Comments (2)
Hi, the reason some of the dimensionalities are commented out is that they increase the compile time and memory cost by quite a lot -- for a feature that most people are not going to use.
But I hear your preference for upstreaming this. How about making the enabled hash encoding dimensions a preprocessor define? I am thinking TCNN_HASH_MIN_DIM
(with default 2) and TCNN_HASH_MAX_DIM
(with default 4). Those variables could then be overridden via CMake options -- see the top of CMakeLists.txt
for how existing options are defined and then turned into preprocessor defines via target_add_definitions
.
For the Python bindings, we could have an additional setup.py
argument, similar to how --no-networks
is currently handled, that similarly gets turned into TCNN_HASH_MIN_DIM
and TCNN_HASH_MAX_DIM
.
from tiny-cuda-nn.
Thank you very much for your reply. I agree that preporcessor defines would be the cleanest approch to balance feature scope and compile time for all users of tcnn.
In principle, I would be interested in making such a contribution. However, I cannot promise ATM when I find time to look into this in more detail. Until then, I will stick to the fork-solution and revist this issue once I start refactoring my own code.
from tiny-cuda-nn.
Related Issues (20)
- 'tiny cuda nn' issue HOT 1
- something to do with tinycudann
- Backward method of the grid encoding
- How to calculate FLOPs?
- Is the RTX4070ti supported?
- install issue HOT 6
- Add auxiliary losses directly imposed on params HOT 1
- README executable instructions include non-executable shell prompts
- Question about the bounding box
- initiailization of hash grid
- tinycudann ImportError: tinycudann_bindings/_80_C.cpython-38-x86_64-linux-gnu.so: undefined symbol: HOT 2
- Link Against tiny-cuda-nn in C++ Program HOT 1
- [Question]: can tiny-cuda-nn build a network with layer's bias=0?
- Problems encountered during installation HOT 1
- Already setted the CUDA_HOME but still:CUDA_HOME environment variable is not set. Please set it to your CUDA install root. HOT 1
- Manual installation with torch extension fails: parameter packs not expanding after cmake build success HOT 1
- Tiny cuda nn compilation issue HOT 1
- pt
- pip install of tiny-cuda-nn does not install it in
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tiny-cuda-nn.