dimension: 512
        max_dimension: 512
        pad_to_max_dimension: true
      }
    }
    object_detection_task {
      task_loss_weight: 1.0
      offset_loss_weight: 1.0
      scale_loss_weight: 0.1
      localization_loss {
        l1_localization_loss {
        }
      }
    }
    object_center_params {
      object_center_loss_weight: 1.0
      min_box_overlap_iou: 0.7
      max_box_predictions: 100
      classification_loss {
        penalty_reduced_logistic_focal_loss {
          alpha: 2.0
          beta: 4.0
        }
      }
    }

    keypoint_label_map_path: "annotations/label_map_cans_in_fridge.pbtxt"
    keypoint_estimation_task {
      task_name: "human_pose"
      task_loss_weight: 1.0
      loss {
        localization_loss {
          l1_localization_loss {
          }
        }
        classification_loss {
          penalty_reduced_logistic_focal_loss {
            alpha: 2.0
            beta: 4.0
          }
        }
      }
      keypoint_class_name: "item"
      keypoint_label_to_std {
        key: "left_ankle"
        value: 0.89
      }
      keypoint_label_to_std {
        key: "left_ear"
        value: 0.35
      }
      keypoint_label_to_std {
        key: "left_elbow"
        value: 0.72
      }
      keypoint_label_to_std {
        key: "left_eye"
        value: 0.25
      }
      keypoint_label_to_std {
        key: "left_hip"
        value: 1.07
      }
      keypoint_label_to_std {
        key: "left_knee"
        value: 0.89
      }
      keypoint_label_to_std {
        key: "left_shoulder"
        value: 0.79
      }
      keypoint_label_to_std {
        key: "left_wrist"
        value: 0.62
      }
      keypoint_label_to_std {
        key: "nose"
        value: 0.26
      }
      keypoint_label_to_std {
        key: "right_ankle"
        value: 0.89
      }
      keypoint_label_to_std {
        key: "right_ear"
        value: 0.35
      }
      keypoint_label_to_std {
        key: "right_elbow"
        value: 0.72
      }
      keypoint_label_to_std {
        key: "right_eye"
        value: 0.25
      }
      keypoint_label_to_std {
        key: "right_hip"
        value: 1.07
      }
      keypoint_label_to_std {
        key: "right_knee"
        value: 0.89
      }
      keypoint_label_to_std {
        key: "right_shoulder"
        value: 0.79
      }
      keypoint_label_to_std {
        key: "right_wrist"
        value: 0.62
      }
      keypoint_regression_loss_weight: 0.1
      keypoint_heatmap_loss_weight: 1.0
      keypoint_offset_loss_weight: 1.0
      offset_peak_radius: 3
      per_keypoint_offset: true
    }
  }
}

train_config: {

  batch_size: 8 # higher volume requires more memory, can change this
  num_steps: 250000

  data_augmentation_options {
    random_horizontal_flip {
      keypoint_flip_permutation: 0
      keypoint_flip_permutation: 2
      keypoint_flip_permutation: 1
      keypoint_flip_permutation: 4
      keypoint_flip_permutation: 3
      keypoint_flip_permutation: 6
      keypoint_flip_permutation: 5
      keypoint_flip_permutation: 8
      keypoint_flip_permutation: 7
      keypoint_flip_permutation: 10
      keypoint_flip_permutation: 9
      keypoint_flip_permutation: 12
      keypoint_flip_permutation: 11
      keypoint_flip_permutation: 14
      keypoint_flip_permutation: 13
      keypoint_flip_permutation: 16
      keypoint_flip_permutation: 15
    }
  }

  data_augmentation_options {
    random_crop_image {
      min_aspect_ratio: 0.5
      max_aspect_ratio: 1.7
      random_coef: 0.25
    }
  }


  data_augmentation_options {
    random_adjust_hue {
    }
  }

  data_augmentation_options {
    random_adjust_contrast {
    }
  }

  data_augmentation_options {
    random_adjust_saturation {
    }
  }

  data_augmentation_options {
    random_adjust_brightness {
    }
  }

  data_augmentation_options {
    random_absolute_pad_image {
       max_height_padding: 200
       max_width_padding: 200
       pad_color: [0, 0, 0]
    }
  }

  optimizer {
    adam_optimizer: {
      epsilon: 1e-7  # Match tf.keras.optimizers.Adam's default.
      learning_rate: {
        cosine_decay_learning_rate {
          learning_rate_base: 1e-3
          total_steps: 250000
          warmup_learning_rate: 2.5e-4
          warmup_steps: 5000
        }
      }
    }
    use_moving_average: false
  }
  max_number_of_boxes: 100
  unpad_groundtruth_tensors: false

  fine_tune_checkpoint_version: V2
  fine_tune_checkpoint: "pre-trained-models/ssd_resnet50_v1_fpn_640x640_coco17_tpu-8/checkpoint/ckpt-0"
  fine_tune_checkpoint_type: "detection"
}

train_input_reader: {
  label_map_path: "annotations/label_map_cans_in_fridge.pbtxt"
  tf_record_input_reader {
    input_path: "annotations/train.record"
  }
  num_keypoints: 17
}

eval_config: {
  metrics_set: "coco_detection_metrics"
  use_moving_averages: false
  num_visualizations: 10
  max_num_boxes_to_visualize: 20
  min_score_threshold: 0.2
  batch_size: 1;
  parameterized_metric {
    coco_keypoint_metrics {
      class_label: "person"
      keypoint_label_to_sigmas {
        key: "nose"
        value: 0.026
      }
      keypoint_label_to_sigmas {
        key: "left_eye"
        value: 0.025
      }
      keypoint_label_to_sigmas {
        key: "right_eye"
        value: 0.025
      }
      keypoint_label_to_sigmas {
        key: "left_ear"
        value: 0.035
      }
      keypoint_label_to_sigmas {
        key: "right_ear"
        value: 0.035
      }
      keypoint_label_to_sigmas {
        key: "left_shoulder"
        value: 0.079
      }
      keypoint_label_to_sigmas {
        key: "right_shoulder"
        value: 0.079
      }
      keypoint_label_to_sigmas {
        key: "left_elbow"
        value: 0.072
      }
      keypoint_label_to_sigmas {
        key: "right_elbow"
        value: 0.072
      }
      keypoint_label_to_sigmas {
        key: "left_wrist"
        value: 0.062
      }
      keypoint_label_to_sigmas {
        key: "right_wrist"
        value: 0.062
      }
      keypoint_label_to_sigmas {
        key: "left_hip"
        value: 0.107
      }
      keypoint_label_to_sigmas {
        key: "right_hip"
        value: 0.107
      }
      keypoint_label_to_sigmas {
        key: "left_knee"
        value: 0.087
      }
      keypoint_label_to_sigmas {
        key: "right_knee"
        value: 0.087
      }
      keypoint_label_to_sigmas {
        key: "left_ankle"
        value: 0.089
      }
      keypoint_label_to_sigmas {
        key: "right_ankle"
        value: 0.089
      }
    }
  }
  # Provide the edges to connect the keypoints. The setting is suitable for
  # COCO's 17 human pose keypoints.
  keypoint_edge {  # nose-left eye
    start: 0
    end: 1
  }
  keypoint_edge {  # nose-right eye
    start: 0
    end: 2
  }
  keypoint_edge {  # left eye-left ear
    start: 1
    end: 3
  }
  keypoint_edge {  # right eye-right ear
    start: 2
    end: 4
  }
  keypoint_edge {  # nose-left shoulder
    start: 0
    end: 5
  }
  keypoint_edge {  # nose-right shoulder
    start: 0
    end: 6
  }
  keypoint_edge {  # left shoulder-left elbow
    start: 5
    end: 7
  }
  keypoint_edge {  # left elbow-left wrist
    start: 7
    end: 9
  }
  keypoint_edge {  # right shoulder-right elbow
    start: 6
    end: 8
  }
  keypoint_edge {  # right elbow-right wrist
    start: 8
    end: 10
  }
  keypoint_edge {  # left shoulder-right shoulder
    start: 5
    end: 6
  }
  keypoint_edge {  # left shoulder-left hip
    start: 5
    end: 11
  }
  keypoint_edge {  # right shoulder-right hip
    start: 6
    end: 12
  }
  keypoint_edge {  # left hip-right hip
    start: 11
    end: 12
  }
  keypoint_edge {  # left hip-left knee
    start: 11
    end: 13
  }
  keypoint_edge {  # left knee-left ankle
    start: 13
    end: 15
  }
  keypoint_edge {  # right hip-right knee
    start: 12
    end: 14
  }
  keypoint_edge {  # right knee-right ankle
    start: 14
    end: 16
  }
}

eval_input_reader: {
  label_map_path: "annotations/label_map_cans_in_fridge.pbtxt"
  tf_record_input_reader {
    input_path: "annotations/test.record"
  }
  num_keypoints: 17
}

我检查了所有目录的路径，没有问题。问题出在下面这一行：

keypoint_class_name: "item"

我从labelimg.pbtxt文件中获得的有价值的项目。它看起来像这样：

    id: 1
    name: 'ColaCan'
}

item {
    id: 2
    name: 'FantaCan'
}

item {
    id: 3
    name: 'SpriteLemonCan'
}

item {
    id: 4
    name: 'Upperside'
}


item {
    id: 5
    name: 'VanishingLine'
}

有人能告诉我我哪里做错了吗？

Answer 1

您选择了一个带有关键点检测的模型，因此pipeline.config将查找两个标签映射。

首先是要通过边界框进行分类的对象的标签映射，然后是关键点标签映射。

object_detection应用编程接口的model/research/object_detection/data文件夹提供了此类关键点标签映射的示例。keypoint_class_name应该引用关键点标签映射中的类标签，例如'Person‘。

这也应该映射到您的训练集中的关键点标签。