search

leeyeehoo / CSRNet-pytorch

CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
642 stars 259 forks source link

Cannot build KDTree #81

Closed pongloongyeat closed 3 years ago

pongloongyeat commented 3 years ago

Hi, I cloned this repo and was looking through the codes and I tried running them but I cannot build the KDTree.

 in gaussian_filter_density(gt)
     10     leafsize = 2048
     11     # build kdtree
---> 12     tree = scipy.spatial.KDTree(pts.copy(), leafsize=leafsize)
     13     # query kdtree
     14     distances, locations = tree.query(pts, k=4)

~/.local/lib/python3.8/site-packages/scipy/spatial/kdtree.py in __init__(self, data, leafsize)
    242     def __init__(self, data, leafsize=10):
    243         self.data = np.asarray(data)
--> 244         self.n, self.m = np.shape(self.data)
    245         self.leafsize = int(leafsize)
    246         if self.leafsize < 1:

ValueError: not enough values to unpack (expected 2, got 0)

During debug I checked and found that pts.shape returned ().

pongloongyeat commented 3 years ago

Nevermind I fixed it. I don't know how but I did.