instant_nsr_pl_colab not working

[fefespn]

anyone could use the instant_nsr_pl_colab ?? (regular colab not plus)

[EddieVec]

No, I get an error as it tries to load NerfAcc

`| Name | Type | Params

0 | cos | CosineSimilarity | 0 1 | model | NeuSModel | 7.7 M

7.7 M Trainable params 0 Non-trainable params 7.7 M Total params 15.371 Total estimated model params size (MB) 2023-10-29 15:46:47.850741: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2023-10-29 15:46:47.850798: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2023-10-29 15:46:47.850840: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2023-10-29 15:46:49.871923: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Epoch 0: : 0it [00:00, ?it/s]Update finite_difference_eps to 0.027204705103003882 ( ● ) NerfAcc: Setting up CUDA (This may take a few minutes the first time)^C`

[nsarafianos]

I had the same issues and after upgrading to colab plus it worked just fine, it goes past this step and shows the training w/ the epochs etc. It needs more memory (keep the GPU as is and increase the System RAM)

[camenduru]

please try the new version

[newsun-boki]

I met a problem when I used V100, when I run %cd /content/Wonder3D/instant-nsr-pl !python launch.py --config configs/neuralangelo-ortho-wmask.yaml --gpu 0 --train dataset.root_dir=/content/Wonder3D/outputs/cropsize-192-cfg3.0 dataset.scene=owl

it showed

/content/Wonder3D/instant-nsr-pl
Traceback (most recent call last):
  File "/content/Wonder3D/instant-nsr-pl/launch.py", line 125, in <module>
    main()
  File "/content/Wonder3D/instant-nsr-pl/launch.py", line 38, in main
    import datasets
  File "/content/Wonder3D/instant-nsr-pl/datasets/__init__.py", line 16, in <module>
    from . import blender, colmap, dtu, ortho
  File "/content/Wonder3D/instant-nsr-pl/datasets/blender.py", line 14, in <module>
    from models.ray_utils import get_ray_directions
  File "/content/Wonder3D/instant-nsr-pl/models/__init__.py", line 16, in <module>
    from . import nerf, neus, geometry, texture
  File "/content/Wonder3D/instant-nsr-pl/models/nerf.py", line 9, in <module>
    from models.utils import chunk_batch
  File "/content/Wonder3D/instant-nsr-pl/models/utils.py", line 10, in <module>
    import tinycudann as tcnn
  File "/usr/local/lib/python3.10/dist-packages/tinycudann/__init__.py", line 9, in <module>
    from tinycudann.modules import free_temporary_memory, NetworkWithInputEncoding, Network, Encoding
  File "/usr/local/lib/python3.10/dist-packages/tinycudann/modules.py", line 59, in <module>
    raise EnvironmentError(f"Could not find compatible tinycudann extension for compute capability {system_compute_capability}.")
OSError: Could not find compatible tinycudann extension for compute capability 70.

[legel]

Had the same problem with trying to run the Google Colab without upgrading to Colab Pro (not enough RAM). Then, had the same problem as @newsun-boki when trying to run on a V100. I can confirm that if you switch the GPU to a T4 instance, then there is no problem and things run!