royinx Goto Github PK

bilinearimageresize

Bilinear Image Resize with openmp/cuda

blog_material

blog script repo

clothes_seg_trt

clothes segmentation

color_extract

color clustering

cuda_resize

resize image in (CUDA, python, cupy)

cutlass

CUDA Templates for Linear Algebra Subroutines

cv-cuda

CV-CUDA™ is an open-source, graphics processing unit (GPU)-accelerated library for cloud-scale image processing and computer vision.

degit

go_mini

exmaple / demo hierarchy for go

java_mini_build

build java mini container image

jetson_triton

Jetpack4.5 Triton server

kernel_tuner

Kernel Tuner

lfd-a-light-and-fast-detector

LFD is a big update upon LFFD. Generally, LFD is a multi-class object detector characterized by lightweight, low inference latency and superior precision. It is for real-world appilcations.

lffd-a-light-and-fast-face-detector-for-edge-devices

A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......

llm_triton

LLM in Triton , Hugging Face -> Pytorch -> ONNX -> TensorRT -> Triton

msbd5001-kaggle

MSBD5001-kaggle

nerf

Instant neural graphics primitives: lightning fast NeRF and more

nsight-systems-docker-image

Nsight Systems in Docker

royinx

setting

Deep learning installation when new ubuntu installed

simple_api_template

simple API , including Flask and FastAPI

simple_flask_demo

blank flask template for quick start and testing

simple_grpc

tensorrt_deployment

Model (ONNX, Pytorch) to TensorRT inference server

tg_assistant

triton_ensemble_model_demo

triton server ensemble model demo

trt_yolov3

tensorRT_yolov3

trtis_issues

trtis_issues2

videoprocessingframework

Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space and pixel format conversions