Tensorflow对象检测配置文件文档 [英] Tensorflow object detection config files documentation

问题描述

我在Tensorflow中使用对象检测api 。我注意到几乎所有参数都通过配置文件。我找不到有关这些配置文件选项的任何文档或教程。

I am using the object detection api in tensorflow. I noticed that practically all parameters pass through the config file. I could not find any documentation or tutorial on the options for these config files though.

我知道在官方git中它们提供了配置文件列表，以了解他们的预训练模型，这可能会很有帮助，但不能涵盖所有内容情况，当然也不需要提供任何解释。

I know that in the official git they provide a list of config files for their pretrained models which could be very helpful but it does not cover every case and of course does not provide any explanation if needed.

例如，在 train_config 部分，这些选项很容易说明，但是尚不清楚其他选项的潜在存在性：

For example in train_config section there are some data augmentation options which are quite self explanatory but the potential existence of other options is unclear:

  data_augmentation_options {
    random_horizontal_flip {
    }
  }
  data_augmentation_options {
    ssd_random_crop {
    }
  }

有没有我可以参考的来源？例如，在此教程两个我不知道的额外选项（ batch_queue_capacity 和 prefetch_queue_capacity ）出现。在哪里可以找到一份不错的选择清单？我知道它是特定于模型的，但是其中一些是通用的并且确实有用。

Is there a source I could refer to? For example in this tutorial two extra options (batch_queue_capacity and prefetch_queue_capacity) I did not know about appear. Where could I find a decent list of options I have? I know that it's model specific but some of them are universal and really helpful.

推荐答案

如配置文档，配置文件只是协议缓冲区对象，该对象在.proto 文件中描述 https://github.com/tensorflow/models/tree/master/research/object_detection/protos rel = noreferrer> research / object_detection / protos 。顶级对象是TrainEvalPipelineConfig .proto rel = noreferrer> pipeline.proto ，不同的文件描述了每个元素。例如， data_augmentation_options 是 PreprocessingStep 对象。 /models/blob/master/research/object_detection/protos/preprocessor.proto rel = noreferrer> preprocessor.proto （依次包含适用于不同预处理任务的其他可能对象的范围）。每个对象和字段的含义可能显而易见，也可能没有明确记载，但是您始终可以参考源代码以确切地了解每个值的使用方式（例如，检查 preprocessor.py 了解如何完成数据扩充）。

As mentioned in the configuration documentation, configuration files are just Protocol Buffers objects described in the .proto files under research/object_detection/protos. The top level object is a TrainEvalPipelineConfig defined in pipeline.proto, and different files describe each of the elements. For example, data_augmentation_options are PreprocessingStep objects, defined in preprocessor.proto (which in turn can include a range of other possible objects for different preprocessing tasks). The meaning of each object and field may or may not be obvious or well-documented, but you can always refer to the source code to see exactly how each value is being used (for example, check preprocessor.py to understand how data augmentation is done).

这篇关于Tensorflow对象检测配置文件文档的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！