tensorflow对象检测中的checkpoint_dir和fine_tune_checkpoint有啥区别？

Posted 2023-03-15

技术标签:

【中文标题】tensorflow对象检测中的checkpoint_dir和fine_tune_checkpoint有啥区别？【英文标题】：What is the difference between checkpoint_dir and fine_tune_checkpoint in tensorflow object detection?tensorflow对象检测中的checkpoint_dir和fine_tune_checkpoint有什么区别？ 【发布时间】：2020-04-12 16:04:18 【问题描述】：

我使用这个link 来学习 Windows 10 上的对象检测。

我准备了400张图片，分为两类（石头和汽车）。

然后我用这个命令训练：

cd E:\test\models-master\research\object_detection

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

在object_detection/model_main.py 中，我看到一个名为checkpoint_dir 的参数。

但是我不知道如何使用checkpoint_dir。如果我的模型训练到超过6000步，training文件夹如下图所示：

然后我停止训练模型。当我想继续训练时，如何设置checkpoint_dir？

我使用这个命令：

python model_main.py --pipeline_config_path=training/ssd_mobilenet_v1_coco.config -- model_dir=training/ --checkpoint_dir=training/ --num_train_steps=20000 --alsologtostderr

当我添加--checkpoint_dir=training/ 时，模型没有继续训练。为什么？如何使用--checkpoint_dir？

我从detection_model_zoo下载ssd_mobilenet_v1_coco_2018_01_28.tar.gz。

然后我将ssd_mobilenet_v1_coco_2018_01_28.tar.gz解压缩到文件夹object_detection/ssd_mobilenet_v1_coco_2018_01_28。

object_detection/ssd_mobilenet_v1_coco_2018_01_28 文件夹有这样的文件：

那么如何在training/ssd_mobilenet_v1_coco.config中使用fine_tune_checkpoint呢？

training/ssd_mobilenet_v1_coco.config 中的内容是这样的：

# 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: 10
  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: 'ssd_mobilenet_v1_coco_2018_01_28/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: 1000
  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

这两行对吗？

fine_tune_checkpoint: 'ssd_mobilenet_v1_coco_2018_01_28/model.ckpt'

from_detection_checkpoint: true

tensorflow对象检测中checkpoint_dir和fine_tune_checkpoint有什么区别？

【问题讨论】：

【参考方案1】：

checkpoint_dir 的功能从名字上看并不明显。此参数允许您提供模型的检查点，以便仅对其进行评估，无需任何培训。确实，如果你看到这个参数的帮助，你会得到 p>

包含检查点的目录的路径。如果checkpoint_dir 是提供，这个二进制文件在 eval-only 模式下运行，写入结果指标到model_dir。

另一方面，fine_tune_checkpoint 是不言自明的，确实可以让您提供一个检查点来进行微调。请注意，如果您不设置 fine_tune_checkpoint_type: "detection" 和 load_all_detection_checkpoint_vars: true，则不会恢复所有可能的（即现有和兼容的）变量。

【讨论】：

我从这个页面学到了一些微调：***.com/questions/56012092/…。该页面不建议使用load_all_detection_checkpoint_vars。我该怎么办？不要使用load_all_detection_checkpoint_vars？我认为这不是真的。例如，您可以在此处查看用于恢复 SSD 型号的代码：github.com/tensorflow/models/blob/master/research/… 具体请查看第 1332 行：github.com/tensorflow/models/blob/master/research/…

以上是关于tensorflow对象检测中的checkpoint_dir和fine_tune_checkpoint有啥区别？的主要内容，如果未能解决你的问题，请参考以下文章