Question

我想用tensorflow对象检测API创建一个模型来检测信用卡中的卡号。因此，我准备了大约50000张卡片用于训练和15000张卡片用于验证的卡片数据集。我的模型是SSD_Mobilenet_V1_0.25_224，我进行了280K步训练。我的total_training_loss低于1大约为0.8，我的validation_classification_loss为0.7，而validation_localication_loss大约为0.02，而average_persion为1.0，一切看起来都很好。这是我的情节，看起来还不错：

这是我的配置：

# SSD with Mobilenet v1 configuration for MSCOCO 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 {
  ssd {
    num_classes: 1
    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: 0.1
        max_scale: 0.95
        aspect_ratios: 1.0
        aspect_ratios: 3.0
        aspect_ratios: 6.0
        aspect_ratios: 9.0
        aspect_ratios: 10.32
        aspect_ratios: 11.96
        aspect_ratios: 12.06
        aspect_ratios: 13.9
        aspect_ratios: 12.96
        aspect_ratios: 14.71
        aspect_ratios: 13.65
        aspect_ratios: 16.27
        aspect_ratios: 17.73
        aspect_ratios: 18.68
        aspect_ratios: 16.74
        aspect_ratios: 14.91
        aspect_ratios: 13.33
        aspect_ratios: 10.67
        aspect_ratios: 10.5
        aspect_ratios: 10.26
        aspect_ratios: 10.81
        aspect_ratios: 10.31
        aspect_ratios: 11.05
        aspect_ratios: 11.52
        aspect_ratios: 11.0
        aspect_ratios: 12.58
        aspect_ratios: 12.12
        aspect_ratios: 12.8
        aspect_ratios: 13.97
        aspect_ratios: 13.34
        aspect_ratios: 13.45
      }
    }
    image_resizer {
      fixed_shape_resizer {
        height: 300
        width: 500
      }
    }
    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: 1
        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_v1'
      min_depth: 16
      depth_multiplier: 0.25
      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 {
        }
      }
      localization_loss {
        weighted_smooth_l1 {
        }
      }
      hard_example_miner {
        num_hard_examples: 3000
        iou_threshold: 0.99
        loss_type: CLASSIFICATION
        max_negatives_per_positive: 3
        min_negatives_per_image: 0
      }
      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: 64
  optimizer {
    rms_prop_optimizer: {
      learning_rate: {
        exponential_decay_learning_rate {
          initial_learning_rate: 0.004
          decay_steps: 5000
          decay_factor: 0.95
        }
      }
      momentum_optimizer_value: 0.9
      decay: 0.9
      epsilon: 1.0
    }
  }
  fine_tune_checkpoint: "/home/shayantabatabaei/Projects/CardScanner/NeuralNetwork/trainer/model/mobilenet_v1_0.25_224.ckpt"
  from_detection_checkpoint: 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: 450000
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  data_augmentation_options {
    ssd_random_crop {
    }
  }
}

train_input_reader: {
  tf_record_input_reader {
    input_path: "/home/shayantabatabaei/Projects/CardScanner/NeuralNetwork/dataset/images/train.record"
  }
  label_map_path: "/home/shayantabatabaei/Projects/CardScanner/NeuralNetwork/trainer/labelmap.pbtxt"
}

eval_config: {
  num_examples: 14000
  # Note: The below line limits the evaluation process to 10 evaluations.
  # Remove the below line to evaluate indefinitely.
  # max_evals: 10
  num_visualizations: 50
}

eval_input_reader: {
  tf_record_input_reader {
    input_path: "/home/shayantabatabaei/Projects/CardScanner/NeuralNetwork/dataset/images/test.record"
  }
  label_map_path: "/home/shayantabatabaei/Projects/CardScanner/NeuralNetwork/trainer/labelmap.pbtxt"
  shuffle: false
  num_readers: 1
}

一切似乎都很不错，但是当我将模型导出为tflite格式并在移动设备上使用时，找不到任何卡号。这是我的数据集的一个示例：

我的模型似乎过拟合了吗？而我该如何解决这个问题呢？

谢谢！

Answer 1

我能想到的一种解决方案是使用OCR从图像中检测文本并处理文本，对于上面的示例，当我们使用ocr时，输出为“•■4.1。111，; .. NOM DC＆IT CARD 744 -14ettiTh H40。 6274 1204 9777 4526 CVV2 427 99/03 w ww.enbank .ir“您可能需要提取“。”和“ cvv2”之间的数字。

查看在线OCR转换-https://www.onlineocr.net/

Answer 2

最后，我找到了解决方案，将配置文件更改为此，并添加了更多aspect_ratios，这增加了我在框预测层中模型的权重，还删除了多余的aspect_ratios。

这是我的配置文件：

anchor_generator {
      ssd_anchor_generator {
        num_layers: 6
        min_scale: 0.1
        max_scale: 0.95
        aspect_ratios: 1.0
        aspect_ratios: 1.5
        aspect_ratios: 2.0
        aspect_ratios: 2.5
        aspect_ratios: 3.0
        aspect_ratios: 3.5
        aspect_ratios: 4.0
        aspect_ratios: 4.5
        aspect_ratios: 5.0
        aspect_ratios: 5.5
        aspect_ratios: 6.0
        aspect_ratios: 6.5
        aspect_ratios: 7.0
        aspect_ratios: 7.5
        aspect_ratios: 8.0
        aspect_ratios: 8.5
        aspect_ratios: 9.0
        aspect_ratios: 9.5
        aspect_ratios: 10.0
        aspect_ratios: 10.5
        aspect_ratios: 11.0
        aspect_ratios: 11.5
        aspect_ratios: 12.0
        aspect_ratios: 12.5
        aspect_ratios: 13.0
        aspect_ratios: 13.5
        aspect_ratios: 14.0
        aspect_ratios: 14.5
        aspect_ratios: 15.0
        aspect_ratios: 15.5
        aspect_ratios: 16.0
        aspect_ratios: 16.5
        aspect_ratios: 17.0
        aspect_ratios: 17.5
        aspect_ratios: 18.0
        aspect_ratios: 18.5
        aspect_ratios: 19.0
        aspect_ratios: 19.5
        aspect_ratios: 20.0
        aspect_ratios: 20.5
        aspect_ratios: 21.0
      }
    }

我遇到的另一个问题是我没有规范化android代码中的输入，因此根据this file，SSD_MOBILENET将规范化范围为[-1,1]之间的输入，所以我这样更改了我的android代码：

   @Override
    protected void addPixelValue(int pixelValue) {
        imgData.putFloat(normalizeValue((pixelValue >> 16) & 0xFF));
        imgData.putFloat(normalizeValue((pixelValue >> 8) & 0xFF));
        imgData.putFloat(normalizeValue(pixelValue & 0xFF));
    }

    private float normalizeValue(float value) {
        return value * (2 / 255.0f) - 1.0f;
    }

终于可以了！

Tensorflow对象检测API即使丢失很低也无法正常工作

2 个答案: