Michal Lukac's Projects
Useful extra functionality for TensorFlow 2.x maintained by SIG-addons
Anchor optimization for RetinaNet.
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
Object detection, 3D detection, and pose estimation using center point detection:
My certificates from Coursera, ...
C++ implementation of RDT protocol, clientserver architecture,...
Lua compiler to IFJ course at Brno University of Technology implemented in C.
Code for confusion matrix in d3 js.
A TensorFlow implementation of https://github.com/bgshih/crnn
Netlogo simulation of diabetes mellitus type 2.
FaceXlib aims at providing ready-to-use face-related functions based on current STOA open-source methods.
Server side session extension for Flask
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
Image augmentation for machine learning experiments.
Prediction model for Kaggle/Rossmann competition.
Keras implementation of RetinaNet object detection.
A Material Design theme for MkDocs
Momentum Contrast for Unsupervised Visual Representation Learning
Models and examples built with TensorFlow
Gui application of Petri nets simulator written in C++/Qt.
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
Tensorflow 1.X implementation of Restricted Boltzman Machine(RBM) and Autoencoder with layerwise pretraining.
A Tensorflow SqueezeNet implementation
A synthetic data generator for text recognition