Tensorflow 对象检测服务

Question

我正在使用 tensorflow 对象检测 api. The problem with this api is that it exports frozen graph for inference. I can't use that graph for serving. So, as a work around I followed the tutorial here。但是当我尝试导出图表时出现以下错误：

InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:

Assign requires shapes of both tensors to match. lhs shape= [1024,4] rhs shape= [1024,8]

[[node save/Assign_258 (defined at /home/deploy/models/research/object_detection/exporter.py:67) = Assign[T=DT_FLOAT, _class=["loc:@SecondStageBoxPredictor/BoxEncodingPredictor/weights"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](SecondStageBoxPredictor/BoxEncodingPredictor/weights, save/RestoreV2/_517)]] [[{{node save/RestoreV2/_522}} = _SendT=DT_FLOAT, client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_527_save/RestoreV2", _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

错误表明图表中存在不匹配。一个可能的原因可能是我正在使用预训练图进行训练，它可能有 4 个分类，而我的模型有 8 个分类。（因此形状不匹配）。 deeplab model 和他们的解决方案也有类似的问题具体模型是用 --initialize_last_layer=False 和 --last_layers_contain_logits_only=False 参数开始训练。但是张量流对象检测没有那个参数。那么，我应该如何进行？此外，还有其他方法可以提供张量流对象检测 api 吗？

我的配置文件如下所示：

model {
  faster_rcnn {
    num_classes: 1
    image_resizer {
      fixed_shape_resizer {
        height: 1000
        width: 1000
        resize_method: AREA
      }
    }
    feature_extractor {
      type: "faster_rcnn_inception_v2"
      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: 0.00999999977648
        }
      }
    }
    first_stage_nms_score_threshold: 0.0
    first_stage_nms_iou_threshold: 0.699999988079
    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 {
        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: 0.0
        iou_threshold: 0.600000023842
        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: 8
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  optimizer {
    adam_optimizer {
      learning_rate {
        manual_step_learning_rate {
          initial_learning_rate: 0.00010000000475
          schedule {
            step: 40000
            learning_rate: 3.00000010611e-05
          }
        }
      }
    }
    use_moving_average: true
  }
  gradient_clipping_by_norm: 10.0
  fine_tune_checkpoint: "/home/deploy/models/research/object_detection/faster_rcnn_inception_v2_coco_2018_01_28/model.ckpt"
  from_detection_checkpoint: true
  num_steps: 60000
  max_number_of_boxes: 100
}
train_input_reader {
  label_map_path: "/home/deploy/models/research/object_detection/Training_carrot_060219/carrot_identify.pbtxt"
  tf_record_input_reader {
    input_path: "/home/deploy/models/research/object_detection/Training_carrot_060219/train.record"
  }
}
eval_config {
  num_visualizations: 100
  num_examples: 135
  eval_interval_secs: 60
  use_moving_averages: false
}
eval_input_reader {
  label_map_path: "/home/deploy/models/research/object_detection/Training_carrot_060219/carrot_identify.pbtxt"
  shuffle: true
  num_epochs: 1
  num_readers: 1
  tf_record_input_reader {
    input_path: "/home/deploy/models/research/object_detection/Training_carrot_060219/test.record"
  }
  sample_1_of_n_examples: 1
}

Answer 1

为 tf 服务导出模型时，配置文件和检查点文件应相互对应。

问题是在导出自定义训练模型时，您使用的是带有新检查点文件的旧配置文件。

Tensorflow 对象检测服务

Tensorflow object detection serving

object-detection

tensorflow