Vladimir Iglovikov

TernausNet. UNet model with VGG11 encoder pre-trained on Kaggle Carvana dataset

robot-surgery-segmentation. Wining solution and its improvement for MICCAI 2017 Robotic Instrument Segmentation Sub-Challenge

TernausNetV2. TernausNetV2: Fully Convolutional Network for Instance Segmentation

retinaface. The remake of the https://github.com/biubug6/Pytorch_Retinaface

cloths_segmentation. Code for binary segmentation of cloths

kaggle_dstl_submission. Code for a winning model (3 out of 419) in a Dstl Satellite Imagery Feature Detection challenge

people_segmentation. Code for the model to segment people at the image

check_orientation. Model to check if image was rotated by 90, 180, 270 degrees.

angiodysplasia-segmentation. Wining solution and its further development for MICCAI 2017 Endoscopic Vision Challenge Angiodysplasia Detection and Localization

midv-500-models. Model for document segmentation trained on the midv-500-models dataset.

iglovikov_helper_functions. An unstructured set of helper functions

datasouls_antispoof. Code and pre-trained models for detecting spoofing attacks from images.

imread_benchmark. I/O benchmark for different image processing python libraries.

facemask_detection. Detection masks on faces.

kaggle_allstate. Repository with files somehow relevant to the Kaggle competition https://www.kaggle.com/c/allstate-claims-severity

iglovikov_segmentation. Semantic segmentation pipeline using Catalyst.

yolov5faceInference. Wrapper over Yolo5Face

base64ToImageConverters. Library for converting from RGB / GrayScale image to base64 and back.

retinafacemask. Detector for faces with masks / no masks on top of them.

retinaface_demo. Code for webapp for https://github.com/ternaus/retinaface

react_face_detection. Detect faces in react App.

kaggle_cdiscount. Python

kaggle_planet. Planet: Understanding the Amazon from Space

clip2onnx. Converts CLIP models to ONNX

insightfaceWrapper. Wrapper for easier inference for insightface

High-Resolution-Image-Inpainting-GAN. Python

lsun_2017. Large-Scale Scene Understanding Challenge at CVPR 2017

kaggle_alaska_2. https://www.kaggle.com/c/alaska2-image-steganalysis

spb_bridges. Jupyter Notebook

giana. WORK IN PROGRESS. Code for GIANA challenge

frog-rcnn. Mask RCNN by Heng CherKeng

Detectron.pytorch-1. A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

people_segmentation_demo. Python

kaggle_otto. Otto Group Product Classification Challenge

quest-qmc. Automatically exported from code.google.com/p/quest-qmc

kaggle_camera. https://www.kaggle.com/c/sp-society-camera-model-identification

kaggle_liberty. https://www.kaggle.com/c/liberty-mutual-group-property-inspection-prediction/data

clip2classdist. Use clip models to find inter and outer class distribution

nexar. https://www.getnexar.com/challenge-2

pytorch-faster-rcnn-1. 0.4 updated. Support cpu test and demo.

google-docstring-parser. A Python package for parsing and validating Google-style docstrings with type hints. Converts docstrings into structured dictionaries and validates type annotations. Requires paid license for non-Albumentations Team users.

ternaus-cleantext. Cleans text as in the CLIP model

pytorch-toolbelt. PyTorch extensions for fast R&D prototyping and Kaggle farming

add_logo. Adds pre-defined logo to the image

ternaus_chrome_extension. Chrome extension for Image and Reverse Image Search on Ternaus

cloths_segmentation_demo. Web App for binary cloths segmentation

onnx_model_optimizations. Python

nuscenes-devkit. Jupyter Notebook

grade-system.

example-get-started. Get started DVC project

docstring2json. Generate folder with parsed JSON from google docstrings

BayesianOptimization. A Python implementation of global optimization with gaussian processes.

rtb-papers. A collection of research and survey papers of real-time bidding (RTB) based display advertising techniques.

cityscapesScripts. README and scripts for the Cityscapes Dataset