Machine Learning: WinML/DirectML, CoreML & all things ML

Instant Neural Graphics Primitives with a Multiresolution Hash Encoding (nvlabs.github.io)
February 19, 2022
We demonstrate near-instant training of neural graphics primitives on a single GPU for multiple tasks.
...
Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that permits the use of a smaller network without sacrificing quality, thus significantly reducing the number of floating point and memory access operations.
Click to expand...
 
Is it just me or is AI going to massively disrupt the video game industry?

It's hard not to the see the progression of image generation -> video generation ->...
 

Random-Access Neural Compression of Material Textures | Research

The continuous advancement of photorealism in rendering is accompanied by a growth in texture data and, consequently, increasing storage and memory demands. To address this issue, we propose a novel neural compression technique specifically designed for material textures. We unlock two more...
research.nvidia.com research.nvidia.com

We propose a novel neural compression technique specifically designed for material textures. We unlock two more levels of detail, i.e., 16× more texels, using low bitrate compression, with image quality that is better than advanced image compression techniques, such as AVIF and JPEG XL. At the same time, our method allows for on-demand, real-time decompression with random access similar to block texture compression on GPUs. This extends our compression benefits all the way from disk storage to memory. The key idea behind our approach is compressing multiple material textures and their mipmap chains together, and using a small neural network, that is optimized for each material, to decompress them. Finally, we use a custom training implementation to achieve practical compression speeds, whose performance surpasses that of general frameworks, like PyTorch, by an order of magnitude.
Click to expand...
 
blogs.nvidia.com

NVIDIA and Microsoft Drive Innovation for Windows PCs in New Era of Generative AI

At the Microsoft Build developer conference, NVIDIA and Microsoft showcased a suite of advancements in Windows 11 PCs and workstations with NVIDIA RTX GPUs.
blogs.nvidia.com
Don't see any thread on DirectML where this would be a better fit.

+
devblogs.microsoft.com

DirectML ❤ Stable Diffusion - DirectX Developer Blog

Text-to-image models are amazing tools that can transform natural language into stunning images. Stable Diffusion is particularly interesting: the base model can create images from text and, since it’s open-source, developers can customize it for their own needs and preferences. With some extra...
devblogs.microsoft.com devblogs.microsoft.com
devblogs.microsoft.com

Optimize DirectML performance with Olive - DirectX Developer Blog

Are you ready to revolutionize the way you optimize your AI models? Say hello to Olive (ONNX Live), the advanced model optimization tool.
devblogs.microsoft.com devblogs.microsoft.com
 
Last edited:
DegustatoR said:
blogs.nvidia.com

NVIDIA and Microsoft Drive Innovation for Windows PCs in New Era of Generative AI

At the Microsoft Build developer conference, NVIDIA and Microsoft showcased a suite of advancements in Windows 11 PCs and workstations with NVIDIA RTX GPUs.
blogs.nvidia.com
Don't see any thread on DirectML where this would be a better fit.
Click to expand...
Seems NVIDIA is left alone optimizing DirectML along with Microsoft, AMD should be present in the scene, but they are not, I feel this is a repeat of DXR.
 
DavidGraham said:
Seems NVIDIA is left alone optimizing DirectML along with Microsoft, AMD should be present in the scene, but they are not, I feel this is a repeat of DXR.
Click to expand...
AMD claims that they are participating:
gpuopen.com

AMD support for Microsoft® DirectML optimization of Stable Diffusion

AMD now has driver support for a metacommand implementation intended to improve performance and reduce the time it takes to generate output from the model.
gpuopen.com gpuopen.com
(Haven't posted that one since it was included into the MS blogpost above.)
 
You must log in or register to reply here.
Back
Top