Discover @gordicaleksa Open Source projects

Aleksa Gordić (@gordicaleksa)

gordicaleksa

Stars
5,805
Global Rank 4,446 (Top 0.2 %)
Followers 3,172
Following 4
Registered over 7 years ago
Most used languages

Python
52.4 %

C++
19.0 %

Jupyter Notebook
19.0 %

MATLAB
4.8 %

Shell
4.8 %
Location 🇷🇸 Serbia
Country Total Rank 5
Country Ranking

Jupyter Notebook
1

Python
2

MATLAB
4

C++
80

Shell
164

pytorch-GAT

My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!

Jupyter Notebook

pytorch-original-transformer

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.

Jupyter Notebook

get-started-with-JAX

The purpose of this repo is to make it easy to get started with JAX, Flax, and Haiku. It contains my "Machine Learning with JAX" series of tutorials (YouTube videos and Jupyter Notebooks) as well as the content I found useful while learning about the JAX ecosystem.

Jupyter Notebook

pytorch-GANs

My implementation of various GAN (generative adversarial networks) architectures like vanilla GAN (Goodfellow et al.), cGAN (Mirza et al.), DCGAN (Radford et al.), etc.

Open-NLLB

Effort to open-source NLLB checkpoints.

pytorch-deepdream

PyTorch implementation of DeepDream algorithm (Mordvintsev et al.). Additionally I've included playground.py to help you better understand basic concepts behind the algo.

Jupyter Notebook

pytorch-neural-style-transfer

Reconstruction of the original paper on neural style transfer (Gatys et al.). I've additionally included reconstruction scripts which allow you to reconstruct only the content or the style of the image - for better understanding of how NST works.

stable_diffusion_playground

Playing around with stable diffusion. Generated images are reproducible because I save the metadata and latent information. You can generate and then later interpolate between the images of your choice.

pytorch-learn-reinforcement-learning

A collection of various RL algorithms like policy gradients, DQN and PPO. The goal of this repo will be to make it a go-to resource for learning about RL. How to visualize, debug and solve RL problems. I've additionally included playground.py for learning more about OpenAI gym, etc.

pytorch-neural-style-transfer-johnson

Reconstruction of the fast neural style transfer (Johnson et al.). Some portions of the paper have been improved by the follow-up work like the instance normalization, etc. Checkout transformer_net.py's header for details.

serbian-llm-eval

Serbian LLM Eval.

pytorch-naive-video-neural-style-transfer

Create naive (no temporal loss) NST for videos with person segmentation. Just place your videos in data/, run and you get your stylized and segmented videos.

OpenGemini

Effort to open-source 10.5 trillion parameter Gemini model.

gordicaleksa

GitHub's new feature: repo with the same name as your GitHub name initialized with README.md will show on your landing page!

digital-image-processing

Projects I did for the Digital Image Processing course on my university

streamlit_playground

Simple Streamlit app.

Open-NLLB-stopes

A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) for the Open-NLLB effort.

MachineLearningMicrosoftPetnica

Problems I solved for Microsoft ML summer camp in Petnica, Serbia

competitive_programming

Contains algorithms and snippets I found useful when solving problems for TopCoder, Google Code Jam etc.

slovenian-llm-eval

Slovenian LLM Eval.

MicrosoftBubbleCup2018

My solutions for Bubble Cup 2018

.dotfiles

Configuration files for my vim editor, bash etc.

GoogleCodeJam2018

My solutions for Google Code Jam 2018