About dataset

[June01]

Hi, bittnx I wondered how to merge the training data and testing data. I download the data from the official website, while the training and testing data is seperated. While in your code, I saw them was processed in a folder. trainSet = CmFile::loadStrList(wkDir + "ImageSets/Main/train.txt"); testSet = CmFile::loadStrList(wkDir + "ImageSets/Main/test.txt"); classNames = CmFile::loadStrList(wkDir + "ImageSets/Main/class.txt") I even could not find class.txt in all the folders. So when I do ./BING_linux , I met errors: Dataset:`/home/june/projects/VOC2007' with 0 training and 0 testing WinRecall.m Base = 2, W = 8, NSS = 2, perSz = 130 Invalidate CvMat data file /home/june/projects/VOC2007Results/ObjNessB2W8MAXBGR.xP What should I do next? Thank you very much.

[RyanCV]

The train.txt, test.txt and class.txt should be in the directory ~/ImageSets/Main/. If you didn't find them, make sure to download again from Mingming Cheng's website. 0 training and 0 testing means it didn't find the train.txt and test.txt. Another important thing is to check the format of .txt in linux. You can read this link:http://superuser.com/questions/294219/what-are-the-differences-between-linux-and-windows-txt-files-unicode-encoding.

[June01]

@RyanCV Hi, thanks to reply. When I works on opencv 3.0, I met problems in the issues before which cannot be solved. So, I change to opencv 2.4.9, while opencv_imgcodecs cannot be found. Could you tell me which subversion you use, such as 2.4.*?

[mtourne]

There is a bit of explanation missing on how to prep the vov2007 dataset for this.

More info can be found in this github below, and as mentionned before it's important to fix the endlines of ImageSets/Main/class.txt to be Unix and not Windows

https://github.com/varun-nagaraja/BING-Objectness

[bittnt]

For dataset preparation, check: http://kylezheng.org/objectproposal/