Convert fast.ai trained image classification model to iOS app via ONNX and Apple Core ML

Flow

Pytorch → ONNX → Apple Core ML

What we need to install

Steps

Replace AdaptivePooling with fixed size Pooling
Extract all layers with few modifications
cat
dog
Convert Pytorch → onnx → Apple Core ML

--

--

--

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Regression Analysis

Faster R-CNN- Using Region Proposal Network for Object Detection

Multi-Task Learning with Pytorch and FastAI

Real-Time Appearance-Based Mapping

Graph Neural Network training with Feast

Feature Engineering — deep dive into Encoding and Binning techniques

Deep Image Matting (CVPR2017)

The SpaceNet 5 Baseline — Part 2: Training a Road Speed Segmentation Model

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Hung Minh Nguyen

Hung Minh Nguyen

More from Medium

Policy design for scaling clean hydrogen supply and demand

Open Source RPA and its benefits

Enjoy latency-optimised networks globally, powered by real-time analytics

End to End Anime Recommendation System: Part 1 (Overview)