Regularized Greedy Forest Regularized Greedy Forest (RGF) is a tree ensemble machine learning method described in this paper. RGF can deliver better results than gradient boosted decision trees (GBDT) on a number of datasets and it has been used to win a few Kaggle competitions. Unlike the traditional boosted decision tree approach, RGF works directly with the underlying forest structure. RGF integrates two ideas: one is to include tree-structured regularization into the learning formulation; and the other is to employ […]

Python package for Bayesian Machine Learning with scikit-learn API Installing & Upgrading package pip install https://github.com/AmazaspShumik/sklearn_bayes/archive/master.zip pip install –upgrade https://github.com/AmazaspShumik/sklearn_bayes/archive/master.zip Algorithms ARD Models Relevance Vector Regression (version 2.0) code, tutorial Relevance Vector Classifier (version 2.0) code, tutorial Type II Maximum Likelihood ARD Linear Regression code Type II Maximum Likelihood ARD Logistic Regression code, tutorial Variational Relevance Vector Regression

Simple machine learning library / 簡單易用的機器學習套件 Installation Tutorial Algorithm Perceptron Perceptron Binary Classification Learning Algorithm Perceptron Multi Classification Learning Algorithm Pocket Perceptron Binary Classification Learning Algorithm Pocket Perceptron Multi Classification Learning Algorithm Regression Linear Regression Learning Algorithm Linear Regression Binary Classification Learning Algorithm Linear Regression Multi Classification Learning Algorithm Ridge Regression Learning Algorithm Ridge Regression Binary Classification Learning Algorithm Ridge Regression Multi Classification Learning Algorithm Kernel Ridge Regression Learning Algorithm Kernel Ridge Regression Binary Classification    

py_neuromodulation The py_neuromodulation toolbox allows for real time capable processing of multimodal electrophysiological data. The primary use is movement prediction for adaptive deep brain stimulation. Find the documentation here https://neuromodulation.github.io/py_neuromodulation/ for example usage and parametrization. Setup For running this toolbox first create a new virtual conda environment: conda env create –file=env.yml –user The main modules include running real time enabled feature preprocessing based on iEEG BIDS data. Different features can be enabled/disabled and parametrized in the `https://github.com/neuromodulation/py_neuromodulation/blob/main/pyneuromodulation/nm_settings.json>`_. The current implementation […]

lazycluster is a Python library intended to liberate data scientists and machine learning engineers by abstracting away cluster management and configuration so that they are able to focus on their actual tasks. Especially, the easy and convenient cluster setup with Python for various distributed machine learning frameworks is emphasized. Highlights High-Level API for starting clusters: DASK Hyperopt More lazyclusters (e.g. Ray, PyTorch, Tensorflow, Horovod, Spark) to come … Lower-level API for: Managing Runtimes or RuntimeGroups to: A-/synchronously execute RuntimeTasks by […]

BytePS is a high performance and general distributed training framework. It supports TensorFlow, Keras, PyTorch, and MXNet, and can run on either TCP or RDMA network. BytePS outperforms existing open-sourced distributed training frameworks by a large margin. For example, on BERT-large training, BytePS can achieve ~90% scaling efficiency with 256 GPUs (see below), which is much higher than Horovod+NCCL. In certain scenarios, BytePS can double the training speed compared with Horovod+NCCL. Performance We show our experiment on BERT-large training, which […]

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch. Torchmeta contains popular meta-learning benchmarks, fully compatible with both torchvision and PyTorch’s DataLoader. Features A unified interface for both few-shot classification and regression problems, to allow easy benchmarking on multiple problems and reproducibility. Helper functions for some popular problems, with default arguments from the literature. An thin extension of PyTorch’s Module, called MetaModule, that simplifies the creation of certain meta-learning models (e.g. gradient based meta-learning methods). See […]

This repository contains the implementation of the paper: Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy NetworksICCV 2021 (Oral) If you find our code or paper useful, please consider citing @inproceedings{tang2021sign, title={SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks}, author={Tang, Jiapeng and Lei, Jiabao and Xu, Dan and Ma, Feiying and Jia, Kui and Zhang, Lei}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, year={2021} } Contact Jiapeng Tang for questions, comments and reporting bugs. Installation […]

This repo contains model, demo, and test codes of our paper: CPF: Learning a Contact Potential Field to Model the Hand-Object InteractionLixin Yang, Xinyu Zhan, Kailin Li, Wenqiang Xu, Jiefeng Li, Cewu LuICCV 2021 1. Get our code: $ git clone –recursive https://github.com/lixiny/CPF.git $ cd CPF 2. Set up your new environment: $ conda env create -f environment.yaml $ conda activate cpf 3. Download asset files Down load our [assets.zip] and unzip it as an assets/ folder. Download the MANO […]

Adversarial-Patch-Training Code for the paper: Sukrut Rao, David Stutz, Bernt Schiele. (2020) Adversarial Training Against Location-Optimized Adversarial Patches. In: Bartoli A., Fusiello A. (eds) Computer Vision – ECCV 2020 Workshops. ECCV 2020. Lecture Notes in Computer Science, vol 12539. Springer, Cham. https://doi.org/10.1007/978-3-030-68238-5_32 Setup Requirements Python 3.7 or above PyTorch scipy h5py scikit-image scikit-learn Optional requirements To use script to convert data to HDF5 format torchvision Pillow pandas To use Tensorboard logging With the exception of Python and PyTorch, all requirements […]