Dimitris Kastaniotis's starred repositories
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
whisper.cpp
Port of OpenAI's Whisper model in C/C++
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
h2o-llmstudio
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/
lion-pytorch
🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
info8010-deep-learning
Lectures for INFO8010 Deep Learning, ULiège
hlb-CIFAR10
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
GenerativeImage2Text
GIT: A Generative Image-to-text Transformer for Vision and Language
RaccoonsVsCats
Train a Deep CNN using images acquired automatically from google search with Selenium
PythonUtilsForCaffe
Some very useful Python utilities for manipulating lmdb files for Caffe (append lmdb, inspect entries, etc)
CudaViaCmake
This is a very simple project using CMake in order to create a project for compiling cuda with cpp code.
OpenCV_examples
Some simple but very usefull OpenCV examples
pytorch-mobilenet
PyTorch MobileNet Implementation of "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications"
STEM_MachineLearningClass
Interdisciplinary Approach to Science, Technology, Engineering and Mathematics - STEM in Education- Lectures site
TorchDemos
Some torch demos based on official torch examples with some extra features