Closed qiminchen closed 2 years ago
@qiminchen could you explain this to me? I am also struggling to understand the tensor shape of the methods in the decoder.
@liopeer the input c
is of size (B, C, H_in, W_in, D_in)
and the query points vgrid
should be of size (B, num_points, 1, 1, 3)
, so theF.grid_sample(c, vgrid)
in line 63 will output the values of all the query points with size (B, num_points, 1, 1, 1)
, check F.grid_sample for more details.
Hi, I'm wondering what does these two lines do? so the input points to the decoder has a shape of
B x num_points x 3
and line 60 changes it toB x num_points x 1 x 1 x 3
? Also why do you need to normalize it from[0, 1]
to[-1, 1]
for the grip sampling? Thankshttps://github.com/autonomousvision/convolutional_occupancy_networks/blob/f44d413f8d455657a44c24d06163934c69141a09/src/conv_onet/models/decoder.py#L60-L61