获得可重现结果的问题，设置种子 Tensorflow 对象检测 API答案

【问题标题】：Problem with getting reproducible results, set seed Tensorflow object detection API获得可重现结果的问题，设置种子 Tensorflow 对象检测 API
【发布时间】：2021-04-02 10:49:30
【问题描述】：

我正在使用带有 tensorflow v1.12 的对象检测 API。我在获得可重现的结果时遇到了麻烦——每次运行我的代码时，我都会得到不同的结果。有没有办法在训练/预测级别设置随机种子？我尝试在 model_main.py 中设置种子，但没有帮助。

def main(unused_argv):
    tf.random.set_random_seed(1234)
    flags.mark_flag_as_required('model_dir')
    flags.mark_flag_as_required('pipeline_config_path')
    config = tf.estimator.RunConfig(model_dir=FLAGS.model_dir, tf_random_seed=1234)

我的 pipeline.config 供参考：

model {
  faster_rcnn {
    num_classes: 1
    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 {
        height_stride: 16
        width_stride: 16
        scales: 0.25
        scales: 0.5
        scales: 1.0
        scales: 2.0
        aspect_ratios: 0.5
        aspect_ratios: 1.0
        aspect_ratios: 2.0
      }
    }
    first_stage_box_predictor_conv_hyperparams {
      op: CONV
      regularizer {
        l2_regularizer {
          weight: 0.0
        }
      }
      initializer {
        truncated_normal_initializer {
          stddev: 0.0099999998
        }
      }
    }
    first_stage_nms_score_threshold: 0.0
    first_stage_nms_iou_threshold: 0.69999999
    first_stage_max_proposals: 100
    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 {
        fc_hyperparams {
          op: FC
          regularizer {
            l2_regularizer {
              weight: 0.0
            }
          }
          initializer {
            variance_scaling_initializer {
              factor: 1.0
              uniform: true
              mode: FAN_AVG
            }
          }
        }
        use_dropout: false
        dropout_keep_probability: 1.0
      }
    }
    second_stage_post_processing {
      batch_non_max_suppression {
        score_threshold: 0.30000001
        iou_threshold: 0.60000002
        max_detections_per_class: 100
        max_total_detections: 100
      }
      score_converter: SOFTMAX
    }
    second_stage_localization_loss_weight: 2.0
    second_stage_classification_loss_weight: 1.0
  }
}
train_config {
  batch_size: 1
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  optimizer {
    momentum_optimizer {
      learning_rate {
        manual_step_learning_rate {
          initial_learning_rate: 0.00030000001
          schedule {
            step: 814096
            learning_rate: 2.9999999e-05
          }
        }
      }
      momentum_optimizer_value: 0.89999998
    }
    use_moving_average: false
  }
  gradient_clipping_by_norm: 10.0
  fine_tune_checkpoint: "/home/kombajn/tensorflow/models/research/object_detection/2020_20_11/model_to_send/model.ckpt"
  from_detection_checkpoint: false
  num_steps: 30000
}
train_input_reader {
  label_map_path: "/home/kombajn/tensorflow/models/research/object_detection/2020_22_12_test/data/pack.pbtxt"
  tf_record_input_reader {
    input_path: "/home/kombajn/tensorflow/models/research/object_detection/2020_22_12_test/data/train.record"
  }
}
eval_config {
  num_examples: 100
  use_moving_averages: false
}
eval_input_reader {
  label_map_path: "/home/kombajn/tensorflow/models/research/object_detection/2020_22_12_test/data/pack.pbtxt"
  shuffle: false
  num_readers: 1
  tf_record_input_reader {
    input_path: "/home/kombajn/tensorflow/models/research/object_detection/2020_22_12_test/data/eval.record"
  }
}

【问题讨论】：

如果您可以在问题/答案中格式化代码，将会很有帮助。

标签： python tensorflow object-detection

【解决方案1】：

在 tensorflow 中获得可重复的结果是一个非常困难的问题。如果你在 Stack Overflow 上搜索，你会发现很多关于这个问题的问题。最重要的是，您必须追踪并播种运行在模型中或生成数据管道的方式中出现的每个随机源。这不是一件容易的事。例如权重初始化、随机数据生成器、dropout 层等。

【讨论】：