[英]How do I train my own dataset on facebook/deepmask?
I am currently trying to add test images to facebook/deepmask so that I can train these images. 我目前正在尝试将测试图像添加到facebook / deepmask,以便可以训练这些图像。 Currently, the deepmask program uses CoCo images and annotations but I was wondering if it was possible for me to add my own images.
目前,deepmask程序使用CoCo图像和注释,但我想知道是否可以添加自己的图像。 The only reason is that I want to only train one type of image, which in this case is grapes.
唯一的原因是我只想训练一种图像,在这种情况下是葡萄。 I looked through the annotation file, but it is full of specs of the image.
我浏览了注释文件,但其中充满了图像的规格。 The only reason I am asking this question is because there were no tutorials/answers online for my specific problem.
我问这个问题的唯一原因是因为没有针对我的特定问题的在线教程/答案。
Here is the github to deepmask: https://github.com/facebookresearch/deepmask 这是要深度屏蔽的github: https : //github.com/facebookresearch/deepmask
Also, to download the annotation file for CoCo image use this command in the terminal: wget http://msvocds.blob.core.windows.net/annotations-1-0-3/instances_train-val2014.zip
另外,要下载CoCo图像的注释文件,请在终端中使用以下命令:
wget http://msvocds.blob.core.windows.net/annotations-1-0-3/instances_train-val2014.zip
Thank you everybody for your time! 谢谢大家的宝贵时间!
Stephen 斯蒂芬
My experience is the same: you should indeed dump your masks into a coco-style format. 我的经验是一样的:您确实应该将口罩转为可可风格。 It's json, and it is available here: coco dataset .
它是json,可在此处使用: coco数据集 。 My only comment is that coco uses a "costum Run Length Encoding (RLE)", that is explained nowhere.
我唯一的评论是,可可使用的是“ costum Run Length Encoding(RLE)”,没有说明。 Therefore it is easy to instead use a polygon encoding of the mask.
因此,很容易改为使用蒙版的多边形编码。 Therefore, do:
因此,请执行以下操作:
Hope this helps :-) 希望这可以帮助 :-)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.