Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

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

PyTorch ,ONNX and TensorRT implementation of YOLOv4

Tengine is a lite, high performance, modular inference engine for embedded device

An easy to use PyTorch to TensorRT converter

Implementation of popular deep learning networks with TensorRT network definition API

YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite

Deep learning gateway on Raspberry Pi and other edge devices

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

HyperPose: A Collection of Real-time Human Pose Estimation

TensorRT YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet

Fast and accurate object detection with end-to-end GPU optimization

TensorFlow models accelerated with NVIDIA TensorRT

Real-time pose estimation accelerated with NVIDIA TensorRT

TensorRT for Yolov3

[ICLR 2020] "FasterSeg: Searching for Faster Real-time Semantic Segmentation" by Wuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang

This repo is implemented based on detectron2 and centernet

Image classification with NVIDIA TensorRT from TensorFlow models.

A simple, efficient, easy-to-use Nvidia TensorRT wrapper for CNN, support c++ and python.

High-performance multiple object tracking based on YOLO, Deep SORT, and optical flow

TensorRT-7 Network Lib 包括常用目标检测、关键点检测、人脸检测、OCR等 可训练自己数据

YOLOv3 implementation in TensorFlow 2.3.1

convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.

Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics.

GPU accelerated deep learning inference applications for RaspberryPi / JetsonNano / Linux PC using TensorflowLite GPUDelegate / TensorRT

Adlik: Toolkit for Accelerating Deep Learning Inference

基于CenterNet训练的目标检测&人脸对齐&姿态估计模型

Reimplement RetinaFace use C++ and TensorRT

A Wide Range of Custom Functions for YOLOv4, YOLOv4-tiny, YOLOv3, and YOLOv3-tiny Implemented in TensorFlow, TFLite, and TensorRT.