BojanFaletic

fpga_ip

Collection of IP used in projects

RL2SL

Robust learning for neural net

IQ_net

Find limits of general inteligence in AI

AdventOfCode_2022

AI

CVPR22_marathon

Implementation of best papers from CVPR22

arch4life

CppTree

eye_grid

Partition input image into multiple augmented images

fewshot-font-generation

The unified repository for few-shot font generation methods. This repository includes FUNIT (ICCV'19), DM-Font (ECCV'20), LF-Font (AAAI'21) and MX-Font (ICCV'21).

fontGAN

galai

Model API for GALACTICA

GPT-text

Using GPT for PDF browsing

i3_megaS

From table data read mesh grid with bl touch

JsonParser

MA_HLS

HLS moving average filter

Matrix

simple matrix class, used for performing dot product.

parseTree

rebel

An algorithm that generalizes the paradigm of self-play reinforcement learning and search to imperfect-information games.

research

AI research

RWKV-Bot

RWKV-LM

RWKV is a RNN with transformer-level performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

SCINet

https://arxiv.org/pdf/2106.09305v2.pdf

sorting

Most common sorting algorithms

streamSerialization

structures

sudoku

fast sudoku, not very good but fast.

sudoku_solver

threading

yolor

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)