xiaqing10 Goto Github PK

tensorrt

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

tensorrtx

Implementation of popular deep learning networks with TensorRT network definition API

tf-mtcnn

This project provide a single tensorflow model implement the mtcnn face detector. And it shows how to convert model from caffe to tensorflow in a hard way.

tf-pose-estimation

Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.

trt_pose

Real-time pose estimation accelerated with NVIDIA TensorRT

understand_facenet

整理和注释了facenet的代码，以便更好地理解facenet的代码。源代码地址：https://github.com/davidsandberg/facenet

understanding-age-gender-deep-learning-models

Understanding and Comparing Deep Neural Networksfor Age and Gender Classification - Data and Models

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

yolo-tensorrt

Support Yolov5s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.

yolov4_tiny-

yolov4_tiny相关，调试记录

yolov5_caffe

yolov5 onnx caffe

yolov5_deepsort_rknn

yolov5_rknn

yolov5_ros

yolov5 with ROS

zqcnn

一款比mini-caffe更快的Forward库，觉得好用请点星啊，400星公布快速人脸检测模型，500星公布106点landmark，600星公布人头检测模型，700星公布人脸检测套餐（六种pnet,两种rnet随意混合使用满足各种速度/精度要求），800星公布更准的106点模型