tensorflow - 为什么在我自己的数据集上使用 ssd_mobilenet_v1

问题描述

张量流 1.12.0

我目前正在尝试使用我的数据集训练 SSD_Mobilenet_V1_pnp 模型（使用 COCO 预训练）。我的数据集有 490 张用于训练的图像和 210 张用于评估的图像，23 个类

label_map.pbtxt：

项目 { id：1 名称：'a' } 项目 { id：2 名称：'b' }

...

管道配置：

model {
  ssd {
    num_classes: 24
    image_resizer {
      fixed_shape_resizer {
        height: 300
        width: 300
      }
    }
    feature_extractor {
      type: "ssd_mobilenet_v1_ppn"
      conv_hyperparams {
        regularizer {
          l2_regularizer {
            weight: 3.99999989895e-05
          }
        }
        initializer {
          random_normal_initializer {
            mean: 0.0
            stddev: 0.00999999977648
          }
        }
        activation: RELU_6
        batch_norm {
          decay: 0.97000002861
          center: true
          scale: true
          epsilon: 0.0010000000475
        }
      }
      override_base_feature_extractor_hyperparams: true
    }
    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
        use_matmul_gather: true
      }
    }
    similarity_calculator {
      iou_similarity {
      }
    }
    box_predictor {
      weight_shared_convolutional_box_predictor {
        conv_hyperparams {
          regularizer {
            l2_regularizer {
              weight: 3.99999989895e-05
            }
          }
          initializer {
            random_normal_initializer {
              mean: 0.0
              stddev: 0.00999999977648
            }
          }
          activation: RELU_6
          batch_norm {
            decay: 0.97000002861
            center: true
            scale: true
            epsilon: 0.0010000000475
            train: true
          }
        }
        depth: 512
        num_layers_before_predictor: 1
        kernel_size: 1
        class_prediction_bias_init: -4.59999990463
        share_prediction_tower: true
      }
    }
    anchor_generator {
      ssd_anchor_generator {
        num_layers: 6
        min_scale: 0.15000000596
        max_scale: 0.949999988079
        aspect_ratios: 1.0
        aspect_ratios: 2.0
        aspect_ratios: 0.5
        aspect_ratios: 3.0
        aspect_ratios: 0.333299994469
        reduce_boxes_in_lowest_layer: false
      }
    }
    post_processing {
      batch_non_max_suppression {
        score_threshold: 0.300000011921
        iou_threshold: 0.600000023842
        max_detections_per_class: 100
        max_total_detections: 100
      }
      score_converter: SIGMOID
    }
    normalize_loss_by_num_matches: true
    loss {
      localization_loss {
        weighted_smooth_l1 {
        }
      }
      classification_loss {
        weighted_sigmoid_focal {
          gamma: 2.0
          alpha: 0.75
        }
      }
      classification_weight: 1.0
      localization_weight: 1.5
    }
    encode_background_as_zeros: true
    normalize_loc_loss_by_codesize: true
    inplace_batchnorm_update: true
    freeze_batchnorm: false
  }
}
train_config {
  batch_size: 512
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  data_augmentation_options {
    ssd_random_crop {
    }
  }
  sync_replicas: true
  optimizer {
    momentum_optimizer {
      learning_rate {
        cosine_decay_learning_rate {
          learning_rate_base: 0.699999988079
          total_steps: 50000
          warmup_learning_rate: 0.13330000639
          warmup_steps: 2000
        }
      }
      momentum_optimizer_value: 0.899999976158
    }
    use_moving_average: false
  }
  fine_tune_checkpoint: "model.ckpt"
  num_steps: 50000
  startup_delay_steps: 0.0
  replicas_to_aggregate: 8
  max_number_of_boxes: 100
  unpad_groundtruth_tensors: false
  from_detection_checkpoint: true
}
train_input_reader {
  label_map_path: "annotations\label_map.pbtxt"
  tf_record_input_reader {
    input_path: "train.record"
  }
}
eval_config {
  num_examples: 210
  max_evals: 10
  metrics_set: "coco_detection_metrics"
  use_moving_averages: false
}
eval_input_reader {
  label_map_path: "annotations\label_map.pbtxt"
  shuffle: false
  num_epochs: 1
  num_readers: 1
  tf_record_input_reader {
    input_path: "val.record"
  }
}

火车：

python object_detection/model_main.py --logtostderr --pipeline_config_path=pipeline.config --model_dir=train

日志：

Accumulating evaluation results...
DONE (t=0.05s).
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000

这是正常的吗？怎么解决？

标签： tensorflowobject-detection

tensorflow - 为什么在我自己的数据集上使用 ssd_mobilenet_v1_pnp 的结果很差？

问题描述

解决方案

推荐阅读