在Tensorlfow对象检测API中导出推理图时出错

嗨，我在做tensorflow object detection api。我已经按照仓库中的所有主要说明进行操作了，直到现在为止一切都很好，但是突然出现了一些奇怪的错误。我以前使用fast rcnn过，现在切换到ssd mobile v2 coco。

使用命令生成推理图时

python export_inference_graph.py --input_type image_tensor --pipeline_config_path training/faster_rcnn_inception_v2_pets.config --trained_checkpoint_prefix training/model.ckpt-10250 --output_directory inference_graph

我得到以下错误：

追溯（最近一次呼叫最近）：文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/client/session.py”，行1356，在_do_call中返回fn（ * args）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/client/session.py”，第1341行，位于_run_fn选项，feed_dict，fetch_list，target_list， run_metadata）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/client/session.py”，行1429，在_call_tf_sessionrun run_metadata中）tensorflow.python.framework.errors_impl .NotFoundError：在检查点[[{{node save / RestoreV2}}]]中找不到密钥转换/偏向

在处理上述异常期间，发生了另一个异常：

追溯（最近一次通话最近）：在还原{self中，文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/training/saver.py”，行1286。 saver_def.filename_tensor_name：save_path}）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/client/session.py”，行950，在运行run_metadata_ptr）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/client/session.py“，第1173行，在_run feed_dict_tensor中，选项，run_metadata）文件“ / home / user / anaconda3 / envs / my_env / lib / python3.6 / site-packages / tensorflow / python / client / session.py“，行1350，在_do_run run_metadata中）文件“ / home / user / anaconda3 / envs / my_env / lib / python3 .6 / site-packages / tensorflow / python / client / session.py“，第1370行，在_do_call中，抬高类型（e）（node_def，op，message）tensorflow.python.framework.errors_impl.NotFoundError：在检查点[[节点保存/ RestoreV2（在/home/user/anaconda3/envs/my_env/lib/python3.6/site-中定义包/object_detection/exporter.py:331）]]

'save / RestoreV2'的原始堆栈跟踪：tf.app.run（）中的文件“ export_inference_graph.py”，第162行，文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages /tensorflow/python/platform/app.py”，第40行，运行_run（main = main，argv = argv，flags_parser = _parse_flags_tolerate_undef）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/运行_run_main（main，args）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/absl/app.py”中的第299行，位于“ site-packages / absl / app.py”行中，在_run_main sys.exit（main（argv））文件“ export_inference_graph.py”中的第250行，在主write_inference_graph = FLAGS.write_inference_graph中的第158行中）文件“ / home / user / anaconda3 / envs / my_env / lib / python3 .6 / site-packages / object_detection / exporter.py”，第497行，在export_inference_graph中，write_inference_graph = write_inference_graph中）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py”中的行426，在_export_inference_graph training_checkpoint_prefix = checkpoint_to_use）文件“ / home / user / anaconda3 / envs / my_env / lib / python3.6 / site-packages / object_detection / exporter.py“，在write_graph_and_checkpoint tf.import_graph_def（inference_graph_def，name =”''）中的第331行，文件“ / home / user / anaconda3 / envs / my_env / lib / python3.6 / site-packages / tensorflow / python / util / deprecation.py“，第507行，在new_func中返回func（* args，** kwargs）文件” / home / user / anaconda3 / envs /my_env/lib/python3.6/site-packages/tensorflow/python/framework/importer.py“，第443行，在import_graph_def _ProcessNewOps（graph）文件中/home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/importer.py”，第236行，在_ProcessNewOps中，用于graph._add_new_tf_operations（compute_devices = False）：＃ pylint：disable =受保护的访问文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”，行3751，在_add_new_tf_operations中用于c_api_util中的c_op .new_tf_operations（self）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”，行3751，用于c_api_util.new_tf_operations中的c_op（ self）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”，行3641，位于_create_op_from_tf_operation ret = Operation（c_op，self）文件中“ / home / user / anaconda3 / envs / my_env / lib / python3。6 / site-packages / tensorflow / python / framework / ops.py“，第2005行，在初始化self._traceback = tf_stack.extract_stack（）

在处理上述异常期间，发生了另一个异常：

追溯（最近一次通话最近）：文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/training/saver.py”，行1296，在还原名称中_to_keys = object_graph_key_mapping （save_path）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/training/saver.py”，行1614，位于object_graph_key_mapping object_graph_string = reader.get_tensor（可跟踪。 OBJECT_GRAPH_PROTO_KEY）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/pywrap_tensorflow_internal.py”，在第678行，在get_tensor中，返回CheckpointReader_GetTensor（self，compat.as_bytes（tensor） ）tensorflow.python.framework.errors_impl.NotFoundError：在检查点找不到键_CHECKPOINTABLE_OBJECT_GRAPH

在处理上述异常期间，发生了另一个异常：

在export_inference_graph中，write_inference_graph = write_inference_graph中）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py”中的行426，在_export_inference_graph training_checkpoint_prefix = checkpoint_to_use）文件“ / home / user / anaconda3 / envs / my_env / lib / python3.6 / site-packages / object_detection / exporter.py“，行335，位于write_graph_and_checkpoint saver.restore（sess，trained_checkpoint_prefix）文件“ / home / user / anaconda3 / envs / my_env /lib/python3.6/site-packages/tensorflow/python/training/saver.py“，行1302，在还原错误中，“缺少变量名或其他图形键”）tensorflow.python.framework.errors_impl。 NotFoundError：从检查点还原失败。这很可能是由于检查点缺少变量名或其他图形键。请确保您没有更改基于检查点的预期图形。原始错误：

在检查点[[节点保存/恢复V2（在/home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py:331中定义）]中找不到关键转换/偏向

'save / RestoreV2'的原始堆栈跟踪：tf.app.run（）中的文件“ export_inference_graph.py”，第162行，文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages /tensorflow/python/platform/app.py”，第40行，运行_run（main = main，argv = argv，flags_parser = _parse_flags_tolerate_undef）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/运行_run_main（main，args）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/absl/app.py”中的第299行，位于“ site-packages / absl / app.py”行中，在_run_main sys.exit（main（argv））文件“ export_inference_graph.py”中的第250行，在主write_inference_graph = FLAGS.write_inference_graph中的第158行中）文件“ / home / user / anaconda3 / envs / my_env / lib / python3 .6 / site-packages / object_detection / exporter.py”，第497行，在export_inference_graph中，write_inference_graph = write_inference_graph中）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/object_detection/exporter.py”中的行426，在_export_inference_graph training_checkpoint_prefix = checkpoint_to_use）文件“ / home / user / anaconda3 / envs / my_env / lib / python3.6 / site-packages / object_detection / exporter.py“，在write_graph_and_checkpoint tf.import_graph_def（inference_graph_def，name =”''）中的第331行，文件“ / home / user / anaconda3 / envs / my_env / lib / python3.6 / site-packages / tensorflow / python / util / deprecation.py“，第507行，在new_func中返回func（* args，** kwargs）文件” / home / user / anaconda3 / envs /my_env/lib/python3.6/site-packages/tensorflow/python/framework/importer.py“，第443行，在import_graph_def _ProcessNewOps（graph）文件中/home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/importer.py”，第236行，在_ProcessNewOps中，用于graph._add_new_tf_operations（compute_devices = False）：＃ pylint：disable =受保护的访问文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”，行3751，在_add_new_tf_operations中用于c_api_util中的c_op .new_tf_operations（self）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”，行3751，用于c_api_util.new_tf_operations中的c_op（ self）文件“ /home/user/anaconda3/envs/my_env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”，行3641，位于_create_op_from_tf_operation ret = Operation（c_op，self）文件中“ / home / user / anaconda3 / envs / my_env / lib / python3。6 / site-packages / tensorflow / python / framework / ops.py“，第2005行，在初始化self._traceback = tf_stack.extract_stack（）

实际上，它一直在正确地工作，无法弄清楚现在发生了什么。我也尝试了快速的rcnn（它已经开始工作了），但是它也开始失败了。

这是配置文件。我目前正在为2个班级做它

# Faster R-CNN with Inception v2, configured for Oxford-IIIT Pets Dataset.
# Users should configure the fine_tune_checkpoint field in the train config as
# well as the label_map_path and input_path fields in the train_input_reader and
# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
# should be configured.

model {
  faster_rcnn {
    num_classes: 2
    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: 1
            learning_rate: .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: "/home/user/Downloads/Data_Science/Git/models/research/object_detection/faster_rcnn_inception_v2_coco_2018_01_28/model.ckpt"
  from_detection_checkpoint: true
  load_all_detection_checkpoint_vars: false
  # 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: "/home/user/Downloads/Data_Science/Git/models/research/object_detection/train.record"
  }
  label_map_path: "/home/user/Downloads/Data_Science/Git/models/research/object_detection/training/labelmap.pbtxt"
}

eval_config: {
  num_examples: 67
  # 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:/tensorflow1/models/research/object_detection/test.record"
  }
  label_map_path: "C:/tensorflow1/models/research/object_detection/training/labelmap.pbtxt"
  shuffle: false
  num_readers: 1
}

找到一个或2中github.But没有用的，类似的错误了。任何帮助将不胜感激。如果您需要更多信息，请发表评论。谢谢！