NotNANtoN

diffusion_gen

lucid-sonic-dreams

AuViMi

AuViMi stands for audio-visual mirror. The idea is to have CLIP generate its interpretation of what your webcam sees, combined with the words thare are spoken.

aigar

Replica of the online game agar.io, wrapped into an OpenAI gym wrapper

Deep-RL-Torch

Modular Deep Reinforcement Learning libary based on PyTorch

AudioCLIP

Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)

CLIP_playground

master_thesis

Roboro

An implementation of modular deep reinforcement learning algorithms (RL) from scratch. It is based on essential libraries such as pytorch-lightning for training organization, hydra for command line input and configuartions, and mlflow for experiment logging.

deep-daze

Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network)

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

stylegan2-ada-pytorch

StyleGAN2-ADA - Official PyTorch implementation

CV-Project-2020

A.I.gar

The Bachelor Project of Anton Orell Wiehe and Nil Stolt Ànso. We implement different reinforcement learning algorithms on a self-written agar.io clone and compare them.

adapter-transformers

Huggingface Transformers + Adapters = ❤️

AITemplate

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

BeatNet

BeatNet is state-of-the-art (Real-Time) and Offline joint music beat, downbeat, tempo, and meter tracking system using CRNN and particle filtering. (ISMIR 2021's paper implementation).

big-sleep

A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN

CLIP

Contrastive Language-Image Pretraining

CV

demucs

Code for the paper Hybrid Spectrogram and Waveform Source Separation

gym

A toolkit for developing and comparing reinforcement learning algorithms.

HAC-TowerBuilding

icp_prediction

instascrape

Powerful and flexible Instagram scraping library for Python, providing easy-to-use and expressive tools for accessing data programmatically

lora

Using Low-rank adaptation to quickly fine-tune diffusion models.

notnanton.github.io

POD_prediction

prioritized_sampling

train2generalize

Use MAML on a single dataset in order to generalize instead of matching patterns