使用 tensorflow 的 OD API 时的低评估结果

如何解决使用 tensorflow 的 OD API 时的低评估结果

我正在尝试使用 tf1.4 OD API 创建用于检测车牌的检测模型。经过前几个评估check point，我开始觉得我一定是做错了什么，因为结果都出来了负面的o_0

 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000

现在我以前使用相同的管道进行过培训，但这是我第一次在单一课程中进行培训，也许我错过了一些重要的东西？ 这是管道：

model {
  ssd {
    num_classes: 1
    image_resizer {
      fixed_shape_resizer {
        height: 320
        width: 320
      }
    }
    feature_extractor {
      type: "ssd_mobiledet_edgetpu"
      depth_multiplier: 1.0
      min_depth: 16
      conv_hyperparams {
        regularizer {
          l2_regularizer {
            weight: 4e-05
          }
        }
        initializer {
          truncated_normal_initializer {
            mean: 0.0
            stddev: 0.03
          }
        }
        activation: RELU_6
        batch_norm {
          decay: 0.97
          center: true
          scale: true
          epsilon: 0.001
          train: true
        }
      }
      use_depthwise: true
      override_base_feature_extractor_hyperparams: false
    }
    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 {
      }
    }
    box_predictor {
      convolutional_box_predictor {
        conv_hyperparams {
          regularizer {
            l2_regularizer {
              weight: 4e-05
            }
          }
          initializer {
            random_normal_initializer {
              mean: 0.0
              stddev: 0.03
            }
          }
          activation: RELU_6
          batch_norm {
            decay: 0.97
            center: true
            scale: true
            epsilon: 0.001
            train: true
          }
        }
        min_depth: 0
        max_depth: 0
        num_layers_before_predictor: 0
        use_dropout: false
        dropout_keep_probability: 0.8
        kernel_size: 3
        box_code_size: 4
        apply_sigmoid_to_scores: false
        class_prediction_bias_init: -4.6
        use_depthwise: 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
      }
    }
    post_processing {
      batch_non_max_suppression {
        score_threshold: 1e-08
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 100
        use_static_shapes: true
      }
      score_converter: SIGMOID
    }
    normalize_loss_by_num_matches: true
    loss {
      localization_loss {
        weighted_smooth_l1 {
          delta: 1.0
        }
      }
      classification_loss {
        weighted_sigmoid_focal {
          gamma: 2.0
          alpha: 0.75
        }
      }
      classification_weight: 1.0
      localization_weight: 1.0
    }
    encode_background_as_zeros: true
    normalize_loc_loss_by_codesize: true
    inplace_batchnorm_update: true
    freeze_batchnorm: false
  }
}
train_config {
  batch_size: 32
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  data_augmentation_options {
    ssd_random_crop {
    }
  }
  sync_replicas: true
  optimizer {
    momentum_optimizer {
      learning_rate {
        cosine_decay_learning_rate {
          learning_rate_base: 0.8
          total_steps: 400000
          warmup_learning_rate: 0.13333
          warmup_steps: 2000
        }
      }
      momentum_optimizer_value: 0.9
    }
    use_moving_average: false
  }
  fine_tune_checkpoint: "/content/pretrained_model/ssdlite_mobiledet_edgetpu_320x320_coco_2020_05_19/ft32/model.ckpt"
  num_steps: 5000
  startup_delay_steps: 0.0
  replicas_to_aggregate: 32
  max_number_of_boxes: 100
  unpad_groundtruth_tensors: false
}
train_input_reader {
  label_map_path: "/content/dataset/label_map.pbtxt"
  tf_record_input_reader {
    input_path: "/content/dataset/train.record"
  }
}
eval_config {
  num_examples: 51
  metrics_set: "coco_detection_metrics"
  use_moving_averages: false
}
eval_input_reader {
  label_map_path: "/content/dataset/label_map.pbtxt"
  shuffle: false
  num_epochs: 1
  tf_record_input_reader {
    input_path: "/content/dataset/test.record"
  }
}
graph_rewriter {
  quantization {
    delay: 0
    weight_bits: 8
    activation_bits: 8
  }
}

解决方法

我想从这个模型中检测到的类别是车牌。 我使用的数据集将对象标记为 licence。 这是我手动创建的label_map.pbtxt....

%%file /content/dataset/label_map.pbtxt
item {
    id: 1
    name: 'license'
}

区别在于拼写错误的数据集中的 s 与 c - 应该是 licence，而不是 license。