-
Notifications
You must be signed in to change notification settings - Fork 78
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Use my own image for training #5
Comments
Did you manage to get it done? I am trying to use my own images as well. |
same here |
你成功完成了吗?我也在尝试使用我自己的图像 |
单独运行显示一个npz文件的代码已经能够顺利跑通了,但是如果要用我们自己的原始图片数据集,需要用他提供的一份转换代码,将原始的图片数据集转换成它代码里需要的npz格式,但是这个转换代码没有什么详细的说明,而且没有给出图像数据集应该具有的格式。然后这个报错是在运行转换代码的时候报的,应该是提示数据集格式有问题,缺少了一些关键的文件,但是我不是很清楚这个CamPose.inf是什么[捂脸] |
请问有没有尝试用nerfvis visualize npz file? 我用作者提供的npz file发现总是load 100%之后卡住,没法显示,除了chair那个可以,其他都不行 |
I want to use my own pictures to reconstruct the scene.
At present, I can use colmap to calculate the pose.I can calculate the pose from colmap and convert it to nex MPI( https://github.com/nex-mpi/nex-code )hwf_cxcy.npy and poses_ bounds.npy
Next, how do I make data sets for training? Is there any relevant code?
The text was updated successfully, but these errors were encountered: