David Ceka

I had a similar issue, you have to either delete all weights section in the json or assign a value to all of them (in this case 3)

@tfzhou Thanks for answering! We're also using another model which implements DeepLab and ResNet and we have good results with that, so I don't really know whats going on with...

> Turns out I was just using Brave (the web browser) with shields up which is on by default. It worked in Firefox so I tried in Brave with shields...

> > Hi, I have a video with 8000 frames and i would like to process it. Is it possible to set a target frames max? 8000 it's way too...

you need to check the data preparation part, there's a precise script that creates the transforms.json for you

> I tried `bakedangelo` in mipnerf360-byclce, and i set the [scene_scale](https://github.com/autonomousvision/sdfstudio/blob/370902a10dbef08cb3fe4391bd3ed1e227b5c165/nerfstudio/data/dataparsers/mipnerf360_dataparser.py#L54) in mipnerf 360 to make it learn the background mesh. And it only trained for 180k iters because of...

> I'm also facing the same issue for some scenes of my private dataset. The 'combined' list is empty instead of being Trimesh datatype. On a closer look, I found...

> I also encountered the same problem. After I trained bakedangelo, I encountered the same error when trying to extract mesh.AttributeError: 'list' object has no attribute 'merge_vertices' > > 1)...

> Hi, line 117 is just because the evaluation on all images is very slow. For the train test split, you need to check with data parser you used. >...

Ok, but by default in the sdfstudio-data parser train and validation splits DO everlap, right? in this part of the sdfstudio data parser there's this flag i found:  So,...