Question

我使用quick_rcnn_resnet101模型在我自己的数据上使用Tensorflow对象检测API。我从头开始训练。培训部分进展顺利，但评估部分从一开始就停滞不前，从未显示结果。它看起来像：

我尝试使用几个月前我在同一数据集上下载的旧版api。一切正常。当前版本的api有什么问题，特别是在评估部分吗？谢谢你的关注。

我的配置文件如下所示：

model {
  faster_rcnn {
    num_classes: 10
    image_resizer {
      keep_aspect_ratio_resizer {
        min_dimension: 600
        max_dimension: 1024
      }
    }
    feature_extractor {
      type: 'faster_rcnn_resnet101'
      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: 0.0003
          schedule {
            step: 0
            learning_rate: .0003
          }
          schedule {
            step: 900000
            learning_rate: .00003
          }
          schedule {
            step: 1200000
            learning_rate: .000003
          }
        }
      }
      momentum_optimizer_value: 0.9
    }
    use_moving_average: false
  }
  gradient_clipping_by_norm: 10.0
  #fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/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 {
    }
  }
}

train_input_reader: {
  tf_record_input_reader {
    input_path: "/PATH/TO/train.record"
  }
  label_map_path: "/PATH/TO/my_label_map.pbtxt"
}

eval_config: {
  num_examples: 2000
  # 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: "/PATH/TO/test.record"
  }
  label_map_path: "/PATH/TO/my_label_map.pbtxt"
  shuffle: false
  num_readers: 1
  num_epochs: 1
}

Answer 1

更快的R-CNN对象检测器需要花费更长的时间进行评估（与YOLO或SSD相比），这是因为更高的精度与速度之间的权衡。我建议将图像数量减少到5-10，以查看评估脚本是否产生输出。作为额外的检查，您可以通过在{val}配置中添加num_visualizations键来在张量板上可视化检测到的对象：

eval_config: {
  num_examples: 10
  num_visualizations: 10
  min_score_threshold: 0.15
  # Note: The below line limits the evaluation process to 10 evaluations.
  # Remove the below line to evaluate indefinitely.
  max_evals: 1
}

使用上述配置，您应该能够在Tensorboard中查看带有对象检测的images标签。请注意，我还将IoU阈值降低到0.15，以允许检测不太可靠的盒子。

Tensorflow对象检测API评估卡住了

1 个答案: