K. S. Ernest (iFire) Lee

https://imgsli.com/ is very good for image comparisons.

Writing down an idea. It should be possible to go over the 10 million 3d item set and find a small set of items in a small set of classes...

I can't use shapenet, but I'm sure we can find 10 class of 100 models like Shapenet in that 10 million dataset.

I want to mention, getting the indices so they're in the right order and making sure they fit in the box and not inside out are problems too. If you're...

I was using the wrong strategy. You were using many same copies of the mesh and then some augments. I was doing the opposite.

Here's what I interpreted it. 1. model * multiple 2. model * multiple * augments You were doing 2000 (same) * 1 * 1. I was trying 1 * 2000...

https://github.com/lucidrains/meshgpt-pytorch/issues/11#issuecomment-1856353929 was the verification of z-y-x order and sort the faces as per their lowest vertex index. Note that I am using the convention that gives me that result like...

@MarcusLoppe on your branch, can you add a feature that on the first quit I save, on the second quit quit. Then, we can restart from a checkpoint.

@lucidrains from https://github.com/lucidrains/meshgpt-pytorch/commit/9cb9614e761fdd0c5f97bebaa78fc9d87b60f7f3 you mentioned inputing these features. I want to try running some samples in. Do you have any preference how to encode the samples from gltf models I...

So the mesh representation you want is ``` vertices = torch.randn((2, 121, 3)) # (batch, num vertices, coor (3)) faces = torch.randint(0, 121, (2, 64, 3)) # (batch, num faces,...