nerf-pytorch

nerf-pytorch copied to clipboard

RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)`

1

HOW TO SOLVE THIS PROBLEM? Thanks.  

RyanCCC

Rendered depth video is black

8

I try to train a NeRF on the lego bulldozer scene, and although the RGB video comes out as expected, the depth video is just black. I'm using torch==1.8.1 and...

gkouros

A small bug

1

It may miss relu layer to the output of the alpha. In current implementation, the alpha can be negative!

Zhiyuan-R

Extracting geometry from a NeRF

6

In the tensorflow implementation, it has a function that the geometry of the scene can be extracted as cubes. https://github.com/bmild/nerf https://github.com/bmild/nerf/blob/master/extract_mesh.ipynb Is it also possible in this pytorch project？

KleinXin

c2w: what does the last operation mean?

1

`def pose_spherical(theta, phi, radius): c2w = trans_t(radius) # print(c2w) c2w = rot_phi(phi / 180. * np.pi) @ c2w # print(c2w) c2w = rot_theta(theta / 180. * np.pi) @ c2w #...

Junwei-LV

Could you please tell me how to use Colmap and LLFF codes to create my own real datasets?

Irina51244

RuntimeError: Function 'PowBackward0' returned nan values in its 0th output.

12

During the learning process, the following error occurs and learning is interrupted. ``` [TRAIN] Iter: 40300 Loss: 0.011321269907057285 PSNR: 23.059185028076172 11%|█████████████████████▎ 11%|█████████████████████▎ 11%|█████████████████████▎ 11%|█████████████████████▎ 11%|█████████████████████▎ 11%|█████████████████████▎ 11%|█████████████████████▎ 11%|█████████████████████▎ 11%|█████████████████████▎ 11%|█████████████████████▎...

m1kit

Hi, In **nerf-pytorch**, inappropriate dependency versioning constraints can cause risks. Below are the dependencies and version constraints that the project is using ``` torch==1.11.0 torchvision>=0.9.1 imageio imageio-ffmpeg matplotlib configargparse tensorboard>=2.0...

PyDeps

Scene with known camera poses

5

Hello, thank you for this project :) I got a problem while training on a scene. When I extracted the camera poses from COLMAP this is the output https://user-images.githubusercontent.com/19538303/142732551-c89f3ed4-06c9-4567-a4d4-d2d5e3272bd9.mp4 the...

mertkiray

Fixed issue #59 problem that someone have encountered. This problem is likely due to the ***nan*** value of `disp` after rendering.

Yuchen-Song