pointconv icon indicating copy to clipboard operation
pointconv copied to clipboard

cannot find rgb info in placeholder

Open iris0329 opened this issue 6 years ago • 0 comments

Hi, Thanks for sharing this work!

in the paper, you said, the input is six channels, x, y, z, r, g, b. but I find in the code, it's

   pointclouds_pl = tf.placeholder(tf.float32, shape=(batch_size, num_point, 3))

it seems the input is three channels?

Thanks!

iris0329 avatar Oct 14 '19 14:10 iris0329