Tensorflow目标检测序列配置文件错误

Question

所以我尝试重新训练一个快速的对象检测模型，只使用一个类，我尝试在本地（在VM上）和通过ML引擎运行它。但是，我在train_config文件方面一直遇到相同的错误，这是对更快的_rcnn_resnet50_coco的改编。配置：

Traceback（最近一次调用）：File"/usr/lib/python2.7/runpy.py"，第174行，_run_module_as_mainmain，fname，loader，pkg_name）File"/usr/lib/python2.7/runpy.py"，第72行，_run_codeexec代码inrun_globalsFile"/root/.local/lib/python2.7/site-packages/trainer/task.py"，第171行，tf.app.run（main=main，Argv=[sys.argv[0]]unparse）File"/usr/local/lib/python2.7/dist-包/tensorflow/python/平台/app.py"，第125行，在运行_sys.exit（main（argv））File"/root/. place/lib/python2.7/site-包/trainer/task.py"，第142行，在主tf.estimator.train_and_evaluate（估计器，train_spec，eval_specs[0]）File"/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/training.py"，第471行，train_and_evaluate返回executor.run（）File"/usr/local/lib/python2.7/dist-包/tensorflow/python/估计器/training.py"，第637行，在run getattr（自我，task_to_run）（）File"/usr/local/lib/python2.7/dist-包/tenstorflow/python/估计器/training.py"，第674行，run_master。_start_distributed_training（saving_listeners=saving_listeners）File"/usr/local/lib/python2.7/dist-包/tenstorflow/python/估计器/training.py"，第788行，_start_distributed_trainingsaving_listeners=saving_listeners）File"/usr/local/lib/python2.7/dist-包/tenstorflow/python/估计器/estimator.py"，第354行，在火车损失=自。_train_model（input_fn，钩子，saving_listeners）File"/usr/local/lib/python2.7/dist-包/tenstorflow/python/估计器/estimator.py"，行_train_model_default（input_fn，钩子，saving_listeners）File"/usr/local/lib/python2.7/dist-包/tenstorflow/python/估计器/estimator.py"，行1234，_train_model_defaultinput_fn，model_fn_lib。ModeKeys.TRAIN））File"/usr/local/lib/python2.7/dist-包/tenstorflow/python/估计器/estimator.py"，第1075行，_get_features_and_labels_from_input_fn自己。_call_input_fn（input_fn，模式）File"/usr/local/lib/python2.7/dist-包/tenstorflow/python/估计器/estimator.py"，第1162行，_call_input_fn返回input_fn（**kwargs）File"/root/. local/lib/python2.7/site-pack/trainer/object_detection/inputs.py"，第375行，_train_input_fn提升TypeError（'对于训练模式，train_config必须是'TypeError：对于训练模式，train_config一定是train_pb2。TrainConfig.

我花了很长时间在配置文件中查找此问题的潜在原因，但我看不出问题出在哪里。除了TF源代码本身，似乎没有任何文档提到这一点。如有任何见解，将不胜感激！

    model {
  faster_rcnn {
    num_classes: 1
    image_resizer {
      fixed_shape_resizer {
        height: 600
        width: 205
      }
    }
    feature_extractor {
      type: 'faster_rcnn_resnet50'
      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: 5
  optimizer {
    momentum_optimizer: {
      learning_rate: {
        exponential_decay_learning_rate {
          initial_learning_rate: 0.0003
          decay_steps: 500
          decay_factor: 0.9
        }
      }
      momentum_optimizer_value: 0.9
    }
    use_moving_average: false
  }
  gradient_clipping_by_norm: 10.0
  fine_tune_checkpoint: "gs://ml-pipeline/checkpoints/fast_rcnn_resnet50/model.ckpt-5500"
  from_detection_checkpoint: true
  load_all_detection_checkpoint_vars: true
  num_steps: 2000
  data_augmentation_options {
    normalize_image {
    }
    random_pixel_value_scale {
    }
    random_adjust_brightness {
    }
    random_jitter_boxes {
    }
    random_pad_image {
    }
  }
  max_number_of_boxes: 35
}
train_input_reader: {
  tf_record_input_reader {
    input_path: "gs://ml-pipeline/data/tf-records/train.record"
  }
  label_map_path: "gs://ml-pipeline/story_label_map.pbtxt"
}
eval_config {
  num_examples: 54
  num_visualizations: 54
  eval_interval_secs: 10
  max_evals: 1
  #use_moving_averages: false
}
eval_input_reader: {
  tf_record_input_reader {
    input_path: "gs://ml-pipeline/data/tf-records/test.record"
  }
  label_map_path: "gs://ml-pipeline/story_label_map.pbtxt"
  shuffle: false
  num_readers: 1
}

Answer 1

我没发现这里有什么明显的问题。您可以为调试执行以下操作：

在此处添加打印类型（配置['train\u config']）和打印配置['train\u config']

让我知道打印的是什么？