OpenLRM
OpenLRM copied to clipboard
3DTopia
An open-source impl. of Large Reconstruction Models
论文中说训练 我们在128个NVIDIA（40G）A100 GPU上以批次大小1024（每次迭代1024个不同形状）训练LRM 30个周期，大约需要3天时间完成。每个周期包含Objaverse的一份渲染图像数据和MV。 论文里使用的数据集allenai/objaverse 有好几个T 没有这么多a100， 一张a100训练少点数据可以么？
Hi ZexinHe, sorry to bother!. I have a question about training with .obj files. Is this possible? or if you can give a hint on how to. Thanks in advance!
I tried the blender_script.py,get the logs: ``Connected to pydev debugger (build 232.10227.11) =================== CYCLES =================== Data are loaded, start creating Blender stuff glTF import finished in 0.18s Failed to render...
Hi @ZexinHe , I wanted to run some metrics on a custom trained model, how do I do that, I tried using FID, but during inference I'm getting ply file...
Hi, Could you please provide some numbers around which GPUs, how many of them, and how many hours roughly were required to train these models?
Hi, could you provide the configuration files that you used to train the models that are made available on huggingface? I noticed that the one available in the repo refers...
1. Do we need to add 'views' folder as root path in training config (views folder has rgba and pose folders) or do we need to add models to directory...
## information ### device info * tested on Runpod GPU instance * A100 SXM 80GB x3, 96 vCPU 750 GB RAM * runpod/pytorch:2.2.0-py3.10-cuda12.1.1-devel-ubuntu22.04 ### data preparation * prepared 100 high...
## summary * error happens when training * tested on Runpod's A100 SXM 80GB x4 GPUs, 128 vCPU 1006 GB RAM * runpod/pytorch:2.2.0-py3.10-cuda12.1.1-devel-ubuntu22.04 ## reproduction of the error 1. installation...
I'm not able to install the following two libraries mathutils and bpy: For bpy it says: ERROR: No matching distribution found for bpy For mathutils it says: ERROR: Failed building...