1.特征匹配任务:
Synthetic Shapes数据集下载:
注意:该数据集无需哪里下载,github:pytorch-superpoint可自行生成
MS COCO2014数据集下载:
$ wget -c http://images.cocodataset.org/zips/train2014.zip
$ wget -c http://images.cocodataset.org/zips/val2014.zip
$ wget -c http://images.cocodataset.org/zips/test2014.zip
$ wget -c http://images.cocodataset.org/annotations/annotations_trainval2014.zip
$ wget -c http://images.cocodataset.org/annotations/image_info_val2014.zip
$ wget -c http://images.cocodataset.org/annotations/image_info_test2014.zip
hpatches-sequences数据集:
~~$ wget -c http://icvl.ee.ic.ac.uk/vbalnt/hpatches/hpatches-sequences-release.tar.gz(无法访问,放弃)
https://aistudio.baidu.com/datasetdetail/107865(幸好,最后找到这里,可以下载了)
2.目标检测任务
COCO数据集:
$ wget -c http://images.cocodataset.org/zips/train2017.zip # --continue, 断点续传
$ wget -c http://images.cocodataset.org/zips/val2017.zip
$ wget -c http://images.cocodataset.org/zips/test2017.zip
$ wget -c http://images.cocodataset.org/annotations/annotations_trainval2017.zip