Tensorflow对象检测API [英] Tensorflow Object Detection API

问题描述

我决定深入研究ML，并且经过反复试验，能够使用TS的开始创建模型.

I decided to take a dip into ML and with a lot of trial and error was able to create a model using TS' inception.

要更进一步，我想使用其对象检测API .但是他们的输入准备指令引用了使用 Pascal VOC 2012 数据集，但我想在我自己的数据集上进行训练.

To take this a step further, I want to use their Object Detection API. But their input preparation instructions, references the use of Pascal VOC 2012 dataset but I want to do the training on my own dataset.

这是否意味着我需要将数据集设置为Pascal VOC或 Oxford IIT 格式?如果是，我该怎么做?

Does this mean I need to setup my datasets to either Pascal VOC or Oxford IIT format? If yes, how do I go about doing this?

如果没有(我的直觉是这种情况)，那么将TS对象检测与我自己的数据集一起使用的替代方案是什么?

If no (my instinct says this is the case), what are the alternatives of using TS object detection with my own datasets?

侧面说明: 我知道我训练有素的初始模型无法用于本地化，因为它具有分类器

对于仍希望实现这一目标的用户，这里是我要做的事情.

For those still looking to achieve this, here is how I went about doing it.

推荐答案

Tensorflow对象检测API中的培训工作希望获得TF Record文件，其中某些字段填充了地实数据.

The training jobs in the Tensorflow Object Detection API expect to get TF Record files with certain fields populated with groundtruth data.

您可以将数据设置为与Pascal VOC或Oxford-IIIT示例相同的格式，或者可以直接创建TFRecord文件而忽略XML格式.

You can either set up your data in the same format as the Pascal VOC or Oxford-IIIT examples, or you can just directly create the TFRecord files ignoring the XML formats.

在后一种情况下，create_pet_tf_record.py或create_pascal_tf_record.py脚本可能仍然有用，可以作为API希望看到的字段以及应该采用的格式的参考.当前，我们不提供通常创建这些TFRecord文件的工具，因此您将必须编写自己的文件.

In the latter case, the create_pet_tf_record.py or create_pascal_tf_record.py scripts are likely to still be useful as a reference for which fields the API expects to see and what format they should take. Currently we do not provide a tool that creates these TFRecord files generally, so you will have to write your own.

这篇关于Tensorflow对象检测API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！