Open psakamoori opened 2 years ago
cmake -DNGP_BUILD_WITH_VULKAN=OFF . -B build cmake --build build --config RelWithDebInfo -j 8
With above commands got rid of the below Warnings:
15:34:58 WARNING Vulkan error: loaderValidateLayers: Layer 0 does not exist in the list of available layers 15:34:58 WARNING Could not initialize Vulkan and NGX. DLSS not supported. (/home/psakamoori/AI/Projects/3DScene/instant-ngp/src/dlss.cu:220 vkCreateInstance(&instance_create_info, nullptr, &vk_instance) failed)
Still seeing.. 15:34:58 ERROR Uncaught exception: FullyFusedMLP: insufficient shared memory available on the GPU. Reduce n_neurons or use CutlassMLP (better compatibility but slower) instead.
Appreciate any help
instant-ngp$ ./build/testbed --scene data/nerf/fox 15:34:57 WARNING Insufficient compute capability 86 detected. 15:34:57 WARNING This program was compiled for >=87 and may thus behave unexpectedly. 15:34:57 INFO Loading NeRF dataset from 15:34:57 INFO data/nerf/fox/transforms.json 15:34:57 SUCCESS Loaded 50 images after 0s 15:34:57 INFO cam_aabb=[min=[1.0229,-1.33309,-0.378748], max=[2.46175,1.00721,1.41295]] 15:34:57 INFO Loading network config from: configs/nerf/base.json 15:34:57 INFO GridEncoding: Nmin=16 b=1.51572 F=2 T=2^19 L=16 15:34:57 INFO Density model: 3--[HashGrid]-->32--[FullyFusedMLP(neurons=64,layers=3)]-->1 15:34:57 INFO Color model: 3--[Composite]-->16+16--[FullyFusedMLP(neurons=64,layers=4)]-->3 15:34:57 INFO total_encoding_params=13074912 total_networkparams=10240 15:34:58 WARNING Vulkan error: loaderValidateLayers: Layer 0 does not exist in the list of available layers 15:34:58 WARNING Could not initialize Vulkan and NGX. DLSS not supported. (/home/psakamoori/AI/Projects/3DScene/instant-ngp/src/dlss.cu:220 vkCreateInstance(&instance_create_info, nullptr, &vk_instance) failed) 15:34:58 ERROR Uncaught exception: FullyFusedMLP: insufficient shared memory available on the GPU. Reduce
n_neurons
or useCutlassMLP
(better compatibility but slower) instead._Any pointers on how to fix this? I am using RTX 3090 with Ubuntu 20.04