DETECTRON Mask_RCNN训练及使用

这个还可以关联pascal voc等等，但pascal voc主要是分割等，关键点的话就coco，posetrack

COCO数据集

下载：https://blog.csdn.net/u014734886/article/details/78830713

Setting Up Datasets

This directory contains symlinks to data locations.

Creating Symlinks for COCO

1.COCO 数据集文件结构如下

coco
|_ coco_train2014
|  |_ <im-1-name>.jpg
|  |_ ...
|  |_ <im-N-name>.jpg
|_ coco_val2014
|_ ...
|_ annotations
   |_ instances_train2014.json
   |_ ...

Symlink the COCO dataset:

ln -s /path/to/coco detectron/detectron/datasets/data/coco

2.否则，大概是这样。

mkdir -p detectron/detectron/datasets/data/coco
ln -s /media/vivian/资料/datesets/coco_train2014 detectron/detectron/datasets/data/coco/
ln -s /media/vivian/资料/datesets/coco_val2014 detectron/detectron/datasets/data/coco/
ln -s /media/vivian/资料/datesets/annotations detectron/detectron/datasets/data/coco/annotations

ln -s a/ b/      创建软连接 
rm -fr xxxx/ 加了个/ 这个是删除文件夹 
rm -fr xxxx 没有/ 这个是删除软链接

COCO Minival Annotations

Our custom minival and valminusminival annotations are available for download here. Please note that minival is exactly equivalent to the recently defined 2017 val set. Similarly, the union of valminusminival and the 2014 train is exactly equivalent to the 2017 train set. To complete installation of the COCO dataset, you will need to copy the minival and valminusminival json annotation files to the coco/annotations directory r