Pytorch3D error on running optimize_to_joints.py

[dishitamidha]

Hey, I am facing the following error while running optimize_to_joints.py. I have followed all the instructions exactly as described but I am still facing this issue. Kindly help out.

100% 1/1 [00:00<00:00, 4.07it/s] Dataset size: 1 0% 0/150 [00:00<?, ?it/s] Traceback (most recent call last): File "smal_fitter/optimize_to_joints.py", line 149, in <module> main() File "smal_fitter/optimize_to_joints.py", line 123, in main loss, losses = model(batch_range, opt_weight, stage_id) File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) File "/content/drive/MyDrive/Jio/SMALify/smal_fitter/smal_fitter.py", line 134, in forward rendered_silhouettes, rendered_joints = self.renderer( File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) File "/content/drive/MyDrive/Jio/SMALify/smal_fitter/p3d_renderer.py", line 68, in forward proj_points = self.cameras.transform_points_screen(points, screen_size)[:, :, [1, 0]] File "/usr/local/lib/python3.8/dist-packages/pytorch3d/renderer/cameras.py", line 353, in transform_points_screen points_ndc = self.transform_points_ndc(points, eps=eps, **kwargs) File "/usr/local/lib/python3.8/dist-packages/pytorch3d/renderer/cameras.py", line 323, in transform_points_ndc return world_to_ndc_transform.transform_points(points, eps=eps) File "/usr/local/lib/python3.8/dist-packages/pytorch3d/transforms/transform3d.py", line 400, in transform_points points_out = points_out[..., :3] / denom RuntimeError: The size of tensor a (3) must match the size of tensor b (2) at non-singleton dimension 2

[mshooter]

@dishitamidha what solved for me is: proj_points = self.cameras.transform_points_screen(points, image_size=screen_size)[:, :, [1, 0]]

[yichuan1998]

@dishitamidha what solved for me is: proj_points = self.cameras.transform_points_screen(points, image_size=screen_size)[:, :, [1, 0]]

Hi, thanks for your code. I changed the IMAGE_RANGE in config.py from range(0,1) to range(0, 20) for training on 20 frames and got this error. Could you help me with that? Thanks!