Tensorflow object detection API not working even loss is low

Question

I want to create a model with tensorflow object detection API to detect card numbers in credit cards. So I prepare my dataset of cards about 50000 cards for training and 15000 cards for validation.My model is SSD_Mobilenet_V1_0.25_224 and I run training for 280K steps. Everything looks work fine my total_training_loss is below 1 about 0.8 and my validation_classification_loss is 0.7 and validation_localication_loss is about 0.02 and average_persion is 1.0. Here is my plots and they seem to be fine:

and here is my config :

# 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
}

Everything seems to be okey, but when I exported my model to tflite format and used on mobile devices it did not find any card number. And here is an example of my dataset :

Does my model seems to be overfitted ? And how can I solve the problem ?

Thanks!

Answer 1

Finally I find the solution, I change my config file to this and add more aspect_ratios, it leads into increasiong my model's weights in box prediction layers and also remove redundant aspect_ratios.

Here is my config file :

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
      }
    }

another problem I had was that I did not normalize input in android code so according to this file the SSD_MOBILENET will normalize input between range [-1,1] so I change my android code like this :

   @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;
    }

And finally it works !