timohromadka Goto Github PK

3-style-solver

Rubik's cube learning tool to efficiently, effectively, and explainably generate 3-style algorithms (commutators) to take blindfold cubing to the next level.

advent_of_code

My solutions to the 2022 advent of code puzzles - https://adventofcode.com/

audio-ai-timeline

A timeline of the latest AI models for audio generation, starting in 2023!

audio-diffusion

Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.

audio-diffusion-pytorch

Audio generation using diffusion models, in PyTorch.

bld-helper

Tool for assisting in learning 3-cycle for blindfold speedcubing

cnc-controller-with-interface

datamaps

Code to experiment with and extend the methodology and findings in the paper: "Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics"

diffusion_distiller

🚀 PyTorch Implementation of "Progressive Distillation for Fast Sampling of Diffusion Models(v-diffusion)"

fadtk

A simple library for Fréchet Audio Distance (FAD) calculation

gen_music

MPhil Project - Timo Hromadka

google-research

Google Research

improved-diffusion

Release for Improved Denoising Diffusion Probabilistic Models

janestreetpuzzles

My solutions to jane street puzzles: https://www.janestreet.com/puzzles/

l101_training_dynamics

L101 Project: Investigating the shifting of training dynamics across model sizes and their impact on adversarial examples

l46_datamaps

L46 Project: Using datamaps and compression techniques for efficient knowledge distillation

l90-summarization

L90 - Practical #2 - Extractive Text Summarization Model

latent_prog_diffusion

opencv-tools

Tools and practice using OpenCV in python

polygonize

Beginning of code taken from my student account's repo

portfolio

Personal portfolio

pytorch-vae-tutorial

A simple tutorial of Variational AutoEncoders with Pytorch

r255_latent_dm_distillation

Investigation of the distillation technique proposed in the paper "Progressive Distillation for Fast Sampling of Diffusion Models", and its combination with latent space diffusion models.

scikit-learn-cm-bug

scikit-learn: bug fix to prevent confusion matrix from being 1x1 instead of NxN

tiny-audio-diffusion

A repository for generating and training short audio samples with unconditional waveform diffusion on accessible consumer hardware (<2GB VRAM GPU)

training_dynamics_cartography

L101 Research Project: Understanding How Training Dynamics Shift Across Model Sizes and Architectures.

transformer_abstractive_summarization

L90 - Practical #3 - Abstractive Text Summarization Model using a Transformer architecture

triangulization