深度学习及机器视觉

damone大约 5 分钟收藏总结机器视觉深度学习

  1. 知乎深度学习大讲堂open in new window
  2. 国外知名大学机器学习课程汇总open in new window
  3. 深度学习论文阅读open in new window
  4. 机器人视觉资源综合open in new window
  5. ApacheCN 人工智能知识树open in new window
  6. 人工智能的下一个拐点:图神经网络迎来快速爆发期open in new window
  7. CSDN 机器学习 Machine Learningopen in new window
  8. 机器学习与人工智能技术分享open in new window
  9. 数学知识点滴积累 矩阵 数值优化 神经网络反向传播 图优化 概率论 随机过程 卡尔曼滤波 粒子滤波open in new window

机器学习

  1. 机器学习python库 scikit-learnopen in new window
  2. 斯坦福大学公开课 :机器学习课open in new window
  3. 轻松理解卡尔曼滤波open in new window
  4. 卡尔曼滤波是如何工作的open in new window
  5. 机器学习的数学基础open in new window
  6. 机器学习资源汇总open in new window
  7. 计算仿射变换六参数(Python)open in new window
  8. 利用最小二乘法求解仿射变换参数open in new window

CNN

  1. 卷积神经网络常用激活函数总结open in new window
  2. 神经网络浅讲:从神经元到深度学习open in new window
  3. 零基础入门深度学习open in new window
  4. 神经网络与深度学习open in new window
  5. 吴恩达 神经网络和深度学习open in new window
  6. Deep Learning 中文翻译open in new window
  7. 深度学习中 Batch Normalization为什么效果好?open in new window
  8. 深度学习中的batch的大小对学习效果有何影响?open in new window
  9. 卷积神经网络操作技巧open in new window
  10. 如何直观地解释 backpropagation 算法?open in new window
  11. DNN可视化研究员Colah的博客open in new window
  12. 机器学习可视化博客DISTILLopen in new window
  13. 深度学习可视化Js组件 tensorspaceopen in new window
  14. 理解 LSTM 网络open in new window
  15. RNN-LSTM-GRUopen in new window
  16. 获奖无数的深度残差学习open in new window
  17. CAFFE卷积层的实现open in new window
  18. CNN(卷积神经网络)、RNN(循环神经网络)、DNN(深度神经网络)的内部网络结构有什么区别?open in new window
  19. 基于3D卷积神经网络的人体行为理解open in new window
  20. 一个模型库学习所有open in new window
  21. One Model to Learn Them All详解open in new window

目标检测

  1. YOLO 检测系列算法open in new window
  2. Bounding box regression详解open in new window
  3. 目标检测评价参数open in new window
  4. 理解YOLO 的Boundig boxopen in new window
  5. YOLO 详解open in new window
  6. 图解YOLOopen in new window
  7. YOLOV2详解open in new window
  8. YOLOv3 深入理解open in new window
  9. SSD: Single Shot MultiBox Detector 模型fine-tune和网络架构open in new window
  10. SSD论文阅读open in new window
  11. Faster R-CNNopen in new window
  12. faster rcnn源码理解open in new window
  13. R-FCN:基于区域的全卷积网络来检测物体open in new window
  14. RCNN, Fast-RCNN, Faster-RCNN的一些事open in new window
  15. 车和车道检测open in new window
  16. 基于深度学习的车道检测open in new window
  17. 图像质量判断:模糊/色偏/亮度检测综合open in new window

目标跟踪

  1. Tracking-Learning-Detection原理分析open in new window
  2. 细说贝叶斯滤波:Bayes filtersopen in new window
  3. 细说Kalman滤波:The Kalman Filteropen in new window
  4. 深度学习在目标跟踪中的应用open in new window
  5. Kalman 多目标跟踪open in new window
  6. 光流计算的效果比较open in new window
  7. 可视化追踪论文集合open in new window
  8. 计算机视觉中,目前有哪些经典的目标跟踪算法?open in new window
  9. Fully-Convolutional Siamese Networks for Object Trackingopen in new window

神经网络量化

  1. 神经网络模型量化方法简介open in new window
  2. 神经网络量化简介open in new window
  3. 神经网络量化资源open in new window
  4. 神经网络工作在低精度的条件下open in new window
  5. Int8量化-介绍open in new window
  6. NCNN Conv量化详解open in new window
  7. 六大国外AI芯片“新势力”同台碰撞 明星创投分享芯片创业之道open in new window
  8. 终于有人把RISC-V讲明白了open in new window
  9. Risk-V 说明文档open in new window
  10. 知乎 AI处理器架构设计open in new window

开发框架

  1. OPENCV 开源的图像处理工具,综合各类算法
  2. 常用框架:Caffe, Tensorlfow, Pytorch, Onnx, Mxnet等
  3. Pytorch 神经网络压缩工具 distilleropen in new window
  4. CCCV, C语言的视觉处理库open in new window
  5. CMSIS Version 嵌入式开发组件open in new window
  6. 纯C的深度学习框架Darknetopen in new window
  7. CPU量化神经网络加速 QNNPACKopen in new window
  8. CPU浮点神经网络加速 XNNPACKopen in new window
  9. 移动端深度学习部署框架NCNNopen in new window
  10. 移动端深度学习部署框架MNNopen in new window
  11. MNNKit Demoopen in new window
  12. 移动端深度学习部署框架MACEopen in new window
  13. Darknet 转换 tensorflow darkflowopen in new window
  14. FaceBook 目标检测系列算法实现 Detectionopen in new window

数据集

  1. 自己学习深度学习时,有哪些途径寻找数据集?open in new window
  2. 常用图像数据集大全(分类,跟踪,分割,检测等)open in new window
  3. 腾讯mult-label 图片数据集open in new window
  4. Openimagesopen in new window
  5. 开源数据集open in new window

车牌数据集

  1. 车牌数据集open in new window
  2. CCPDopen in new window
  3. 所有车牌样式大全open in new window
  4. 车牌及车数据集 platesmaniaopen in new window
  5. 世界各国车牌open in new window
  6. 世界各国车牌发展史open in new window