Giters

hzxie / Pix2Vox

The official implementation of "Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images". (Xie et al., ICCV 2019)

Home Page:https://haozhexie.com/project/pix2vox

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

voxel size

kaphleamrit2 opened this issue · comments

commented

I am trying to train my custom data. Voxel size of all of my binvox files are 256x256x256. I got the following errors:

ValueError: Using a target size (torch.Size([1, 256, 256, 256])) that is different to the input size (torch.Size([1, 32, 32, 32])) is deprecated. Please ensure they have the same size.

How can I train with 256 voxel size?

commented

You need to update the network architecture.

commented

I'm not sure whether the GPU memory is enough to generate 256^3 voxels.

commented

Thanks for the reply @hzxie . Any idea in which network and where architecture I need to update if I want to use higher voxel?

commented

Thanks for the reply @hzxie . Any idea in which network and where architecture I need to update if I want to use higher voxel?

Thanks, I have the same question，did you solve this problem?