013利用tensorflow目标检测接口实现SSD模型训练

模型训练主要采用model_main.py脚本,里面有要训练的SSD的框架，选择哪个模型以及模型需要的参数需要在配置文件中进行配置

进入models/research/object_detection/samples/configs下，里面是配置文件，config文件对应了我们想要的网络配置，选择ssd_resnet_fpn作为主干网络

因为没有专门的文件所以copy上述文件，将文件修改为针对人脸检测业务的配置文件

修改：

ssd {
     
    inplace_batchnorm_update: true
    freeze_batchnorm: false
    num_classes: 1#只进行人脸检测，定义为1，这里不包含背景
    box_coder {
     
      faster_rcnn_box_coder {
     
        y_scale: 10.0
        x_scale: 10.0
        height_scale: 5.0
        width_scale: 5.0
      }
    }

修改最后的文件路径：

train_input_reader: {
     
  tf_record_input_reader {
     
    input_path: "/Users/apple/Downloads/11人脸识别/数据集/widerface/tf-data/train.record"
  }
  label_map_path: "/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/models/research/object_detection/data/face_label_map.pbtxt"
}

eval_config: {
     
  metrics_set: "coco_detection_metrics"
  use_moving_averages: false
  num_examples: 8000
}

eval_input_reader: {
     
  tf_record_input_reader {
     
    input_path: "/Users/apple/Downloads/11人脸识别/数据集/widerface/tf-data/test.record"
  }
  label_map_path: "/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/models/research/object_detection/data/face_label_map.pbtxt"
  shuffle: false
  num_readers: 1
}

因为不使用预训练模型，所以将其注释：

train_config: {
     
  #fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
  batch_size: 64
  sync_replicas: true
  startup_delay_steps: 0
  replicas_to_aggregate: 8
  num_steps: 25000
  data_augmentation_options {
     
    random_horizontal_flip {
     
    }
  }

接下来进行模型训练：
打开终端进入reserch路径，也就是目标检测文件夹的上层路径，在终端执行时还要对相应的参数进行赋值，包括网络结构配置文件路径，生成的log日志，以及model对应的路径，训练的迭代次数，关于log配置的参数

python3 object_detection/model_main.py --pipeline_config_path=/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/models/research/object_detection/samples/configs/ssd_resnet50_v1_fpn_shared_box_predictor_640x640_coco14_sync_face.config --model_dir=/Users/apple/Downloads/11人脸识别/数据集/widerface/resnet50_fpn_model --num_train_steps=100000 --alsologtostder

然后运行就开始训练模型。

训练完成后生成pb文件：

python3 object_detection/export_inference_graph.py --input_type=image_tensor --pipeline_config_path=/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/models/research/object_detection/samples/configs/ssd_resnet50_v1_fpn_shared_box_predictor_640x640_coco14_sync_face.config --trained_checkpoint_prefix=/Users/apple/Downloads/11人脸识别/数据集/widerface/resnet50_fpn_model/model.ckpt-1 --output_directory=/Users/apple/Downloads/11人脸识别/数据集/widerface/resnet50_fpn_model/pb

分析源码：

ssd {
     
    inplace_batchnorm_update: true
    freeze_batchnorm: false
    num_classes: 1
    box_coder {
     
      faster_rcnn_box_coder {
     
        y_scale: 10.0#放大图片尺度，最终回归值变大，最终的loss也会变大
        x_scale: 10.0
        height_scale: 5.0
        width_scale: 5.0
      }
    }
#判断人脸框是否是真值，是正样本还是负样本,利用预测的人脸框同真实的人脸框进行比对，阈值大与0.5是正样本，小于0.5是负样本
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
      }
    }
#anchor
#根据不同的参数选择不同的bdnbox
 anchor_generator {
     
      multiscale_anchor_generator {
     
        min_level: 3
        max_level: 7
        anchor_scale: 4.0
        aspect_ratios: [1.0, 2.0, 0.5]#人脸长宽比：1:1，1:2，2:1三个尺寸
        scales_per_octave: 2
      }
    }
#图片大小，图片越小，时间越短，但输入图片越大越好，越大意味着保留了更多原始图片的信息
#640*640，512*512，384*384，这些尺寸都能整除128
image_resizer {
     
      fixed_shape_resizer {
     
        height: 640
        width: 640
      }
    }
#
 box_predictor {
     
 #定义卷积层共享参数
      weight_shared_convolutional_box_predictor {
     
        depth: 256#深度256
        class_prediction_bias_init: -4.6
        conv_hyperparams {
     
          activation: RELU_6,
          regularizer {
     
            l2_regularizer {
     
              weight: 0.0004
            }
          }
          initializer {
     
            random_normal_initializer {
     
              stddev: 0.01
              mean: 0.0
            }
          }
          batch_norm {
     
            scale: true,
            decay: 0.997,
            epsilon: 0.001,
          }
        }
        num_layers_before_predictor: 4#卷积核层数4层
        kernel_size: 3#卷积核大小3x3
      }
    }
#特征提取，主干网络层
feature_extractor {
     
      type: 'ssd_resnet50_v1_fpn'
      #fpn考虑层数为第三到第七
      fpn {
     
        min_level: 3
        max_level: 7
      }
      min_depth: 16#最小channel
      depth_multiplier: 1.0#网络宽度
      #卷积参数
      conv_hyperparams {
     
        activation: RELU_6,#relu激活函数
        regularizer {
     
        #l2正则
          l2_regularizer {
     
            weight: 0.0004
          }
        }
        initializer {
     
          truncated_normal_initializer {
     
            stddev: 0.03
            mean: 0.0
          }
        }
        batch_norm {
     
          scale: true,
          decay: 0.997,
          epsilon: 0.001,
        }
      }
      override_base_feature_extractor_hyperparams: true
    }

#loss
loss {
     
#分类的loss
      classification_loss {
     
        weighted_sigmoid_focal {
     
          alpha: 0.25
          gamma: 2.0
        }
      }
      #回归的loss
      localization_loss {
     
        weighted_smooth_l1 {
     
        }
      }
      classification_weight: 1.0
      localization_weight: 1.0
    }

#loss归一化参数
normalize_loss_by_num_matches: true
normalize_loc_loss_by_codesize: true

#优化器
optimizer {
     
    momentum_optimizer: {
     
      learning_rate: {
     
        cosine_decay_learning_rate {
     
          learning_rate_base: .04
          total_steps: 25000
          warmup_learning_rate: .013333
          warmup_steps: 2000
        }
      }
      momentum_optimizer_value: 0.9
    }
    use_moving_average: false
  }