-1

我想使用 ssd_mobilenet_v2_coco_2018_03_29 训练我的 tensorflow 对象检测模型。当我运行训练步骤时:

python object_detection/train.py --logtostderr--train_dir=train         
--pipeline_config_path=ssd_mobilenet_v2_coco_2018_03_29/pipeline.config

它抛出

Traceback (most recent call last):
File "object_detection/train.py", line 198, in <module>
tf.app.run()
File "/home/user/tensor/lib/python3.5/site- 
packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
 File "object_detection/train.py", line 143, in main
model_config, train_config, input_config = 
get_configs_from_pipeline_file()
File "object_detection/train.py", line 103, in 
get_configs_from_pipeline_file
text_format.Merge(f.read(), pipeline_config)
File "/home/user/tensor/lib/python3.5/site- 
packages/google/protobuf/text_format.py", line 536, in Merge
descriptor_pool=descriptor_pool)
File "/home/user/tensor/lib/python3.5/site- 
packages/google/protobuf/text_format.py", line 590, in MergeLines
return parser.MergeLines(lines, message)
File "/home/user/tensor/lib/python3.5/site- 
packages/google/protobuf/text_format.py", line 623, in MergeLines
 self._ParseOrMerge(lines, message)
File "/home/user/tensor/lib/python3.5/site- 
packages/google/protobuf/text_format.py", line 638, in _ParseOrMerge
self._MergeField(tokenizer, message)
File "/home/user/tensor/lib/python3.5/site- 
packages/google/protobuf/text_format.py", line 763, in _MergeField
merger(tokenizer, message, field)
File "/home/user/tensor/lib/python3.5/site- 
packages/google/protobuf/text_format.py", line 837,in _ 

google.protobuf.text_format.ParseError: 80:7 : Message type 
"object_detection.protos.SsdFeatureExtractor" has no field named 
 "use_depthwise".

我的配置文件:


model {
  ssd {
    num_classes: 2
    box_coder {
      faster_rcnn_box_coder {
        y_scale: 10.0
        x_scale: 10.0
        height_scale: 5.0
        width_scale: 5.0
      }
    }
    matcher {
      argmax_matcher {
        matched_threshold: 0.5
        unmatched_threshold: 0.5
        ignore_thresholds: false
        negatives_lower_than_unmatched: true
        force_match_for_each_row: true
      }
    }
    similarity_calculator {
      iou_similarity {
      }
    }
    anchor_generator {
      ssd_anchor_generator {
        num_layers: 6
        min_scale: 0.2
        max_scale: 0.95
        aspect_ratios: 1.0
        aspect_ratios: 2.0
        aspect_ratios: 0.5
        aspect_ratios: 3.0
        aspect_ratios: 0.3333
      }
    }
    image_resizer {
      fixed_shape_resizer {
        height: 300
        width: 300
      }
    }
    box_predictor {
      convolutional_box_predictor {
        min_depth: 0
        max_depth: 0
        num_layers_before_predictor: 0
        use_dropout: false
        dropout_keep_probability: 0.8
        kernel_size: 3
        box_code_size: 4
        apply_sigmoid_to_scores: false
        conv_hyperparams {
          activation: RELU_6,
          regularizer {
            l2_regularizer {
              weight: 0.00004
            }
          }
          initializer {
            truncated_normal_initializer {
              stddev: 0.03
              mean: 0.0
            }
          }
          batch_norm {
            train: true,
            scale: true,
            center: true,
            decay: 0.9997,
            epsilon: 0.001,
          }
        }
      }
    }
    feature_extractor {
      type: 'ssd_mobilenet_v2'
      min_depth: 16
      depth_multiplier: 1.0
      use_depthwise: true
      conv_hyperparams {
        activation: RELU_6,
        regularizer {
          l2_regularizer {
            weight: 0.00004
          }
        }
        initializer {
          truncated_normal_initializer {
            stddev: 0.03
            mean: 0.0
          }
        }
        batch_norm {
          train: true,
          scale: true,
          center: true,
          decay: 0.9997,
          epsilon: 0.001,
        }
      }
    }
    loss {
      classification_loss {
        weighted_sigmoid {
                anchorwise_output: true
        }
      }
      localization_loss {
        weighted_smooth_l1 {
                anchorwise_output: true
        }
      }
      hard_example_miner {
        num_hard_examples: 3000
        iou_threshold: 0.99
        loss_type: CLASSIFICATION
        max_negatives_per_positive: 3
        min_negatives_per_image: 3
      }
      classification_weight: 1.0
      localization_weight: 1.0
    }
    normalize_loss_by_num_matches: true
    post_processing {
      batch_non_max_suppression {
        score_threshold: 1e-8
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 100
      }
      score_converter: SIGMOID
    }
  }
}

train_config: {
  batch_size: 24
  optimizer {
    rms_prop_optimizer: {
      learning_rate: {
        exponential_decay_learning_rate {
          initial_learning_rate: 0.004
          decay_steps: 800720
          decay_factor: 0.95
        }
      }
      momentum_optimizer_value: 0.9
      decay: 0.9
      epsilon: 1.0
    }
  }
  fine_tune_checkpoint: "ssd_mobilenet_v2_coco_2018_03_29/model.ckpt"
  num_steps: 2000
  fine_tune_checkpoint_type: "detection"
}
train_input_reader {
  label_map_path: "ssd_mobilenet_v2_coco_2018_03_29/label_map.pbtxt"
  tf_record_input_reader {
    input_path: "data/train.record"
  }
}
eval_config {
  num_examples: 8000
  max_evals: 10
  use_moving_averages: false
}
eval_input_reader {
  label_map_path: "ssd_mobilenet_v2_coco_2018_03_29/label_map.pbtxt"
  shuffle: false
  num_readers: 1
  tf_record_input_reader {
    input_path: "data/val.record"
  }
}

在这里,我使用了 2 个类。我从https://github.com/tensorflow/models/blob/master/research/object_detection/samples/configs/ssd_mobilenet_v2_coco.config复制了配置文件 我的 Tensorflow 版本:1.12.0 protobuf:3.6.1

4

1 回答 1

0

如果您编译的原型来自旧版本,则可能会发生这种情况。确保您的 proto 文件(在 /proto 下)是最新的,然后按照以下步骤重新编译它们:

cd path/to/models/research/
protoc object_detection/protos/*.proto --python_out=.

重新编译原型后再次尝试训练。

于 2019-02-06T14:52:42.443 回答