Tensorflow仅显示一个标签

Question

我将Tensorflow与Python 3.6和Anaconda 1.7.0结合使用。作为模型，我使用“faster_rcnn_inception_v2_pets”。

我用8个不同的类重新训练它，一切正常，对象预测（边界框）也是正确的，但问题是，Tensorflow总是只显示一个标签。例如，我正在训练探测器以区分几种车型（SUV，Coupe，Limousine，......）。因此它总是显示“SUV”标签。 同样奇怪的是，显示的标签始终是我列表中的第一个。因此，当例如“Coupe”写在我的labelmap的第一个位置时，预​​测的标签是“Coupe”标签。当“SUV”站在第一位时，它就是“SUV”标签。

可能是配置问题吗？或者也许培训期间的重量更多地放在第一个标签上？

谢谢你的帮助！

“faster_rcnn_inception_v2_pets”模型的配置代码：

model {
  faster_rcnn {
    num_classes: 8
    image_resizer {
      keep_aspect_ratio_resizer {
        min_dimension: 600
        max_dimension: 1024
      }
    }
    feature_extractor {
      type: 'faster_rcnn_inception_v2'
      first_stage_features_stride: 16
    }
    first_stage_anchor_generator {
      grid_anchor_generator {
        scales: [0.25, 0.5, 1.0, 2.0]
        aspect_ratios: [0.5, 1.0, 2.0]
        height_stride: 16
        width_stride: 16
      }
    }
    first_stage_box_predictor_conv_hyperparams {
      op: CONV
      regularizer {
        l2_regularizer {
          weight: 0.0
        }
      }
      initializer {
        truncated_normal_initializer {
          stddev: 0.01
        }
      }
    }
    first_stage_nms_score_threshold: 0.0
    first_stage_nms_iou_threshold: 0.7
    first_stage_max_proposals: 300
    first_stage_localization_loss_weight: 2.0
    first_stage_objectness_loss_weight: 1.0
    initial_crop_size: 14
    maxpool_kernel_size: 2
    maxpool_stride: 2
    second_stage_box_predictor {
      mask_rcnn_box_predictor {
        use_dropout: false
        dropout_keep_probability: 1.0
        fc_hyperparams {
          op: FC
          regularizer {
            l2_regularizer {
              weight: 0.0
            }
          }
          initializer {
            variance_scaling_initializer {
              factor: 1.0
              uniform: true
              mode: FAN_AVG
            }
          }
        }
      }
    }
    second_stage_post_processing {
      batch_non_max_suppression {
        score_threshold: 0.0
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 300
      }
      score_converter: SOFTMAX
    }
    second_stage_localization_loss_weight: 2.0
    second_stage_classification_loss_weight: 1.0
  }
}

train_config: {
  batch_size: 1
  optimizer {
    momentum_optimizer: {
      learning_rate: {
        manual_step_learning_rate {
          initial_learning_rate: 0.0002
          schedule {
            step: 900000
            learning_rate: .00002
          }
          schedule {
            step: 1200000
            learning_rate: .000002
          }
        }
      }
      momentum_optimizer_value: 0.9
    }
    use_moving_average: false
  }
  gradient_clipping_by_norm: 10.0
  fine_tune_checkpoint: "C:/Users/DS/Anaconda3/envs/tensorflow1/models/research/object_detection/faster_rcnn_inception_v2_coco_2018_01_28/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: 10000
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
}


train_input_reader: {
  tf_record_input_reader {
    input_path: "C:/Users/DS/Anaconda3/envs/tensorflow1/models/research/object_detection/train.record"
  }
  label_map_path: "C:/Users/DS/Anaconda3/envs/tensorflow1/models/research/object_detection/training/labelmap.pbtxt"
}

eval_config: {
  num_examples: 65
  # Note: The below line limits the evaluation process to 10 evaluations.
  # Remove the below line to evaluate indefinitely.
  max_evals: 10
}

eval_input_reader: {
  tf_record_input_reader {
    input_path: "C:/Users/DS/Anaconda3/envs/tensorflow1/models/research/object_detection/test.record"
  }
  label_map_path: "C:/Users/DS/Anaconda3/envs/tensorflow1/models/research/object_detection/training/labelmap.pbtxt"
  shuffle: false
  num_readers: 1
}