Learn how to design, develop, deploy and iterate on production-grade ML applications.

A collection of various deep learning architectures, models, and tips

An annotated implementation of the Transformer paper.

Data augmentation for NLP

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

Keras version of Realtime Multi-Person Pose Estimation project

Attributing predictions made by the Inception network using the Integrated Gradients method

PyTorch implementation of VQ-VAE by Aäron van den Oord et al.

Deep Replay - Generate visualizations as in my "Hyper-parameters in Action!" series!

Authors' implementation of DeepSpeech Distances.

Personalizing Dialogue Agents via Meta-Learning

Tacotron 2 - PyTorch implementation with faster-than-realtime inference