SimpNet-Deep-Learning-in-a-Shader
Language-Translation-with-Fragment-Shaders
SimpNet-Deep-Learning-in-a-Shader | Language-Translation-with-Fragment-Shaders | |
---|---|---|
2 | 1 | |
104 | 89 | |
- | - | |
0.0 | 1.8 | |
almost 3 years ago | almost 2 years ago | |
GLSL | ShaderLab | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
SimpNet-Deep-Learning-in-a-Shader
-
Can ML upscaling / DLSS be used to enhace shadow map quality?
If you think doing this https://github.com/SCRN-VRC/SimpNet-Deep-Learning-in-a-Shader/blob/master/Images/RenderTexture.png on all of the shadowmaps in a scene is faster than simply relying on tried-and-true hardware rasterization then you should work on more graphics/rendering projects to get a better grasp as to what is actually possible on hardware.
Language-Translation-with-Fragment-Shaders
-
I made a Japanese/English translator with just fragment shaders for VR
It's just for educational purposes on how ML works, not very fast or practical. The entire thing's here for free https://github.com/SCRN-VRC/Language-Translation-with-Fragment-Shaders
What are some alternatives?
YOLOv4-Tiny-in-UnityCG-HLSL - A modern object detector inside fragment shaders
Anime-Speed-Lines - Post-processing effect to procedurally generate a anime/manga-style vignette of lines typically used to portray speed or surprise.
AviSynthAiUpscale - An AviSynth+ implementation of some Super-Resolution Convolutional Neural Networks.
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
CodeSearchNet - Datasets, tools, and benchmarks for representation learning of code.
ACNetGLSL - ACNet (Anime4KCPP Net) re-implemented in GLSL for real-time anime upscaling
NCRFpp - NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.