-
Preferred Networks
- Tokyo, Japan
- in/shotarosano
- https://www.kaggle.com/shotaro
Highlights
- Pro
Stars
A flexible framework of neural networks for deep learning
A Python toolbox for gaining geometric insights into high-dimensional data
ChainerCV: a Library for Deep Learning in Computer Vision
PFRL: a PyTorch-based deep reinforcement learning library
Examples for https://github.com/optuna/optuna
Python module for Simulated Annealing optimization
Python library for CMA Evolution Strategy.
Flexible Feature Engineering & Exploration Library using GPUs and Optuna.
Financial Portfolio Optimization Routines in Python
HandyRL is a handy and simple framework based on Python and PyTorch for distributed reinforcement learning that is applicable to your own environments.
Supplementary components to accelerate research and development in PyTorch
AutoGBT is used for AutoML in a lifelong machine learning setting to classify large volume high cardinality data streams under concept-drift. AutoGBT was developed by a joint team ('autodidact.ai')…
A Python wrapper of NVIDIA Video Loader (NVVL) with CuPy for fast video loading with Python
A toy hyperparameter optimization framework intended for understanding Optuna's internal design.
Elasticsearch integration into LangChain
4th Place Solution for Kaggle Competition: Quora Insincere Questions Classification
Machine learning tasks which are used with data pipeline library "luigi" and its wrapper "gokart".
⚡️ AllenNLP plugin for adding subcommands to use Optuna, making hyperparameter optimization easy
Tools for Optuna, MLflow and the integration of both.
Hyperparameter tuning with Optuna integrated tensor2tensor.
unofficial Python implementation to demonstrate PLaMo-100B