Corso di formazione TensorFlow Lite for iOS

Last updated

Codice del corso

tensorflowliteios

Durata

21 ore (generalmente 3 giorni pause incluse)

Requisiti

  • Experience with Swift programming
  • Experience with mobile application development
  • An iOS device running v12 or higher

Audience

  • Developers
  • Data scientists who wish to develop AI-enabled mobile applications on iOS

Overview

TensorFlow Lite è un framework di apprendimento approfondito open source per dispositivi mobili e sistemi incorporati.

Questo allenamento diretto da istruttori, dal vivo (online o on-site) è rivolto ai sviluppatori che vogliono utilizzare TensorFlow Lite per sviluppare iOS applicazioni mobili con capacità di apprendimento profondo.

Al termine di questo corso, i partecipanti saranno in grado di:

    Installare e configurare TensorFlow Lite. Comprendere i principi dietro TensorFlow e l'apprendimento automatico su dispositivi mobili. Caricare TensorFlow Modelli su un dispositivo iOS Eseguire un'applicazione iOS capace di rilevare e classificare un oggetto catturato attraverso la fotocamera del dispositivo.

Il formato del corso

    Interattiva lezione e discussione. Molti esercizi e pratiche. Implementazione a mano in un ambiente live-lab.

Opzioni di personalizzazione del corso

    Per richiedere una formazione personalizzata per questo corso, si prega di contattarci per organizzare.

Machine Translated

Struttura del corso

Introduction

  • Tensorflow vs Tensorflow Lite

Overview of TensorFlow Lite Features and Workflow

  • Recap of machine learning and deep learning concepts
  • How on-device low-latency inference is achieved
  • End-to-end model building and deployment

Preparing the Development Environment

  • Starting a Swift project
  • Adding TensorFlow to the project

Capturing an Image with a Device Camera

  • How camera input is captured
  • Overview of classes and methods
  • Running inference on a frame (performing image classification)

Creating an App for Object Detection

  • Selecting a TensorFlow Model
  • Converting the TensorFlow Model
  • Loading the TensorFlow Model onto a Mobile Device
  • Loading a Pre-trained TensorFlow Model

Creating an App for Image Classification

  • Selecting a TensorFlow Model
  • Converting the TensorFlow Model
  • Loading the TensorFlow Model onto a Mobile Device
  • Loading a Pre-trained TensorFlow Model

Customizing the Model and Data

  • Pre-processing a dataset
  • Setting the hyperparameters

Optimizing the TensorFlow Model

  • Measuring performance against a benchmark
  • Measuring accuracy
  • Retraining a TensorFlow model

Exploring Alternative Models

  • Choosing a different model
  • Training a model to recognize new classes (transfer learning)
  • Obtaining training images for new labels

Deploying the AI Enabled iOS App

  • Performing image classification in the field

Troubleshooting

Summary and Conclusion

Recensioni

★★★★★
★★★★★

Categorie relative

Corsi relativi

Corsi scontati

Newsletter per ricevere sconti sui corsi

Rispettiamo la privacy di ogni indirizzo mail. Non diffonderemo,né venderemo assolutamente nessun indirizzo mail a terzi. Inserire prego il proprio indirizzo mail. E' possibile sempre cambiare le impostazioni o cancellarsi completamente.

I nostri clienti

is growing fast!

We are looking for a good mixture of IT and soft skills in Italy!

As a NobleProg Trainer you will be responsible for:

  • delivering training and consultancy Worldwide
  • preparing training materials
  • creating new courses outlines
  • delivering consultancy
  • quality management

At the moment we are focusing on the following areas:

  • Statistic, Forecasting, Big Data Analysis, Data Mining, Evolution Alogrithm, Natural Language Processing, Machine Learning (recommender system, neural networks .etc...)
  • SOA, BPM, BPMN
  • Hibernate/Spring, Scala, Spark, jBPM, Drools
  • R, Python
  • Mobile Development (iOS, Android)
  • LAMP, Drupal, Mediawiki, Symfony, MEAN, jQuery
  • You need to have patience and ability to explain to non-technical people

To apply, please create your trainer-profile by going to the link below:

Apply now!

This site in other countries/regions