C:\Users\me\nerf\instant-ngp\build>testbed.exe --scene ../data/fox
15:37:58 INFO Loading NeRF dataset from
15:37:58 INFO ..\data\fox\transforms.json
15:37:58 SUCCESS Loaded 50 images after 0s
15:37:58 INFO cam_aabb=[min=[1.0229,-1.33309,-0.378748], max=[2.46175,1.00721,1.41295]]
15:37:59 ERROR Network config path configs\nerf\base.json does not exist.

I think I'm almost there, but I get this error that doesn't bring up much results on Google. Anyone knows what this could be?

Since it use tinnyml
Is it possible to use a Google coral with this project?

Encountered below error while preparing the dataset:

==== running: colmap exhaustive_matcher --SiftMatching.guided_matching=true --database_path colmap.db

==============================================================================
Exhaustive feature matching

Matching block [1/1, 1/1] in 0.890s
Elapsed time: 0.023 [minutes]
==== running: mkdir colmap_sparse
==== running: colmap mapper --database_path colmap.db --image_path "C:\nvidia-instant-ngp\instant-ngp\data\nerf\vivid-alast" --output_path colmap_sparse

==============================================================================
Loading database

Loading cameras... 1 in 0.000s
Loading matches... 0 in 0.000s
Loading images... 12 in 0.000s (connected 0)
Building correspondence graph... in 0.000s (ignored 0)

Elapsed time: 0.000 [minutes]

WARNING: No images with matches found in the database.

ERROR: failed to create sparse model
FATAL: command failed

I think this is the issue with colmap...did anyone encountered the same? any suggestions?

Hi! Thanks for your work:)
When I run cmake . -B build,I got this:

-- Selecting Windows SDK version 10.0.19041.0 to target Windows 10.0.17763.
CMake Error at E:/Software/cmake/share/cmake-3.23/Modules/CMakeDetermineCUDACompiler.cmake:311 (message):
  CMAKE_CUDA_ARCHITECTURES must be valid if set.
Call Stack (most recent call first):
  CMakeLists.txt:11 (project)

-- Configuring incomplete, errors occurred!
See also "D:/graduate/nerf/instant-ngp-master/build/CMakeFiles/CMakeOutput.log".
See also "D:/graduate/nerf/instant-ngp-master/build/CMakeFiles/CMakeError.log".

I searched this online, and tried these 2 things below:

1.Add set(CMAKE_CUDA_ARCHITECTURES 48) in cmakelists
2. Use cmake . -B build -DCMAKE_CUDA_COMPILER=E:\Software\cuda\bin\nvcc -DTCNN_CUDA_ARCHITECTURES=61

But they didn't work

C:\Users\user\Desktop\Tutorial\ngp\instant-ngp>cmake . -B build
-- Selecting Windows SDK version 10.0.19041.0 to target Windows 10.0.22621.
-- The CUDA compiler identification is unknown
CMake Error at CMakeLists.txt:11 (project):
No CMAKE_CUDA_COMPILER could be found.

-- Configuring incomplete, errors occurred!
See also "C:/Users/user/Desktop/Tutorial/ngp/instant-ngp/build/CMakeFiles/CMakeOutput.log".
See also "C:/Users/user/Desktop/Tutorial/ngp/instant-ngp/build/CMakeFiles/CMakeError.log".

hello ,
I followed the whole tutorial and steps to run instant-ngp gui but it crashes and never starts when i ran this line of code :
"""<path_to_your_ngp>\instant-ngp\build\testbed.exe --scene data/<image_set_name>"""
as figured in the attachment (

)]
it stop and crashes .
i also tried to decrease the number of images of the dataset from 100 to 50 images but the same error appeared.
I'm not sure , but i think it is related to hardware problem (GPU) not a software one although i think it could run on different GPUs types lower than mine.
i installed CUDA 11.7
my GPU is (NVIDIA [MX150)])
thanks in advance...

Hi.

I'd like to render an image with exact same pose from transforms.json file using render.py.

For example, datan/nerf/fox/, first image images/0001.jpg has transform matrix as below.

      "transform_matrix": [
    [
      0.8926439112348871,
      0.08799600283226543,
      0.4420900262071262,
      3.168359405609479
    ],
    [
      0.4464189982715247,
      -0.03675452191179031,
      -0.8940689141475064,
      -5.4794898611466945
    ],
    [
      -0.062425682580756266,
      0.995442519072023,
      -0.07209178487538156,
      -0.9791660699008925
    ],
    [
      0.0,
      0.0,
      0.0,
      1.0
    ]

Here, I have to convert it to quaternion & translation to use it as base_cam.json format

for example, ...

"R":[0.8109075427055359,0.03559545800089836,0.5819807648658752,-0.04959719628095627],
"T": -2.2435450553894043,0.11715501546859741,1.4327683448791504],"dof":0.0,"fov":50.625,"scale":2.9230759143829346,"slice":0.03611110895872116

I tried to convert it using code below, the result does not match to what I want. Am I missing something?

import numpy as np
from scipy.spatial.transform import Rotation as R

T = np.array(
[[
	0.8926439112348871,
	0.08799600283226543,
	0.4420900262071262,
	3.168359405609479
],
[
	0.4464189982715247,
	-0.03675452191179031,
	-0.8940689141475064,
	-5.4794898611466945
],
[
	-0.062425682580756266,
	0.995442519072023,
	-0.07209178487538156,
	-0.9791660699008925
]]
)

# Extract rotation matrix (R) and translation vector (t)
R_mat = T[:3, :3]
t = T[:3, 3]

# Convert the rotation matrix to a quaternion
rot = R.from_matrix(R_mat)
q = rot.as_quat()

I made it to "Get transform.json" successfully. However when I use the command: python scripts/colmap2nerf.py --colmap_matcher exhaustive --run_colmap --aabb_scale 16 --images /image/vibe I get the error below.

I am using an admin terminal, and have tried the conda prompt as well. I am in the data directory of the repo C:\stable-diffusion\instant-ngp\data. My goal is to create a directory named 'vibe' where I am going to put my photos.

instant-ngp-
                    |_data-
                              |_image-
                                           |_vibe

I'm so close after days of resolving an issue with Git and Windows ASLR!
What am I doing wrong, and what info can I give to help? I am on Windows 10x64.

C:\stable-diffusion\instant-ngp>python scripts/colmap2nerf.py --colmap_matcher exhaustive --run_colmap --aabb_scale 16 --images /image/vibe
running colmap with:
        db=colmap.db
        images="/image/vibe"
        sparse=colmap_sparse
        text=colmap_text
warning! folders 'colmap_sparse' and 'colmap_text' will be deleted/replaced. continue? (Y/n)y
==== running: colmap feature_extractor --ImageReader.camera_model OPENCV --ImageReader.camera_params "" --SiftExtraction.estimate_affine_shape=true --SiftExtraction.domain_size_pooling=true --ImageReader.single_camera 1 --database_path colmap.db --image_path "/image/vibe"
[option_manager.cc:811] Check failed: ExistsDir(*image_path)
ERROR: Invalid options provided.
FATAL: command failed

I kept forgetting to reorganize the file structure in the second to last step, so I made a little script that does it for you. Just drop it in /instant-ngp/scripts, make it a little batch file, run it, and tell it the name of your photos folder!

Link to script

when run build\testbed --scene data/fox :
• Vulkan error: loader_validate_device_extensions: Device extension VK_NVX_binary_import not supported by selected physical device or enabled layers.
• Vulkan error: vkCreateDevice: Failed to validate extensions in list
• WARNING Could not initialize Vulkan and NGX. DLSS not supported

windows 10 x64
nvdia gtx 1080ti
Python  3.9
cuda 11.6
instant-ngp  version=2022-11-16
cmake 3.22
VulkanSDK 1.3.231.1

(py39) D:\Program\Anaconda3\envs\py39\Lib\site-packages\instant-ngp>build\testbed --scene data/fox
04:51:54 INFO     Loading NeRF dataset from
04:51:54 INFO       data\fox\transforms.json
04:51:54 SUCCESS  Loaded 50 images after 0s
04:51:54 INFO       cam_aabb=[min=[1.12716,-0.673166,-0.135153], max=[2.06779,1.13592,1.24793]]
04:51:55 INFO     Loading network config from: configs\nerf\base.json
04:51:55 INFO     GridEncoding:  Nmin=16 b=1.66248 F=2 T=2^19 L=16
Warning: FullyFusedMLP is not supported for the selected architecture 61. Falling back to CutlassMLP. For maximum performance, raise the target GPU architecture to 75+.
Warning: FullyFusedMLP is not supported for the selected architecture 61. Falling back to CutlassMLP. For maximum performance, raise the target GPU architecture to 75+.
Warning: FullyFusedMLP is not supported for the selected architecture 61. Falling back to CutlassMLP. For maximum performance, raise the target GPU architecture to 75+.
04:51:55 INFO     Density model: 3--[HashGrid]-->32--[FullyFusedMLP(neurons=64,layers=3)]-->1
04:51:55 INFO     Color model:   3--[Composite]-->16+16--[FullyFusedMLP(neurons=64,layers=4)]-->3
04:51:55 INFO       total_encoding_params=13623184 total_network_params=10240

04:51:55 WARNING  Vulkan error: loader_validate_device_extensions: Device extension VK_NVX_binary_import not supported by selected physical device or enabled layers.

04:51:55 WARNING  Vulkan error: vkCreateDevice: Failed to validate extensions in list

04:51:55 WARNING  Could not initialize Vulkan and NGX. DLSS not supported. (D:\Program\Anaconda3\envs\py39\Lib\site-packages\instant-ngp\src\dlss.cu:358 vkCreateDevice(vk_physical_device, &device_create_info, nullptr, &vk_device) failed)

04:51:55 ERROR    Uncaught exception: D:\Program\Anaconda3\envs\py39\Lib\site-packages\instant-ngp\dependencies\tiny-cuda-nn\include\tiny-cuda-nn/cutlass_matmul.h:332 status failed with error Error Internal

I get the dreaded out of memory error for cuda. I limited the amount of pictures to 40, resolution to 320 x 240 and I still get it.

I am running a Geforce GTX 960 with 2048 MB Dedicated Video Memory.

Can I make it run on this GPU or which graphics card should I own for this to run fluently?

Visual Studio Community 2022 v17.10 throws up an error stating only VS 2017 to 2022 is supported. Upon further research I found VS 2022 17.9 is support BUT...older versions VS Community 2022 cannot be downloaded and only the current version is supported by Microsoft. Removed VS Community 2022 and downloaded VS 2022 Professional v17.9 and ran cmake and now get this error because Nvidia does not update their projects in the past 2 years.

Thanks for wasting 2 weeks of my time troubleshooting errors.

C:\NGP\instant-ngp>cmake . -B build
CMake Error at CMakeLists.txt:11 (project):
Generator

Visual Studio 17 2022

could not find specified instance of Visual Studio:

C:/Program Files/Microsoft Visual Studio/2022/Community

-- Configuring incomplete, errors occurred!