dimkastan

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.

lowdb

Simple and fast JSON database

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

tinydb

TinyDB is a lightweight document oriented database optimized for your happiness :)

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!)

CutLER

Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"

SimCLR

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations by T. Chen et al.

silk

SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.

MCC

Multiview Compressive Coding for 3D Reconstruction

GenerativeImage2Text

GIT: A Generative Image-to-text Transformer for Vision and Language

PVN3D

Code for "PVN3D: A Deep Point-wise 3D Keypoints Hough Voting Network for 6DoF Pose Estimation", CVPR 2020

Wis3D

A web-based 3D visualization tool for 3D computer vision.

diffq

DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weights, in order to achieve a given trade-off between model size and accuracy.

DCLGAN

Code for Dual Contrastive Learning for Unsupervised Image-to-Image Translation, NTIRE, CVPRW 2021, oral.

SkyCam

sift-cnn-all-sky-images

RaccoonsVsCats

Train a Deep CNN using images acquired automatically from google search with Selenium

BMViT

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

websocket_tutorials