项目解析-affnet项目

https://github.com/ducha-aiki/affnet

数据生成：

python -utt gen_ds.py

 

http://matthewalunbrown.com/patchdata/patchdata.html

http://phototour.cs.washington.edu/patches/default.htm

原始下载后 

其中一个解压：

生成后的样子：

生成流程：

affnet/gen_ds.py

affnet/dataset.py- class TripletPhotoTour(dset.PhotoTour):

python2.7/site-packages/torchvision/datasets/phototour.py-

class PhotoTour(data.Dataset):

    def __init__(self, root, name, train=True, transform=None, download=False):

        if download:
            self.download()

    def download(self):

        # process and save as torch files
        print('# Caching data {}'.format(self.data_file))

        dataset = (
            read_image_file(self.data_dir, self.image_ext, self.lens[self.name]),
            read_info_file(self.data_dir, self.info_file),
            read_matches_files(self.data_dir, self.matches_files)
        )

        with open(self.data_file, 'wb') as f:
            torch.save(dataset, f)

    mean = {'notredame': 0.4854, 'yosemite': 0.4844, 'liberty': 0.4437,
            'notredame_harris': 0.4854, 'yosemite_harris': 0.4844, 'liberty_harris': 0.4437}
    std = {'notredame': 0.1864, 'yosemite': 0.1818, 'liberty': 0.2019,
           'notredame_harris': 0.1864, 'yosemite_harris': 0.1818, 'liberty_harris': 0.2019}
    lens = {'notredame': 468159, 'yosemite': 633587, 'liberty': 450092,
            'liberty_harris': 379587, 'yosemite_harris': 450912, 'notredame_harris': 325295}
    image_ext = 'bmp'
    info_file = 'info.txt'
    matches_files = 'm50_100000_100000_0.txt'

def read_image_file(data_dir, image_ext, n):
    """Return a Tensor containing the patches
    """
    def PIL2array(_img):
        """Convert PIL image type to numpy 2D array
        """
        return np.array(_img.getdata(), dtype=np.uint8).reshape(64, 64)

    def find_files(_data_dir, _image_ext):
        """Return a list with the file names of the images containing the patches
        """
        files = []
        # find those files with the specified extension
        for file_dir in os.listdir(_data_dir):
            if file_dir.endswith(_image_ext):
                files.append(os.path.join(_data_dir, file_dir))
        return sorted(files)  # sort files in ascend order to keep relations

    patches = []
    list_files = find_files(data_dir, image_ext)

    for fpath in list_files:
        img = Image.open(fpath)
        for y in range(0, 1024, 64):
            for x in range(0, 1024, 64):
                patch = img.crop((x, y, x + 64, y + 64))
                patches.append(PIL2array(patch))
    return torch.ByteTensor(np.array(patches[:n]))


def read_info_file(data_dir, info_file):
    """Return a Tensor containing the list of labels
       Read the file and keep only the ID of the 3D point.
    """
    labels = []
    with open(os.path.join(data_dir, info_file), 'r') as f:
        labels = [int(line.split()[0]) for line in f]
    return torch.LongTensor(labels)


def read_matches_files(data_dir, matches_file):
    """Return a Tensor containing the ground truth matches
       Read the file and keep only 3D point ID.
       Matches are represented with a 1, non matches with a 0.
    """
    matches = []
    with open(os.path.join(data_dir, matches_file), 'r') as f:
        for line in f:
            l = line.split()
            matches.append([int(l[0]), int(l[3]), int(l[1] == l[4])])
    return torch.LongTensor(matches)

先重建出点云，点云中某个三维点可能对应多个2D点 

这个点云是来自项目：

http://phototour.cs.washington.edu/

info.txt 这个文件对应所有patchID的label

matches.append([int(l[0]), int(l[3]), int(l[1] == l[4])]) 

These are name "m50_n1_n2.txt" where n1 and n2 are the number of matches and non-matches present in the file. 

n1:100000  n2:100000 是指这个txt中匹配和不匹配的数目，该文件共有100000条

patchID1   3DpointID1   unused1   patchID2   3DpointID2   unused2

(patchID1, patchID2, (3DpointID1==3DpointID2)) 

"matches" have the same 3DpointID, and correspond to interest points that were detected with 5 pixels in position, and agreeing to 0.25 octaves of scale and pi/8 radians in angle. "non-matches" have different 3DpointID's, and correspond to interest points lying outside a range of 10 pixels in position, 0.5 octaves of scale and pi/4 radians in angle. 

patchID从0开始计

66！= 129

162 66 0 313 129 0 0

patch162 patch313

  

173088 67671 104 173089 67671 104 0

interest.txt

The first number is the ID of the reference image in which the interest point was found.

The other information in interest.txt is: x, y, orientation, scale (log2 units)  x,y,方向,尺度

 

---