问题训练更快rcnn tensorflow。检测率不好

Question

我正在尝试训练frcnn_resnet101_kitti检测一些食物马铃薯和鸡块。总数据大约为1200张图像，每张图像包含至少10张图片，每张图片共生产12000块鸡肉和土豆。 样本图像

从真实环境中标记图像以及单独的各个项目。训练为110k步，平均速率为0.14-0.4

pipeline.config

   model {
      faster_rcnn {
       num_classes: 4
       image_resizer {
         keep_aspect_ratio_resizer {
           min_dimension: 600
           max_dimension: 1987
         }
       }
       feature_extractor {
         type: "faster_rcnn_resnet101"
         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: 100
       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: 0.300000011921
           iou_threshold: 0.600000023842
           max_detections_per_class: 100
           max_total_detections: 100
         }
         score_converter: SOFTMAX
       }
       second_stage_localization_loss_weight: 2.0
       second_stage_classification_loss_weight: 1.0
     }
   }
   train_config {
     batch_size: 1
     data_augmentation_options {
       random_horizontal_flip {
       }
     }
     optimizer {
       momentum_optimizer {
         learning_rate {
           manual_step_learning_rate {
             initial_learning_rate: 9.99999974738e-05
             schedule {
               step: 0
               learning_rate: 9.99999974738e-05
             }
             schedule {
               step: 500000
               learning_rate: 9.99999974738e-06
             }
             schedule {
               step: 700000
               learning_rate: 9.99999997475e-07
             }
           }
         }
         momentum_optimizer_value: 0.899999976158
       }
       use_moving_average: false
     }
     gradient_clipping_by_norm: 10.0
     fine_tune_checkpoint: "home/kitti/model.ckpt"
     from_detection_checkpoint: true
     num_steps: 800000
   }
     train_input_reader {
       label_map_path: "home/kitti/kitti_label_map.pbtxt"
       tf_record_input_reader {
         input_path: "home/kitti/kitti_train.tfrecord"
       }
     }
     eval_config {
       num_examples: 500
       metrics_set: "coco_metrics"
       use_moving_averages: false
     }
     eval_input_reader {
       label_map_path: "home/kitti/kitti_label_map.pbtxt"
       tf_record_input_reader {
         input_path: "home/kitti/kitti_val.tfrecord"
       }
     }