Jacopo Mangiavacchi – Medium

Jacopo Mangiavacchi

Jacopo Mangiavacchi
in
Towards Data Science

Optimizing Style Transfer Models for Videos on Mobile Devices

Experimenting wth PyTorch Lighting and Flash flexibility to create a face-to-cartoon model

9 min readJan 18, 2022

--

Optimizing Style Transfer Models for Videos on Mobile Devices

--

Jacopo Mangiavacchi

Optimize a face to cartoon style transfer model, trained quickly on small style dataset, and…

Hugging Face Spaces demo at: https://huggingface.co/spaces/Jacopo/ToonClip

9 min readJan 17, 2022

--

1

Optimize a face to cartoon style transfer model, trained quickly on small style dataset, and…

--

1

Jacopo Mangiavacchi
in
Data Science at Microsoft

A tale of two frameworks: PyTorch vs. TensorFlow

Comparing auto-diff and dynamic model sub-classing approaches with PyTorch 1.x and TensorFlow 2.x

8 min readFeb 2, 2021

--

2

A tale of two frameworks: PyTorch vs. TensorFlow

--

2

Jacopo Mangiavacchi
in
Towards Data Science

AutoDiff and Dynamic Subclassed Models with PyTorch Vs TensorFlow

Comparing AutoDiff and Dynamic Model Sub-classing approaches between PyTorch 1.x and TensorFlow 2.x, training from scratch a Linear…

4 min readOct 13, 2020

--

AutoDiff and Dynamic Subclassed Models with PyTorch Vs TensorFlow

--

Jacopo Mangiavacchi

AutoDiff and Dynamic Subclassed Models with PyTorch Vs TensorFlow

Comparing AutoDiff and Dynamic Model Sub-classing approaches between PyTorch 1.x and TensorFlow 2.x, training from scratch a Linear…

4 min readOct 12, 2020

--

AutoDiff and Dynamic Subclassed Models with PyTorch Vs TensorFlow

--

Jacopo Mangiavacchi
in
Towards Data Science

Use Apple new ML Compute framework to accelerate ML training and inferencing on iOS and macOS

Hacking the new Apple ML Compute framework to accelerate training of neural networks across CPU and GPU

6 min readJul 17, 2020

--

1

Use Apple new ML Compute framework to accelerate ML training and inferencing on iOS and macOS

--

1

Jacopo Mangiavacchi

ML Compute

Hacking the new Apple ML Compute framework to accelerate training of neural networks across CPU and GPU

5 min readJul 16, 2020

--

1

ML Compute

--

1

Jacopo Mangiavacchi
in
Heartbeat

Fully Training a Core ML Convolutional Neural Network On-Device

Did you know you can fully train a LeNet convolutional neural network (CNN) directly on iOS devices?

9 min readMay 7, 2020

--

2

Fully Training a Core ML Convolutional Neural Network On-Device

--

2

Jacopo Mangiavacchi

MNIST CNN Core ML Training

Did you know you can fully train a LeNet Convolutional Neural Network model with the MNIST dataset directly on iOS devices ? And that the…

8 min readApr 26, 2020

--

MNIST CNN Core ML Training

--

Jacopo Mangiavacchi
in
Heartbeat

Core ML On-Device Training, with Transfer Learning from Swift for TensorFlow Models

A demonstration of the potentiality of the SwiftCoreMLTools library in a long journey towards a Swift federated learning infrastructure

10 min readMar 27, 2020

--

Core ML On-Device Training, with Transfer Learning from Swift for TensorFlow Models

--

Jacopo Mangiavacchi

Jacopo Mangiavacchi

Microsoft Principal Data Scientist — Google Machine Learning Developer Expert (ML GDE) — Former  + IBM Senior Architect and Engineer

Following

Help
Status
About
Careers
Blog
Privacy
Terms
Text to speech
Teams