trevor-m

tensorflow-SRGAN

Tensorflow implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network" (Ledig et al. 2017)

deep-gbuffers

Implementation of "Fast Global Illumination Approximations on Deep G-Buffers" (Mara et. al, 2016) using C++, OpenGL, and GLSL

tensorflow-bicubic-downsample

tf.image.resize_images has aliasing when downsampling and does not have gradients for bicubic mode. This implementation fixes those problems.

reyes-renderer

A REYES-style micropolygon renderer written in C++ which implements a subset of the RenderMan specification.

raytracer

A multithreaded Whitted ray tracer (C++) which supports reflection, refraction, shadows, interpolated textures and normals, color and intersection shaders, as well as Monte Carlo anti-aliasing, depth-of-field, and BSSSRDFs

cuda-pathtrace

A realtime photorealistic pathtracer implemented in CUDA, using a convolutional neural network denoising algorithm

gpu-pathtracer

A real-time photorealistic path tracer using OpenGL GPU Compute Shaders

deep-tor-detection

Using deep learning to distinguish between Tor and nonTor traffic

DeepLearningExamples

Deep Learning Examples

tensorflow

An Open Source Machine Learning Framework for Everyone

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

neo-ai-dlr

Neo-AI-DLR is a common runtime for machine learning models compiled by AWS SageMaker Neo, TVM, or TreeLite.

bert

TensorFlow code and pre-trained models for BERT

cyclegan-audio

fastT5

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

horovod

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

iree

A retargetable MLIR-based machine learning compiler and runtime toolkit.

llvm-project

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at http://reviews.llvm.org.

models

Models and examples built with TensorFlow

naives-bayes-movie-reviews

Naive Bayes classifier to detect whether movie reviews are positive or negative (won 2nd place)

nccl

Optimized primitives for collective multi-GPU communication

neo-loader

OpenSeq2Seq

Toolkit for efficient experimentation with various sequence-to-sequence models

openxla-pjrt-plugin

PJRT plugin for interfacing the OpenXLA compiler to Jax, PyTorch/XLA and TensorFlow

tensorflow-tensorrt

TensorFlow/TensorRT integration

TensorRT

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

tf-addons

Useful extra functionality for TensorFlow 2.x maintained by SIG-addons

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference.

treelite

model compiler for decision tree ensembles

xla

A machine learning compiler for GPUs, CPUs, and ML accelerators