假设我训练了一个像ResNet这样的预训练网络，并在pipeline.config file属性中将其设置为detection。据我所知，这意味着我们获取模型的预训练权重。除了分类和盒预测头之外。此外，这意味着我们可以创建我们自己的标签类型，然后将作为分类和框预测头产生我们想要的模型创造/训练。
现在，假设我训练了这个网络25000步，并希望以后继续训练，而模型不会忘记任何东西，我应该将pipeline.config中的fine_tune_checkpoint_type更改为full，以便继续训练（当然，还要加载正确的检查点文件），还是仍然将其设置为detection？
编辑：
这基于https://github.com/tensorflow/models/blob/master/research/object_detection/protos/train.proto中的信息：

//   1. "classification": Restores only the classification backbone part of
  //        the feature extractor. This option is typically used when you want
  //        to train a detection model starting from a pre-trained image
  //        classification model, e.g. a ResNet model pre-trained on ImageNet.
  //   2. "detection": Restores the entire feature extractor. The only parts
  //        of the full detection model that are not restored are the box and
  //        class prediction heads. This option is typically used when you want
  //        to use a pre-trained detection model and train on a new dataset or
  //        task which requires different box and class prediction heads.
  //   3. "full": Restores the entire detection model, including the
  //        feature extractor, its classification backbone, and the prediction
  //        heads. This option should only be used when the pre-training and
  //        fine-tuning tasks are the same. Otherwise, the model's parameters
  //        may have incompatible shapes, which will cause errors when
  //        attempting to restore the checkpoint.

因此，classification只提供了特征提取器的分类 Backbone.js 部分，这意味着模型将在网络的许多部分从头开始。
detection恢复了整个特征提取器，但是"最终结果"将被遗忘，这意味着我们可以添加自己的类，并从头开始学习这些分类。
full恢复所有内容，甚至包括类和盒预测权重。不过，只要我们不添加或删除任何类/标签，这就可以了。
是这样吗？