Onur Kaplan

disgenet. Processing the DisGeNET database of disease–gene association

probabilistic-wind-power-forecasting. Probabilistic Wind Power Forecasting with R

one_shot_text_labeling. code and data for paper "One-shot Text Field Labeling using Attention and BeliefPropagation for Structure Information Extraction"

text2painting. Convert text into beautiful artistic images

cml. ♾️ CML - Continuous Machine Learning | CI/CD for ML

CascadeTabNet. This repository contains the code and implementation details of the CascadeTabNet paper "CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents"

hair-dye. Neural Network for Dying Hair💈

PortraitNet. Code for the paper "PortraitNet: Real-time portrait segmentation network for mobile device" @ CAD&Graphics2019

face-parsing.PyTorch. Using modified BiSeNet for face parsing in PyTorch

shapely. Manipulation and analysis of geometric objects

geos. Geometry Engine, Open Source

Turkish-Bert-NLP-Pipeline. Bert-base NLP pipeline for Turkish, Ner, Sentiment Analysis, Question Answering etc.

Background-Matting. Background Matting: The World is Your Green Screen

bbox. Python library for 2D/3D bounding boxes

superstring.py. A fast and memory-optimized string library for heavy-text manipulation in Python

3d-wind-turbine-power-curve-model. Dynamical Three Dimensional Wind Turbine Power Curve Model and IEC Corrections

mpad. Message Passing Attention Networks for Document Understanding

spleeter. Deezer source separation library including pretrained models.

Real-Time-Voice-Cloning. Clone a voice in 5 seconds to generate arbitrary speech in real-time

cpp-base64. base64 encoding and decoding with c++

nimtorch. PyTorch - Python + Nim

googletest. GoogleTest - Google Testing and Mocking Framework

torchbearer. torchbearer: A model fitting library for PyTorch

ESRNN-GPU. PyTorch GPU implementation of the ES-RNN model for time series forecasting

albumentations. Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

pytorch-fid. Compute FID scores with PyTorch.

DILATE. Code for our NeurIPS 2019 paper "Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models"

mirror. Visualisation tool for CNNs in pytorch

Deep-Flow-Guided-Video-Inpainting. pytorch implementation for "Deep Flow-Guided Video Inpainting"(CVPR'19)

DocProj. Document Rectification and Illumination Correction using a Patch-based CNN

CRAFT-pytorch. Official implementation of Character Region Awareness for Text Detection (CRAFT)

seamseg. Seamless Scene Segmentation

the-incredible-pytorch. The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

fonduer. A knowledge base construction engine for richly formatted data

label-studio. Label Studio is a multi-type data labeling and annotation tool with standardized output format

INQ-pytorch. A PyTorch implementation of "Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights"

i-librarian. Legacy I, Librarian - collaborative PDF manager. Not maintained, new version is at https://github.com/mkucej/i-librarian-free

signature-recognition. Verify the authenticity of handwritten signatures through digital image processing and neural networks. ✍️

fsociety. fsociety Hacking Tools Pack – A Penetration Testing Framework

voxelmorph. Unsupervised Learning for Image Registration

InvoiceNet. Deep neural network to extract intelligent information from invoice documents.

brainstorm. Implementation of "Data augmentation using learned transforms for one-shot medical image segmentation"

scikit-onnx-fastapi-example. Example project to predict housing pricing by using scikit, onnx and fastapi.

signature_extractor. A super lightweight image processing algorithm for detection and extraction of overlapped handwritten signatures on scanned documents using OpenCV and scikit-image.

handwriting-generation. Implementation of handwriting generation with use of recurrent neural networks in tensorflow. Based on Alex Graves paper (https://arxiv.org/abs/1308.0850).

FixRes. This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423

autoclint. A specially designed light version of Fast AutoAugment

twint. An advanced Twitter scraping & OSINT tool written in Python that doesn't use Twitter's API, allowing you to scrape a user's followers, following, Tweets and more while evading most API limitations.

receipt-scanner. a machine learning implementation of OCR

torch2trt. convert torch module to tensorrt network or tvm function

GoodNews. Good News Everyone! - CVPR 2019

hocr-tools. Tools for manipulating and evaluating the hOCR format for representing multi-lingual OCR results by embedding them into HTML.

wavetorch. 🌊 Numerically solving and backpropagating through the wave equation

nativefier. Make any web page a desktop application

equivariant-transformers. Equivariant Transformer (ET) layers are image-to-image mappings that incorporate prior knowledge on invariances with respect to continuous transformations groups (ICML 2019). Paper: https://arxiv.org/abs/1901.11399

boundary-loss. Official code for "Boundary loss for highly unbalanced segmentation", runner-up for best paper award at MIDL 2019. Extended version in MedIA, volume 67, January 2021.

invoice2data. Extract structured data from PDF invoices

locating-objects-without-bboxes. PyTorch code for "Locating objects without bounding boxes" - Loss function and trained models

tnn. Biologically-realistic recurrent convolutional neural networks

python-exercises. Python exercises

pykliep. A density ratio estimator package for python using the KLIEP algorithm.

lime. Lime: Explaining the predictions of any machine learning classifier

tensorwatch. Debugging, monitoring and visualization for Python Machine Learning and Data Science

Morpheus. Contextual Lemmatization and Morphological Tagging in 100 different languages. A Participant System for SigMorphon2019 Task 2

pix2pixHD. Synthesizing and manipulating 2048x1024 images with conditional GANs

vid2vid. Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

pachyderm. Data-Centric Pipelines and Data Versioning

CycleGAN. Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

receipt-parser-legacy. A supermarket receipt parser written in Python using tesseract OCR

whatwordwhere. Tooling to extract data from scanned paper forms OCR-ed by Tesseract using the HOCR standard.

hocrviewer-mirador. View HOCR files with Mirador

flowpoints_ml. An intuitive approach to creating deep learning models

retinanet-examples. Fast and accurate object detection with end-to-end GPU optimization

interpret. Fit interpretable models. Explain blackbox machine learning.

brusta. PyTorch model serving project

HandwritingRecognitionSystem. Handwriting Recognition System based on a deep Convolutional Recurrent Neural Network architecture

Pytorch-Model-to-TensorRT. Python

deepwriting. Code for `DeepWriting: Making Digital Ink Editable via Deep Generative Modeling` paper

Ax. Adaptive Experimentation Platform

tesseract. Tesseract Open Source OCR Engine (main repository)

leptonica. Leptonica is an open source library containing software that is broadly useful for image processing and image analysis applications. The official github repository for Leptonica is: danbloomberg/leptonica. See leptonica.org for more documentation.

ARU-Net. Python

PyLaia. A deep learning toolkit specialized for handwritten document analysis

Laia. Laia: A deep learning toolkit for HTR based on Torch

pageDistanceBasedContourGenerator. Program that calculates the extraction polygon of present text lines given an existing baseline in the page file

TextRecognitionDataGenerator. A synthetic data generator for text recognition

morph-net. Fast & Simple Resource-Constrained Learning of Deep Network Structure

deep-voice-conversion. Deep neural networks for voice conversion (voice style transfer) in Tensorflow

document-layout-analysis. A simple document layout analysis using Python-OpenCV

translate. Translate - a PyTorch Language Library

spdlog. Fast C++ logging library.

Invisibility_Cloak. This is a fun application of image processing which enables you to experience the magic of an invisibility cloak. Let's make our childhood fantasy of using an invisibility cloak come true.

lfai-landscape. 🌄 Open Source AI & Data Landscape - provides overview of top tier projects in the open source AI and Data ecosystem, shows projects through GitHub data, funding or market cap, first and last commits, contributor count and much other information.

CTCDecoder. Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.

KnightOnline. OpenKO is an open source version of the old school Knight Online MMORPG. Specifically designed for version 1.298.

warp-transducer. A fast parallel implementation of RNN Transducer.

start_follow_read. Python

crow. Crow is very fast and easy to use C++ micro web framework (inspired by Python Flask)

tensorflow_cpp_object_detection_web_server. This is an example how to run a TensorFlow object detection model as web server in TensorFlow C++ API.

Deep-Learning-in-Production. In this repository, I will share some useful notes and references about deploying deep learning-based models in production.

semantic-release. :package::rocket: Fully automated version management and package publishing

cz-cli. The commitizen command line utility. #BlackLivesMatter

loss-landscape. Code for visualizing the loss landscape of neural nets

cpp-pytorch. A bite of cpp api in PyTorch-1.0

MNIST_Pytorch_python_and_capi. This is an example of how to train a MNIST network in Python and run it in c++ with pytorch 1.0

shap. A game theoretic approach to explain the output of any machine learning model.

P2PaLA. Page to PAGE Layout Analysis Tool

prophet. Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.

ctcdecode. PyTorch CTC Decoder bindings

USBuildingFootprints. Computer generated building footprints for the United States

pynamical. Model, simulate, and visualize discrete nonlinear dynamical systems, chaos, and fractals

osmnx. Download, model, analyze, and visualize street networks and other geospatial features from OpenStreetMap.

torchdiffeq. Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

DeOldify. A Deep Learning based project for colorizing and restoring old images (and video!)

dhSegment. Generic framework for historical document processing

DeepColoring. Instance Segmentation by Deep Coloring

mobile-semantic-segmentation. Real-Time Semantic Segmentation in Mobile device

dlib. A toolkit for making real world machine learning and data analysis applications in C++

face_segmentation. Deep face segmentation in extremely hard conditions

face_recognition. The world's simplest facial recognition api for Python and the command line

maskrcnn-benchmark. Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

libdmtx. libdmtx Library

pytorch-EverybodyDanceNow. Implementation of Everybody Dance Now by pytorch

zxing-cpp. ZXing C++ Library

sourcerer-app. 🦄 Sourcerer app makes a visual profile from your GitHub and git repositories.

alrao. Implementation of "Learning with Random Learning Rates" in PyTorch.

kornia. 🐍 Geometric Computer Vision Library for Spatial AI

nntailoring. Capacity Estimation and Measuring Tools for Neural Networks

catalyst. Accelerated deep learning R&D

imgaug. Image augmentation for machine learning experiments.

FAI-PEP. Facebook AI Performance Evaluation Platform

attn2d. Pervasive Attention: 2D Convolutional Networks for Sequence-to-Sequence Prediction

rapidjson. A fast JSON parser/generator for C++ with both SAX/DOM style API

cxxopts. Lightweight C++ command line option parser

binfs. Library for embedding binary or text files into C++ programs

pytorch-deeplab-xception. DeepLab v3+ model in PyTorch. Support different backbones.

pytorch-qrnn. PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM

sru. Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

skiprnn_pytorch. A pytorch implementation of the paper: "Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks"

pytorch-playground. Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)

darts. Differentiable architecture search for convolutional and recurrent networks

pyGAM. [CONTRIBUTORS WELCOME] Generalized Additive Models in Python

Git-Loss-For-Deep-Face-Recognition. This repository contains code for my paper "Git Loss for Deep Face Recognition".

calamari. Line based ATR Engine based on OCRopy

pyprob. A probabilistic programming system for simulators and high-performance computing (HPC), based on PyTorch

hypergradient-descent. Hypergradient descent

ELF. ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation

wavefunction. Python package for calculating wavefunctions for 1D and 2D potentials.

KhatamiThesis. Jupyter Notebook

PyTorch-Encoding. A CV toolkit for my papers.

deepglobe2018. Python

TuSimple-DUC. Understanding Convolution for Semantic Segmentation

Autofocus-Layer. Autofocus Layer for Semantic Segmentation

pyGRN. Python GRNs, GRN evolutionary algorithm, and a GRN Keras layer

apex. A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

coord-conv-pytorch. All convolution operators replaced with coordinate convolutions

CoordConv-pytorch. Pytorch implementation of CoordConv introduced in 'An intriguing failing of convolutional neural networks and the CoordConv solution' paper. (https://arxiv.org/pdf/1807.03247.pdf)

ConvGRUCell-pytorch. Convolution GRU cell in PyTorch

vnet.pytorch. A PyTorch implementation for V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

tps_stn_pytorch. PyTorch implementation of Spatial Transformer Network (STN) with Thin Plate Spline (TPS)

SurfConv. Code & data for SurfConv paper at CVPR18

SSTD. Single Shot Text Detector with Regional Attention

pytorch-histogram-loss. PyTorch implementation for Histogram Loss

instance-segmentation-with-discriminative-loss-tensorflow. Tensorflow implementation of "Semantic Instance Segmentation with a Discriminative Loss Function"

AttentionDeepMIL. Implementation of Attention-based Deep Multiple Instance Learning in PyTorch

indrnn-pytorch. pytorch implementation of Independently Recurrent Neural Networks https://arxiv.org/abs/1803.04831

pytorch_compact_bilinear_pooling. Compact Bilinear Pooling for PyTorch

crpn. Corner-based Region Proposal Network

caser_pytorch. A PyTorch implementation of Convolutional Sequence Embedding Recommendation Model (Caser)

spotlight. Deep recommender models using PyTorch.

RotEqNet. Rotational Equivariant Networks for PyTorch/Python

GRCNN-for-OCR. This is the implementation of the paper "Gated Recurrent Convolution Neural Network for OCR"

OCR-DETECTION-CTPN. OCR, CNN+LSTM (CTPN) for image text detection, tensorflow

cnngeometric_pytorch. CNNGeometric PyTorch implementation

OrganSegRSTN. An end-to-end coarse-to-fine framework for organ segmentation

Adversarial-Semisupervised-Semantic-Segmentation. Pytorch Implementation of "Adversarial Learning For Semi-Supervised Semantic Segmentation" for ICLR 2018 Reproducibility Challenge

kaggle_carvana_segmentation. Code for the 1st place model in Carvana Image Masking Challenge

Total-Text-Dataset. Total Text Dataset. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.

LSD-seg. Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation

frustum-pointnets. Frustum PointNets for 3D Object Detection from RGB-D Data

Autopilot. A simple self-driving car module for humans 🚘 🛣️

pointwise. Code for Pointwise Convolutional Neural Networks, CVPR 2018

STATS701W18. Data Analysis in Python

deepwaldo. Using MaskRCNN to solve Where's waldo

baselines. OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

dynamic-image-nets. Dynamic Image Networks for Action Recognition

hello-world. Hello world in every computer language. Thanks to everyone who contributes to this, make sure to see contributing.md for contribution instructions!

car-damage-detective. Assessing car damage with convolution neural networks for a personal auto claims expedition use case

crowdcount-cascaded-mtl. Single Image Crowd Counting (CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting)

crowdcount-mcnn. Single Image Crowd Counting via MCNN (Unofficial Implementation)

TernausNetV2. TernausNetV2: Fully Convolutional Network for Instance Segmentation

footballNotifier. A Python application that sends you a SMS when the football team you support scores.

DeepLeague. (Open Source) Computer Vision + Deep Learning + League of Legends

DeepTextSpotter. Python

sampleRNN_ICLR2017. SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

hdbscan. A high performance implementation of HDBSCAN clustering.

CDTM-Deep-Learning-Drones. Course Material for CDTM Deep Learning Drones Course

PhotoGoalNavigation_2015. Vision based target navigation for Parrot AR DRONE. Uses epipolar geometry methods to compute the target position of the quadcopter based on the current location and target image provided.

ObjectDetection. This work was done as part of my thesis at Technical University of Munich. The goal of this thesis was to do object detection using Fully Convolutional Network. Full Report of this work can be found here: https://www.dropbox.com/s/hq5y2vxqo0r0ddn/ObjectDetectionThesisReport.pdf?dl=0