Question

我试图在GitHub上关注TensorFlow的对象检测示例。我成功训练了我的模型，但是当我试图评估我的模型时，无论是在我的本地机器上运行还是谷歌云端的ML引擎，我都遇到了错误。

    Traceback (most recent call last): 
    File "/usr/lib/python2.7/runpy.py", line 162, 
in _run_module_as_main "__main__", fname, loader, pkg_name) 
    File "/usr/lib/python2.7/runpy.py", line 72, in _run_code exec code 
in run_globals File "/root/.local/lib/python2.7/site-packages/object_detection/eval.py", line 130, in <module> tf.app.run() 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 44, 
in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "/root/.local/lib/python2.7/site-packages/object_detection/eval.py", line 117, 
in main label_map = label_map_util.load_labelmap(input_config.label_map_path) 
    File "/root/.local/lib/python2.7/site-packages/object_detection/utils/label_map_util.py", line 122, 
in load_labelmap label_map.ParseFromString(label_map_string) DecodeError: Error parsing message

我使用以下内容在云平台上进行评估;

gcloud ml-engine jobs submit training `whoami`_object_detection_eval_`date +%s`
    --job-dir=gs://poochie/training
    --packages /home/User/Downloads/models-master/research/dist/object_detection-0.1.tar.gz,/home/User/Downloads/models-master/research/slim/dist/slim-0.1.tar.gz
    --module-name object_detection.eval
    --region europe-west1
    --scale-tier BASIC_GPU
    --
    --checkpoint_dir=gs://poochie/training
    --eval_dir=gs://poochie/eval
    --pipeline_config_path=gs://poochie/dogs.config

基于;

gcloud ml-engine jobs submit training `whoami`_object_detection_eval_`date +%s` \
    --job-dir=${YOUR_GCS_BUCKET}/train \
    --packages dist/object_detection-0.1.tar.gz,slim/dist/slim-0.1.tar.gz \
    --module-name object_detection.eval \
    --region us-central1 \
    --scale-tier BASIC_GPU \
    -- \
    --checkpoint_dir=${YOUR_GCS_BUCKET}/train \
    --eval_dir=${YOUR_GCS_BUCKET}/eval \
    --pipeline_config_path=${YOUR_GCS_BUCKET}/data/${CONFIG_FILE}

培训包含我在火车过程中的检查点

eval是评估过程输出的空文件

dogs.config

    # 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: 1
    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: 0
            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: "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: "gs://poochie/train.record"
  }
  label_map_path: "gs://poochie/labelmap.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: "gs://poochie/valid.record"
  }
  label_map_path: "gs://poochie/labelmap.pbtxt"
  shuffle: false
  num_readers: 1
}

labelmap.pbtxt

{
  "affenpinscher": 1
}

编辑我将标签贴图更改为

item {
  id: 1
  name: 'affenpinscher'
}

它解决了这个问题。

Answer 1

调用.ParseFromString（...）时，可能超出了输入流的大小。如果是这种情况，您可以尝试修复此问题并通过执行以下操作在本地运行：

export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python

在运行tensorflow之前。

Answer 2

gs：//poochie/labelmap.pbtxt似乎存在语法错误。你介意分享吗？

DecodeError：在评估tensorflow对象检测api示例时解析消息时出错

2 个答案: