Liam Schoneveld

tsne_raw. Implementation of Symmetric SNE and t-SNE in numpy and python

adversarial-neural-crypt. Implementation of model described in 'Learning to Protect Communications with Adversarial Neural Cryptography' (Martín Abadi & David G. Andersen, 2016, https://arxiv.org/abs/1610.06918)

bpm. neural network for detecting music bpm

SHeaP. Code and models for SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians

np-to-tf-embeddings-visualiser. Quick function to go from a dictionary of sets of (images, labels, feature vectors) to checkpoints that can be opened in Tensorboard

MoCo. Momentum Contrast for Unsupervised Visual Representation Learning

deconstruct-mediapipe. Python

bpm2. Python

YoCLI. yo lets you find the the CLI command you are looking for by asking in natural language

dreamz. deep learning-driven visual art stuff

perturbations-torch. Pytorch reimplement of google-research/perturbations

cats-vs-dogs-classifier-pruned-and-served. Cats vs. dogs convnet classifier training (with model pruning) with Pytorch and serving with Flask and Docker

onnx-raspberry-pi-zero-wheel. ONNX wheel compiled on a Raspberry Pi Zero