Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
CoreMLではじめる機械学習
Search
naru-jpn
June 21, 2017
Technology
0
1.2k
CoreMLではじめる機械学習
Neural Networks on Keras ( TensorFlow backends )
naru-jpn
June 21, 2017
Tweet
Share
More Decks by naru-jpn
See All by naru-jpn
配信アプリのためのリアルタイムプッシュ通知ぼかしの夢
narujpn
3
870
PiPを応用した配信コメントバー機能の開発秘話と技術の詳解 / pip_streaming_comment_bar
narujpn
3
4.1k
Updating an App to Use Swift Concurrency 解説
narujpn
2
330
PiP で実現するミラティブの配信コメントバー / pip-streaming-comment-bar
narujpn
0
1.1k
App Extension のスタックトレース情報からクラッシュを解析/集計する / Analyzing app extension's stack trace
narujpn
3
1.5k
ミラティブとWebRTC - WebRTC framework の中身を覗いてみよう / WebRTC framework AudioUnit Processing
narujpn
1
2.2k
CoreML3のオンデバイストレーニングでつくる母音推定
narujpn
0
430
AltConfと周辺の歩き方
narujpn
0
2k
エンジニア経験を活かしたスクラムマスターとして 開発チームとプロダクトを成長させる
narujpn
1
400
Other Decks in Technology
See All in Technology
Streamlit in Snowflakeで加速する不動産テック企業のデータ活用 @Snowflake WESTユーザー会
yuto16
1
150
Creative UIs with Compose: Kotlinconf 2025
chrishorner
0
140
激動の一年を通じて見えてきた「技術でリードする」ということ
ktr_0731
8
8.6k
テスト設計、逆から読むとおもしろい──仕様にない“望ましさ”の逆設計
mhlyc
0
200
AIエージェントのオブザーバビリティについて
yunosukey
1
420
AWS_MCP_Servers入門.pdf
naotoiso
0
200
10年もののアプリケーションを運用・開発するアプリケーションエンジニアのDatadog活用術
miyamu
0
130
スイッチのBMC、つかってますか?
sonic
0
490
Опыт использования Nessie в Азбуке Вкуса
emeremyanina1234
0
480
Why every SwiftUI developer should care about the Environment - iOSKonf25
peterfriese
0
160
Software Delivery Observability CI・CD , DORA metrics も Datadog で可視化しよう / datadog-ci-cd-observability
parupappa2929
0
190
Amplifyとゼロからはじめた AIコーディング。失敗と気づき
mkdev10
1
190
Featured
See All Featured
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
8
720
4 Signs Your Business is Dying
shpigford
183
22k
Bash Introduction
62gerente
613
210k
Designing Experiences People Love
moore
142
24k
How to Think Like a Performance Engineer
csswizardry
23
1.6k
Raft: Consensus for Rubyists
vanstee
137
6.9k
Building Better People: How to give real-time feedback that sticks.
wjessup
368
19k
BBQ
matthewcrist
88
9.6k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
331
21k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
5
590
YesSQL, Process and Tooling at Scale
rocio
172
14k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.3k
Transcript
CoreMLͰ͡ΊΔػցֶश Neural Networks on Keras ( TensorFlow backends ) Timers
inc. / Github: naru-jpn / Twitter: @naruchigi
CoreMLͰ͡ΊΔػցֶश Timers inc. / Github: naru-jpn / Twitter: @naruchigi Neural
Networks on Keras ( TensorFlow backends )
What is Neural Networks?
One of machine learning models. - Neural networks - Tree
ensembles - Support vector machines - Generalized linear models - … https://developer.apple.com/documentation/coreml/converting_trained_models_to_core_ml
What is Keras?
Theano TensorFlow Keras Keras is a high-level neural networks API,
written in Python and capable of running on top of either TensorFlow, CNTK or Theano. https://keras.io
What is CoreML?
Accelerate and BNNS Metal Performance Shaders CoreML BNNS : Basic
Neural Network Subroutines https://developer.apple.com/documentation/coreml With Core ML, you can integrate trained machine learning models into your app. Core ML requires the Core ML model format.
CoreML Trained Model Application Keras Train coremltools
What is coremltools?
Convert existing models to .mlmodel format from popular machine learning
tools including Keras, Caffe, scikit-learn, libsvm, and XGBoost. https://pypi.python.org/pypi/coremltools coremltools
CoreML Trained Model Application Keras Train coremltools
(Demo App)
Environment - Tensorflow 1.1.0 (virtualenv) - Keras 1.2.2 - coremltools
0.3.0 - Xcode 9.0 beta ※ Tensorflow, Keras coremltools ͷରԠόʔδϣϯͰ͋Δඞཁ͕͋ΔͷͰগ͠ݹ͍Ͱ͢ɻ
Programs to train neural networks - mnist_mlp.py - mnist_cnn.py ※
Keras ͷ࠷৽όʔδϣϯͷϦϯΫʹͳ͍ͬͯ·͕͢ɺ࣮ࡍόʔδϣϯ 1.2.2 Λࢀর͠·͢ɻ https://github.com/fchollet/keras/tree/master/examples
Convert model with coremltools 1. Import coremltools import coremltools model
= Sequential() … coreml_model = coremltools.converters.keras.convert(model) coreml_model.save("keras_mnist_mlp.mlmodel") 2. Convert model
Import model into Xcode project // 入力データ class keras_mnist_mlpInput :
MLFeatureProvider { var input1: MLMultiArray // … } // 出力データ class keras_mnist_mlpOutput : MLFeatureProvider { var output1: MLMultiArray // … } // モデル @objc class keras_mnist_mlp:NSObject { var model: MLModel init(contentsOf url: URL) throws { self.model = try MLModel(contentsOf: url) } // … func prediction(input: keras_mnist_mlpInput) throws -> keras_mnist_mlpOutput { // … keras_mnist_mlp.mlmodel Λѻ͏ҝͷίʔυ͕ࣗಈੜ͞ΕΔ
Prepare model and input in code // モデルの作成 let model
= keras_mnist_mlp() // 入力データの格納用変数 (入力は28*28の画像) let input = keras_mnist_mlpInput( input1: try! MLMultiArray(shape: [784], dataType: .double) )
Modify input value // 入力データの 0 番目の要素に 1.0 を代入 input.input1[0]
= NSNumber(value: 1.0)
Make a prediction // モデルに入力データを渡して計算 let output = try model.prediction(
input: self.input )
CoreML Trained Model Application Keras Train coremltools Recap
Demo App on Github https://github.com/naru-jpn/MLModelSample
͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠