Michal Lukac's starred repositories
GroundingDINO
Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
yolov8-face
yolov8 face detection with landmark
supervision
We write your reusable computer vision tools. 💜
gconv_experiments
Experiments with Group Equivariant Convolutional Networks
pytorch-gconv-experiments
Experiments with Group Equivariant Convolutions in PyTorch
tf2-keras-gcnn
Tensorflow 2 / tf.keras port of keras-gcnn.
gigagan-pytorch
Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs
gpt-engineer
Specify what you want it to build, the AI asks for clarification, and then builds it.
vue3-calendar-heatmap
A lightweight calendar heatmap Vue 3 component built on SVG, inspired by julienr114's vue-calendar-heatmap and github's contribution calendar graph
vue-calendar-heatmap
A lightweight calendar heatmap Vuejs component built on SVG, inspired by github's contribution calendar graph
vit-tensorflow
Vision Transformer Cookbook with Tensorflow
tensorflow-image-models
TensorFlow port of PyTorch Image Models (timm) - image models with pretrained weights.
transparent-background
This is a background removing tool powered by InSPyReNet (ACCV 2022)
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.