Stars
An Open Source Machine Learning Framework for Everyone
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
Tutorial code on how to build your own Deep Learning System in 2k Lines
FlexFlow Serve: Low-Latency, High-Performance LLM Serving
Stores documents used by the TensorFlow developer community
Fast, accurate and easy to run dense optical flow with python wrapper
libXCam is a project for extended camera(not limited in camera) features and focus on image quality improvement and video analysis. There are lots features supported in image pre-processing, image …
Spatially-sparse convolutional networks. Allows processing of sparse 2, 3 and 4 dimensional data.Build CNNs on the square/cubic/hypercubic or triangular/tetrahedral/hyper-tetrahedral lattices.
Implementation of the paper "No Reference Image Quality Assessment in the Spatial Domain" by A Mittal et al. in OpenCV (using both C++ and Python)
Accelerate mobileNet-ssd with tensorRT
Permutohedral Lattice C++/CUDA implementation + TensorFlow Op (CPU/GPU)
Straight To Shapes: Real-Time Detection of Encoded Shapes