All Projects → hollance → Coreml Training

hollance / Coreml Training

Licence: mit
Source code for my blog post series "On-device training with Core ML"

Programming Languages

swift
15916 projects

Projects that are alternatives of or similar to Coreml Training

sense-iOS
Enhance your iOS app with the ability to see and interact with humans using the RGB camera.
Stars: ✭ 19 (-75.32%)
Mutual labels:  edge-computing, coreml
Mnist draw
This is a sample project demonstrating the use of Keras (Tensorflow) for the training of a MNIST model for handwriting recognition using CoreML on iOS 11 for inference.
Stars: ✭ 139 (+80.52%)
Mutual labels:  jupyter-notebook, coreml
Ios Coreml Yolo
Almost Real-time Object Detection using Apple's CoreML and YOLO v1 -
Stars: ✭ 153 (+98.7%)
Mutual labels:  jupyter-notebook, coreml
Keras Openface
Keras-OpenFace is a project converting OpenFace from Torch implementation to a Keras version
Stars: ✭ 538 (+598.7%)
Mutual labels:  jupyter-notebook, coreml
Build Ocr
Build an OCR for iOS apps
Stars: ✭ 17 (-77.92%)
Mutual labels:  jupyter-notebook, coreml
Shapedetector keras coreml
Deep learning installed Shape Detector using Keras and CoreML 📱
Stars: ✭ 25 (-67.53%)
Mutual labels:  jupyter-notebook, coreml
Har Keras Coreml
Human Activity Recognition (HAR) with Keras and CoreML
Stars: ✭ 23 (-70.13%)
Mutual labels:  jupyter-notebook, coreml
Ios Coreml Mnist
Real-time Number Recognition using Apple's CoreML 2.0 and MNIST -
Stars: ✭ 74 (-3.9%)
Mutual labels:  jupyter-notebook, coreml
Branchynet
Stars: ✭ 76 (-1.3%)
Mutual labels:  jupyter-notebook
Dash 120million Taxi App
Explore 120 million taxi trips in real time with Dash and Vaex
Stars: ✭ 77 (+0%)
Mutual labels:  jupyter-notebook
Suspeitando
Projeto de análise de contratos com suspeita de superfaturamento e má qualidade na prestação de serviços.
Stars: ✭ 76 (-1.3%)
Mutual labels:  jupyter-notebook
Nipype tutorial
Learn Nipype with these tutorial notebooks - go here to see them online -->
Stars: ✭ 76 (-1.3%)
Mutual labels:  jupyter-notebook
Maskdetect Yolov4 Pytorch
基于PyTorch&YOLOv4实现的口罩佩戴检测 ⭐️ 自建口罩数据集分享
Stars: ✭ 77 (+0%)
Mutual labels:  jupyter-notebook
Battle tested
Fully automated python fuzzer built to test if code actually is production ready in seconds.
Stars: ✭ 76 (-1.3%)
Mutual labels:  jupyter-notebook
Deepfakedetection
Stars: ✭ 77 (+0%)
Mutual labels:  jupyter-notebook
Pythondata
python数据分析代码资料
Stars: ✭ 76 (-1.3%)
Mutual labels:  jupyter-notebook
Machine Learning For Beginners
Start writing machine learning code in just 10 hours
Stars: ✭ 76 (-1.3%)
Mutual labels:  jupyter-notebook
Nltk Python Cn
创建《Python自然语言处理》学习代码的中文注释版本。
Stars: ✭ 77 (+0%)
Mutual labels:  jupyter-notebook
Ntk
Code for experiments in my blog post on the Neural Tangent Kernel: https://rajatvd.github.io/NTK
Stars: ✭ 76 (-1.3%)
Mutual labels:  jupyter-notebook
Shot Detection Benchmarks
A comparison of ffmpeg, Shotdetect and PySceneDetect for shot transition detection
Stars: ✭ 76 (-1.3%)
Mutual labels:  jupyter-notebook

Training with Core ML 3

This is the sample code for my blog post series On-device training with Core ML.

Included are:

  • Dataset: a small dataset of 30 training images and 15 test images

  • iOS App: the source code of the demo app described in the blog post

  • Models: the empty and pre-trained models used by the app

    • TuriOriginal.mlmodel: the SqueezeNet classifier trained by Turi Create
    • HandsTuri.mlmodel: the TuriOriginal model but made updatable
    • HandsEmpty.mlmodel: like HandsTuri but with a classifier layer that has random weights
    • HandskNN.mlmodel: like TuriOriginal but with an untrained k-Nearest Neighbors classifier
  • Scripts:

    • make_nn.py: converts TuriOriginal.mlmodel to HandsTuri and HandsEmpty.mlmodel
    • make_knn.py: creates the k-Nearest Neighbor model, HandskNN.mlmodel
    • TuriCreate.ipynb: the notebook used to train TuriOriginal.mlmodel

Credits:

The source code is copyright 2019 M.I. Hollemans and licensed under the terms of the MIT license.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].