ehud baumatz's repositories
german-transformer-training
Plan and train German transformer models.
InstaRaider
Non-API script to download all public photos for any Instagram user
kaggle-past-solutions
A searchable compilation of Kaggle past solutions
minirocket
MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification
ML_ShipDetection
Detectron2 and FastAI based ship segmentation for Kaggle dataset.
mlconvgec2018
Code and model files for the paper: "A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction" (AAAI-18).
mongo-hadoop
MongoDB Connector for Hadoop
mysqldump-to-csv
A quickly-hacked-together Python script to turn mysqldump files to CSV files. Optimized for Wikipedia database dumps.
python-stdnum
A Python library to provide functions to handle, parse and validate standard numbers.
scrapy-splash
Scrapy+Splash for JavaScript integration
vowpal_wabbit
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.