projection-conditioned-point-cloud-diffusion Dataset

Can you please mention how your dataset looks like. I am trying to implement your work [your code] But something is wrong with the way I downloaded dataset I guess. It's showing num_sample=0.

You work is amazing and I am working on a similar topic. Your reply will be helpful on this issue. thank you again.

Jul 12 '23 12:07 cv-chaitali

I am also facing the same issue. Have you found a solution to this ?

Aug 31 '23 05:08 surtantheta

I am also facing the same issue.

Sep 05 '23 08:09 gzgwink

i download the whole co3d dataset of category 'hydrant' [about 180+G], and the problem of 'num_sample=0' is gone. but I got a new error:

"/home/mldai/miniconda3/envs/pytorch3d/lib/python3.9/site-packages/pytorch3d/implicitron/dataset/frame_data.
py", line 671, in _load_images
    image_rgb *= fg_probability
TypeError: unsupported operand type(s) for *=: 'numpy.ndarray' and 'Tensor'

Sep 10 '23 04:09 RaccoonDML

fixed it by common issue #2 image_rgb = torch.from_numpy(load_image(self._local_path(path)))

Sep 10 '23 05:09 RaccoonDML

i download the whole co3d dataset of category 'hydrant' [about 180+G], and the problem of 'num_sample=0' is gone. but I got a new error:
"/home/mldai/miniconda3/envs/pytorch3d/lib/python3.9/site-packages/pytorch3d/implicitron/dataset/frame_data.
py", line 671, in _load_images
    image_rgb *= fg_probability
TypeError: unsupported operand type(s) for *=: 'numpy.ndarray' and 'Tensor'

I also download the whole co3d dataset of category 'hydrant',but this file size is 129 GB.

Sep 12 '23 01:09 gzgwink