低训练和验证损失，但Mapillary数据集上Faster R-CNN的mAP也很低

如何解决低训练和验证损失，但Mapillary数据集上Faster R-CNN的mAP也很低

我是深度学习的新手，我正在使用Tensorflow 2对象检测API来微调Mapillary数据集上的Faster R-CNN模型（在COCO 2017数据集上进行了预训练）以检测道路标志。该数据集包含训练集中的36589张图像（带有180287个边界框）和验证集中的5320张图像（带有26101个边界框）。

但是我正在经历一种怪异的行为：训练和验证损失似乎正在收敛（我也在尝试不同的学习率），但是mAP仍然为0。

通过使用以下配置：

# Faster R-CNN with resnet-50 (v1)
# Trained on COCO,initialized from Imagenet classification checkpoint

# This config is TPU compatible.

model {
  faster_rcnn {
    num_classes: 314
    image_resizer {
      keep_aspect_ratio_resizer {
        min_dimension: 1024
        max_dimension: 1024
        pad_to_max_dimension: true
      }
    }
    feature_extractor {
      type: 'faster_rcnn_resnet101_keras'
      batch_norm_trainable: false #fine-tuning: false | from-scratch: true
    }
    first_stage_anchor_generator {
      grid_anchor_generator {
        scales: [0.25,0.5,1.0,2.0]
        aspect_ratios: [0.5,2.0]
        height_stride: 16
        width_stride: 16
      }
    }
    first_stage_Box_predictor_conv_hyperparams {
      op: CONV
      regularizer {
        l2_regularizer {
          weight: 0.0 #no regularization?
        }
      }
      initializer {
        truncated_normal_initializer {
          stddev: 0.01
        }
      }
    }
    first_stage_nms_score_threshold: 0.0
    first_stage_nms_IoU_threshold: 0.7
    first_stage_max_proposals: 300
    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 {
        use_dropout: false
        dropout_keep_probability: 1.0
        fc_hyperparams {
          op: FC
          regularizer {
            l2_regularizer {
              weight: 0.0 #no regularization?
            }
          }
          initializer {
            variance_scaling_initializer {
              factor: 1.0
              uniform: true
              mode: FAN_AVG
            }
          }
        }
        share_Box_across_classes: false #it should'nt be needed in this case since a Box has only one class
      }
    }
    second_stage_post_processing {
      batch_non_max_suppression {
        score_threshold: 0.0
        IoU_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 300
      }
      score_converter: softmax #applies softmax on input detection scores
    }
    second_stage_localization_loss_weight: 2.0
    second_stage_classification_loss_weight: 1.0
    use_static_shapes: true
    use_matmul_crop_and_resize: true
    clip_anchors_to_image: true
    use_static_balanced_label_sampler: true
    use_matmul_gather_in_matcher: true
  }
}

train_config: {
  batch_size: 1
  sync_replicas: true
  startup_delay_steps: 0
  replicas_to_aggregate: 8
  num_steps: 10000
  optimizer {
    momentum_optimizer: {
      learning_rate: {
        cosine_decay_learning_rate {
          learning_rate_base: .0000004
          total_steps: 10000
          warmup_learning_rate: .000000133
          warmup_steps: 2000
        }
      }
      momentum_optimizer_value: 0.9
    }
    use_moving_average: false
  }

  add_regularization_loss: true
  fine_tune_checkpoint_version: V2
  fine_tune_checkpoint: "pretrained-model/faster_rcnn_resnet101_v1_1024x1024_coco17_tpu-8/checkpoint/ckpt-0"
  fine_tune_checkpoint_type: "detection"

#  data_augmentation_options {
#    random_horizontal_flip {
#    }
#  }
#  data_augmentation_options {
#    random_adjust_hue {
#    }
#  }
#  data_augmentation_options {
#    random_adjust_contrast {
#    }
#  }
#  data_augmentation_options {
#    random_adjust_saturation {
#    }
#  }
#  data_augmentation_options {
#     random_square_crop_by_scale {
#      scale_min: 0.6
#      scale_max: 1.3
#    }
#  }

  #merge_multiple_label_Boxes: false
  max_number_of_Boxes: 206388 #this is the total number considering the entire dataset
  unpad_groundtruth_tensors: false
  use_bfloat16: false  # works only on TPUs
}

train_input_reader: {
  label_map_path: "data/training/label_map.pbtxt"
  tf_record_input_reader {
    input_path: "data/training/train.tfrecord"
  }
}

eval_config: {
  min_score_threshold: 0.5
  batch_size: 1
  #num_examples: 100
  num_visualizations: 10
  metrics_set: "pascal_voc_detection_metrics"
  use_moving_averages: false
  eval_interval_secs: 30
  #max_evals: 10
  include_metrics_per_category: true
}

eval_input_reader: {
  label_map_path: "data/validation/label_map.pbtxt"
  shuffle: false
  num_epochs: 1
  tf_record_input_reader {
    input_path: "data/validation/train.tfrecord"
  }
}

我得到以下结果：

但所有mAP均为0（总计和每个类别）。

通过将学习率基数更改为.00000004并将预热学习率更改为.0000000133，将batch_size更改为8并将num_steps更改为50000，我得到以下结果（仍在训练中）：

按类别划分的性能全为0，但总体mAP似乎开始有所提高，但仍然很低：

我认为此行为可能是由某些错误的超参数引起的。我应该在配置文件中更改一些内容吗？您还认为两者之间最好的配置是什么？

注意：在使用整个数据集之前，我在非常小型数据集（具有较高的学习率）上训练了模型，并通过使用相同的数据集来评估模型，该模型表现良好（但可能太适合了）。打开整个数据集会导致这种奇怪的行为。