penningavery

penningavery's starred repositories

niftidataset

pytorch dataset class for reading and transforming NIfTI files

Language:Jupyter NotebookNOASSERTION6200

intensity-normalization

normalize the intensities of various MR image modalities

Language:PythonNOASSERTION29800

iwildcam_comp

iWildCam competition details

13800

fastai_sparse

3D augmentation and transforms of 2D/3D sparse data, such as 3D triangle meshes or point clouds in Euclidean space. Extension of the Fast.ai library to train Sub-manifold Sparse Convolution Networks

Language:Jupyter NotebookMIT5000

Catalyst-Inria-Segmentation-Example

An example project showing the power of Catalyst for training segmentation model for Inria Sattelite Segmentation Challenge

Language:PythonMIT4400

pytorch-toolbelt

PyTorch extensions for fast R&D prototyping and Kaggle farming

Language:PythonMIT149700

tsne-cuda

GPU Accelerated t-SNE for CUDA with Python bindings

Language:CudaBSD-3-Clause174600

ignite

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

Language:PythonBSD-3-Clause448300

Kaggle-Ensemble-Guide

Code for the Kaggle Ensembling Guide Article on MLWave

Language:Python153400

safitty

Safitty is a wrapper on JSON/YAML configs for Python

Language:PythonMIT3000

dfc2019

2019 IEEE GRSS Data Fusion Contest data, baselines, and metrics

Language:PythonMIT13400

point-cloud-annotation-tool

Language:C++MIT47100

darty

Data dependency manager

Language:PythonNOASSERTION2200

spotty

Training deep learning models on AWS and GCP instances

Language:PythonMIT49300

segmentation_models.pytorch

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Language:PythonMIT906000

catalyst

Accelerated deep learning R&D

Language:PythonApache-2.0324600

frs-cheat-sheet

Fiona-Rasterio-Shapely Cheat Sheet

BSD-3-Clause10200

geometry-collections

A bestiary of frightful and ungodly GeoJSON geometries

Language:PythonMIT900

machine_flow

Machine Flow enables visual execution and tracking of machine learning workflows. Users dynamically create dependency graphs, with each node responsible for executing a task and displaying results.

Language:JavaScript6300