Published inTDS ArchiveOptimizing Style Transfer Models for Videos on Mobile DevicesExperimenting wth PyTorch Lighting and Flash flexibility to create a face-to-cartoon modelJan 18, 2022Jan 18, 2022
Optimize a face to cartoon style transfer model, trained quickly on small style dataset, and…Hugging Face Spaces demo at: http://huggingface.co/spaces/Jacopo/ToonClipJan 17, 2022A response icon1Jan 17, 2022A response icon1
Published inData Science at MicrosoftA tale of two frameworks: PyTorch vs. TensorFlowComparing auto-diff and dynamic model sub-classing approaches with PyTorch 1.x and TensorFlow 2.xFeb 2, 2021A response icon2Feb 2, 2021A response icon2
Published inTDS ArchiveAutoDiff and Dynamic Subclassed Models with PyTorch Vs TensorFlowComparing AutoDiff and Dynamic Model Sub-classing approaches between PyTorch 1.x and TensorFlow 2.x, training from scratch a Linear…Oct 13, 2020Oct 13, 2020
AutoDiff and Dynamic Subclassed Models with PyTorch Vs TensorFlowComparing AutoDiff and Dynamic Model Sub-classing approaches between PyTorch 1.x and TensorFlow 2.x, training from scratch a Linear…Oct 12, 2020Oct 12, 2020
Published inTDS ArchiveUse Apple new ML Compute framework to accelerate ML training and inferencing on iOS and macOSHacking the new Apple ML Compute framework to accelerate training of neural networks across CPU and GPUJul 17, 2020A response icon1Jul 17, 2020A response icon1
ML ComputeHacking the new Apple ML Compute framework to accelerate training of neural networks across CPU and GPUJul 16, 2020A response icon1Jul 16, 2020A response icon1
Published inHeartbeatFully Training a Core ML Convolutional Neural Network On-DeviceDid you know you can fully train a LeNet convolutional neural network (CNN) directly on iOS devices?May 7, 2020A response icon2May 7, 2020A response icon2
MNIST CNN Core ML TrainingDid you know you can fully train a LeNet Convolutional Neural Network model with the MNIST dataset directly on iOS devices ? And that the…Apr 26, 2020Apr 26, 2020
Published inHeartbeatCore ML On-Device Training, with Transfer Learning from Swift for TensorFlow ModelsA demonstration of the potentiality of the SwiftCoreMLTools library in a long journey towards a Swift federated learning infrastructureMar 27, 2020Mar 27, 2020