Machine Learning

Apple create ML

overview

create ML swift and macOS playgrounds . to . train custom machine learning models;

Create ML

TensorFlow Lite

Image classification

Note: Image classification can only tell you the probability that an image represents one or more of the classes that the model was trained on. It cannot tell you the position or identity of objects within the image. If you need to identify objects and their positions within images, you should use an object detection model.

object detection

  • position
  • identity

choose Model

性能、精度、大小、結(jié)構(gòu)
performance
Accuracy
size
Architecture

For Android && iOS

examples git

Objc

  1. run workspace
  2. change model with (.tflite .txt)

語義分割

Segmentation

  1. Deep Convolutional Neural Networks.

移動端深度學(xué)習(xí)SDK

百度 MDL
騰訊 NCNN

只支持Caffe框架生成的模型文件。

?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請聯(lián)系作者
【社區(qū)內(nèi)容提示】社區(qū)部分內(nèi)容疑似由AI輔助生成,瀏覽時請結(jié)合常識與多方信息審慎甄別。
平臺聲明:文章內(nèi)容(如有圖片或視頻亦包括在內(nèi))由作者上傳并發(fā)布,文章內(nèi)容僅代表作者本人觀點,簡書系信息發(fā)布平臺,僅提供信息存儲服務(wù)。

相關(guān)閱讀更多精彩內(nèi)容

友情鏈接更多精彩內(nèi)容