I am trying to import the SUN RGB-D dataset into lmdb format so that caffe can train for the bounding box regression. I see for imagenet conversion, there is a file putting the filename and the class label on one row. How can I prepare the data so I can label an object by four point coordinates? There are about 10 objects recognized in the ground truth image, so one image should contain around 10 * 8 values for the regression result.
Asked
Active
Viewed 964 times
2
-
1Maybe you can follow this [question](http://stackoverflow.com/questions/38095280/how-to-predict-float-vector-labels-with-caffe/38137119#38137119) – Dale Jul 06 '16 at 02:18
-
Refer this site https://xiaoyuliu.github.io/2018/02/23/combine-datasets-into-lmdb-for-caffe/ – Surya Tej Jul 11 '18 at 10:03