search

NVlabs / instant-ngp

Instant neural graphics primitives: lightning fast NeRF and more
https://nvlabs.github.io/instant-ngp
Other
16k stars 1.93k forks source link

'std::runtime_error' #1430

Open hnj5247 opened 1 year ago

hnj5247 commented 1 year ago

(python3.6) nvidia@jetson-desktop:~/project/a/instant-ngp$ ./instant-ngp data/nerf/fox 00:43:35 SUCCESS Initialized CUDA 10.2. Active GPU is #0: NVIDIA Tegra X2 [62] 00:43:35 INFO Loading NeRF dataset from 00:43:35 INFO data/nerf/fox/transforms.json 00:43:36 SUCCESS Loaded 50 images after 0s 00:43:36 INFO cam_aabb=[min=[1.0229,-1.33309,-0.378748], max=[2.46175,1.00721,1.41295]] 00:43:37 INFO Loading network config from: ./configs/nerf/base.json 00:43:37 INFO 1 00:43:37 INFO GridEncoding: Nmin=16 b=2.43803 F=4 T=2^19 L=8 00:43:37 WARNING FullyFusedMLP is not supported for the selected architecture 62. Falling back to CutlassMLP. For maximum performance, raise the target GPU architecture to 75+. 00:43:37 WARNING FullyFusedMLP is not supported for the selected architecture 62. Falling back to CutlassMLP. For maximum performance, raise the target GPU architecture to 75+. 00:43:37 WARNING FullyFusedMLP is not supported for the selected architecture 62. Falling back to CutlassMLP. For maximum performance, raise the target GPU architecture to 75+. 00:43:37 INFO Density model: 3--[HashGrid]-->32--[FullyFusedMLP(neurons=64,layers=3)]-->1 00:43:37 INFO Color model: 3--[Composite]-->16+16--[FullyFusedMLP(neurons=64,layers=4)]-->3 00:43:37 INFO total_encoding_params=12855296 total_network_params=10240 00:43:37 WARNING GPUMemoryArena: GPU 0 does not support virtual memory. Falling back to regular allocations, which will be larger and can cause occasional stutter. terminate called after throwing an instance of 'std::runtime_error' what(): /home/nvidia/project/a/instant-ngp/dependencies/tiny-cuda-nn/include/tiny-cuda-nn/multi_stream.h:83 cudaEventRecord(m_event, m_stream) failed: operation failed due to a previous error during capture Aborted

Trying to run instant-ngp in jetson TX2.

Does anyone know about this error? it occurs when testbed.frame()is implemented.

+Is there anyone who had built instant-ngp in jetson TX2?

limshoonkit commented 1 year ago

Saw a paper that mentioned they implemented it on Jetson TX2. https://arxiv.org/pdf/2212.01959.pdf. The author's profile https://github.com/licj15, https://github.com/BichenWuUCB.

hnj5247 commented 1 year ago

Saw a paper that mentioned they implemented it on Jetson TX2. https://arxiv.org/pdf/2212.01959.pdf. The author's profile https://github.com/licj15, https://github.com/BichenWuUCB.

Thank you!

AmeYatoro commented 6 months ago

Saw a paper that mentioned they implemented it on Jetson TX2. https://arxiv.org/pdf/2212.01959.pdf. The author's profile https://github.com/licj15, https://github.com/BichenWuUCB.

Thank you!

Hi! Did you solve it?