使用tensorflow的object detection训练我的模型，ckpt文件的时间戳超过4小时没有变化

Question

我在 Windows 10 上使用 anaconda(python3.6) 和 tensorflow(1.9.0) 来训练我的模型。

我用这个命令训练模型：

python model_main.py --pipeline_config_path=training/ssd_mobilenet_v1_coco.config --model_dir=training/ --num_train_steps=500 --alsologtostderr

Anaconda 提示符输出以下信息。

在我的模型文件夹中，ckpt 文件的时间戳从未改变。

ssd_mobilenet_v1_coco.config 里面的内容是这样的：

# 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: 2
    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: 0.2
        max_scale: 0.95
        aspect_ratios: 1.0
        aspect_ratios: 2.0
        aspect_ratios: 0.5
        aspect_ratios: 3.0
        aspect_ratios: 0.3333
      }
    }
    image_resizer {
      fixed_shape_resizer {
        height: 300
        width: 300
      }
    }
    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: 1.0
      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: 1
  optimizer {
    rms_prop_optimizer: {
      learning_rate: {
        exponential_decay_learning_rate {
          initial_learning_rate: 0.004
          decay_steps: 800720
          decay_factor: 0.95
        }
      }
      momentum_optimizer_value: 0.9
      decay: 0.9
      epsilon: 1.0
    }
  }
  #fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
  #from_detection_checkpoint: true
  # 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: 100
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  data_augmentation_options {
    ssd_random_crop {
    }
  }
}

train_input_reader: {
  tf_record_input_reader {
    input_path:'data/train.record'
  }
  label_map_path:'data/side_vehicle.pbtxt'
}

eval_config: {
  num_examples: 8000
  # Note: The below line limits the evaluation process to 10 evaluations.
  # Remove the below line to evaluate indefinitely.
  max_evals: 10
}

eval_input_reader: {
  tf_record_input_reader {
    input_path: 'data/test.record'
  }
  label_map_path: 'data/side_vehicle.pbtxt'
  shuffle: false
  num_readers: 1
}

为什么模型文件的时间戳不变？哪里出错了？

当我使用这个命令训练时：

python model_main.py --pipeline_config_path=training/ssd_mobilenet_v1_coco.config --model_dir=training/ --num_train_steps=10000

错误信息是：

Traceback（最近一次调用最后一次）：文件 "E:\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", 第 1334 行，在 _do_call 返回 fn(*args) 文件 "E:\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", 第 1319 行，在 _run_fn 中 选项、feed_dict、fetch_list、target_list、run_metadata）文件“E:\Anaconda3\lib\site-packages\tensorflow\python\client\session.py”， 第 1407 行，在 _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.InvalidArgumentError： 断言失败：[最大框坐标值大于 1.100000：] [1.11401868] [[{{node ToAbsoluteCoordinates_1/Assert/AssertGuard/Assert}} = Assert[T=[DT_STRING, DT_FLOAT], summarize=3, _device="/job:localhost/replica:0/task:0/device:CPU:0 "](ToAbsoluteCoordinates_1/Assert/AssertGuard/Assert/Switch, ToAbsoluteCoordina tes_1/Assert/AssertGuard/Assert/data_0, ToAbsoluteCoordinates_1/Assert/AssertGuard/Assert/Switch_1)]]

Answer 1

现在我知道哪里错了。我的 tensorflow 版本是 1.9.0。我把tensorflow的版本改成1.12.0，然后修改了这个文件box_list_ops.py，设置check_range=False，问题就解决了。