flybiubiu

Skipping ERROR caught in nll = model.optimize_parameters(current_step): svd_cuda: the updating process of SBDSDC did not converge (error: 23)

3

Thx author!I train x4 is ok! But when I train x8: Skipping ERROR caught in nll = model.optimize_parameters(current_step): svd_cuda: the updating process of SBDSDC did not converge (error: 23) Python...

About train parameters

6

Thx author! This is a great work! I have some wrong with origin code First: what mean with train 4:Open train.py and modify user parameters in L22. L22????????? Second: With...

Abort Validate

1

This is a nice project!Thx! But I train it with original code(Validate is 0150.png,0300.png,0450.png-----,**not** 1501.png,1502.png---) **_return torch._C._nn.upsample_nearest2d(input, output_size, sfl[0], sfl[1]) RuntimeError: CUDA out of memory. Tried to allocate 7.08 GiB...

Thx author! In Paper,I find β is 0.2.But why this scaling parameter choose 0.2? This value 0.1 ?0.3?or more?

Can I train it with pytorch 1.2? Because I find MMSR project need pytorch 1.3~1.5. So, wheather pytorch 1.2 produce a error if I install pytorch 1.2??? Thx!

Thx author's nice work! One question is that the unit of translation error is meter？

显存不够

4

您好！感谢作者的开源！ 我在ixi_config.yaml里修改了batch_size 变小 但是1080ti显存还是不够，貌似batch_size这里不起作用

AttributeError: 'pyngp.Nerf' object has no attribute 'sharpness_threshold'

3

Nice Work!But I have a problem: Loss type: L2 ---------------------------------------------------- Scene: lego ************************************* IDX: 0 delta_phi: 8.140797565872028 delta_theta: 10.820093141330617 delta_psi: -10.48089103181714 delta_tx: 0.24528741576016583 delta_ty: 0.09526715962921517 delta_tz: 0.22406161059494684 12:25:40 SUCCESS Initialized...

too much floaters

2

https://github.com/SuLvXiangXin/zipnerf-pytorch/assets/20927755/b3db06b4-9aa2-4cd3-ad35-101555d14e75 Awesome work！ there is always too much floaters in rendered img. what should I do when I train my data? Thank you!