Example render command in readme gives size mismatch error.

[andybak]

Note that I think this is different to #2 as I'm just trying to render the examples without training them. I might be misunderstanding though.

I've downloaded the dataset and pretrained checkpoints for Synthetic Nerf.

python train.py --config configs/lego.txt --ckpt checkpoints/lego.th --render_only 1 --render_test 1

gives

size mismatch for basis_mat.weight: copying a param with shape torch.Size([27, 288]) from checkpoint, the shape in current model is torch.Size([27, 864]).

[apchenstu]

the default configs correspond to the VM checkpoint, maybe you are using the CP checkpoints

[andybak]

Yep. I had to download this instead: https://onedrive.live.com/?authkey=%21AKpIQCzsxSTyFXA&id=C624178FAB774B7%21230&cid=0C624178FAB774B7

The readme is very unclear on what needs to be downloaded and what steps to follow. It might be worth spelling it out a bit more.

[rhmaaa]

Thanks. It is very useful.