wang7393 Goto Github PK

ai-toolbox

Algorithm Engineer Toolbox, for the purpose of quickly iterating new ideas

anchor_computation_tool

aod-net

arivo_custom_openvino_layers

awesome-object-detection

Awesome Object Detection based on handong1587 github: https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html

benchmark_results

Visual Tracking Paper List

bolt

Bolt is a deep learning toolbox with high performance and heterogeneous flexibility.

caffe

Caffe: a fast open framework for deep learning.

caffe-1

This fork of BVLC/Caffe is dedicated to improving performance of this deep learning framework when running on CPU, in particular Intel® Xeon processors.

centernetcpp

centerNet Caffe inference CPP

cnstream

CNStream is a streaming framework for building Cambricon machine learning pipelines http://forum.cambricon.com https://gitee.com/SolutionSDK/CNStream

custom-layers-with-openvino

darknet2caffe

Convert darknet weights to caffemodel

deep-hough-transform

Jittor and Pytorch code for paper "Deep Hough Transform for Semantic Line Detection" (ECCV 2020, PAMI 2021)

deepstream-yolo

NVIDIA DeepStream SDK 5 configuration for YoloV4 and YoloV3 model

deepstream_reference_apps

Samples for TensorRT/Deepstream for Tesla & Jetson

facemaskdetection

开源人脸口罩检测模型和数据 Detect faces and determine whether people are wearing mask.

fitlog

fitlog是一款在深度学习训练中用于辅助用户记录日志和管理代码的工具

ghostnet-ssd

GhostNet Object Detection

ghostnet_cifar10

ghostnet_cifar10

gst-video-analytics

This repository contains a collection of GStreamer* elements to enable CNN model based video analytics capabilities (such as object detection, classification, recognition) in GStreamer* framework.

hwcodec

hardware codec for windows using ffmpeg (nvi qsv enc\dxva2 dec) 使用ffmpeg进行Qsv硬编码、Nvi硬编码、DXVA硬解码的封装API

imgclsmob

Sandbox for training convolutional networks for computer vision

jetsontx1_decode

using gstreamer decode multi rtsp at nvidia_tx1

kmeans-anchor-boxes

k-means clustering with the Intersection over Union (IoU) metric as described in the YOLO9000 paper

kmeans-anchors-ratios

K-Means anchors ratios calculator.

libfacedetection

An open source library for face detection in images. The face detection speed can reach 1000FPS.

mobilenet-ssd

Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.

mobilenetv3-ssd-compact-version

MobileNetV3 SSD的简洁版本

model-compression

model compression based on pytorch (1、quantization: 8/4/2bits(dorefa)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution structure；4、batch-normalization folding for binary value of feature(A))