NeRF代码复现----Pytorch版（更新中）

顾默@

已于 2024-04-03 22:46:20 修改

阅读量745

点赞数 6

分类专栏： NeRF代码复现文章标签：图像处理

于 2024-03-28 22:24:42 首次发布

本文链接：https://blog.csdn.net/weixin_53765004/article/details/137125869

版权

在这里插入图片描述

进入github搜索代码https://github.com/yenchenlin/nerf-pytorch

在这里插入图片描述

可以加镜像源快速下载数据集

在这里插入图片描述

下载乐高和蕨类植物的数据集

在这里插入图片描述

出现以下错误

/home/uriky/anaconda3/envs/nerf-pytorch-master/lib/python3.7/site-packages/torch/cuda/init.py:145: UserWarning:
NVIDIA GeForce RTX 4060 Ti with CUDA capability sm_89 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_70.
If you want to use the NVIDIA GeForce RTX 4060 Ti GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/

warnings.warn(incompatible_device_warn.format(device_name, capability, " ".join(arch_list), device_name))
Traceback (most recent call last):
File “run_nerf.py”, line 878, in
train()
File “run_nerf.py”, line 570, in train
images, poses, render_poses, hwf, i_split = load_blender_data(args.datadir, args.half_res, args.testskip)
File “/home/uriky/nerf-pytorch-master/load_blender.py”, line 75, in load_blender_data
render_poses = torch.stack([pose_spherical(angle, -30.0, 4.0) for angle in np.linspace(-180,180,40+1)[:-1]], 0)
File “/home/uriky/nerf-pytorch-master/load_blender.py”, line 75, in
render_poses = torch.stack([pose_spherical(angle, -30.0, 4.0) for