erik-koynov's repositories
facemaskdetection
kaggle face mask detection challenge
split4pandas
Easy splitting into train/test or k-forlds for data stored as pandas DataFrame, which to iterate on
augraphy
Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes
backboned-unet
Build U-Nets for segmentation from pre-trained TorchVision models.
dataset4objdet
Dataset class for processing different types of formats out-of-the-box for object detection. Should be compatible with my implementation of yolo and the pytorch implementation of faster rcnn.
dataset4textclass
Basic dataset class for text classificaiton with transformers
example_solutionsIBN
One or many example solutions I wrote as a tutor for the IBN lecture
invertransforms
A library which turns torchvision transformations invertible and replayable.
laws_preprocessing
Reformat Laws
nvidia-htop
A tool for enriching the output of nvidia-smi.
pytorch-classification-uncertainty
This repo contains a PyTorch implementation of the paper: "Evidential Deep Learning to Quantify Classification Uncertainty"
Smoothly-Blend-Image-Patches
Using a U-Net for image segmentation, blending predicted patches smoothly is a must to please the human eye.
xml2df
Convert nested xml files to pandas dataframes
yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
yolov7
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors