Zexin He

Hi @juanfraherrero, You can try decreasing the `frame_size` [here](https://github.com/3DTopia/OpenLRM/blob/3108b6902d27912e1dcdce76970eab51436f5b21/configs/infer-s.yaml#L6) and see if it still throws OOM error. If it still doesn't work, then I guess RTX1050 is not enough to...

> Just to clarify the blender_script.py works only for 1 object right? Can you please also tell the format of the json file that I have to mention in train...

Hi, Thanks to @RiccardoLincetto, it looks like you should run with blender cli to work. Plz refer to this https://github.com/3DTopia/OpenLRM/issues/44. The blender script [here](https://github.com/3DTopia/OpenLRM/blob/main/scripts/data/objaverse/blender_script.py) is designed to be used with...

Hi, It looks like some usage problem with `self.log_images` method. Could you plz provide more details about your environment? I don't see it a problem in mine.

One possible workaround here is to modify https://github.com/3DTopia/OpenLRM/blob/main/openlrm/runners/train/lrm.py#L418-L422. `self.log_images({ f'Images_split{split}/rendered': renders.unsqueeze(0), f'Images_split{split}/gt': gts.unsqueeze(0), f'Images_merged{split}': merged.unsqueeze(0), }, log_progress, {})` Just add an explicit empty `{}` to `self.log_images` method.

Hi, We are setting encoder freeze to be `False` by default, which means the encoder is trainable. We tried both freezing encoder and trainable encoder at earlier experiments and found...

Hi, Currently, the mesh exportation is using `trimesh` package, which automatically detects the type of file to export based on the extension. Have you tried changing `ply` to `glb` or...

Hi, You can simply change the model configs and dataset configs based on the differences described in the `model_card.md`. Here's an example.

Hi, I've updated some docs here https://github.com/3DTopia/OpenLRM/tree/main?tab=readme-ov-file#inference-on-trained-models. Plz try to use `python scripts/convert_hf.py --config convert.global_step=null`, which will convert the last training checkpoint by setting the `convert.global_step` to `null`.

@da2r-20 This is amazing! Thanks!