Disappearing-People - Person removal from complex backgrounds over time.
Use tensorflow to implement a Deep Neural Network for real time lane detection mainly based on the IEEE IV conference paper "Towards End-to-End Lane Detectio.
The official pytorch implemention of the paper "Res2Net: A New Multi-scale Backbone Architecture"
This my implementation of CenterNet(Objects as Points) in pure TensorFlow.You can refer to the official code.
Free online math resources for Machine Learning
This is a Python (2 and 3) library that provides a webcam-based eye tracking system. It gives you the exact position of the pupils and the gaze direction, in real time.
StyleGAN2 - Official TensorFlow Implementation with practical improvements
Fast Waifu2x Video Upscaling.
giotto-tda is a high performance topological machine learning toolbox in Python built on top of scikit-learn and is distributed under the GNU AGPLv3 license.
Evaluating Weakly Supervised Object Localization Methods Right.
This repository contains some models for semantic segmentation and the pipeline of training and testing models, implemented in PyTorch.
A PyTorch implementation of Neighbourhood Components Analysis by J. Goldberger, G. Hinton, S. Roweis, R. Salakhutdinov.
a generalist algorithm for cellular segmentation
zmMagik will be a list of growing foo-magic things you can do with video images that ZM stores.
PyTorch Wrapper is a library that provides a systematic and extensible way to build, train, evaluate, and tune deep learning models using PyTorch.
Mac users warning : currently the addon does not work anymore on Mac because of an issue relative to Blender Mac build itself.
This codebase is created to build benchmarks for object detection in aerial images. It is modified from mmdetection.
CogDL-TensorFlow: The TensorFlow Implementation of CogDL. With Support from Professor Jie Tang.
code for Mesh R-CNN, an academic publication, presented at ICCV 2019.
Detecto is a Python package that allows you to build fully-functioning computer vision and object detection models with just 5 lines of code.
Easily develop state of the art time series models to forecast univariate data series. Simply load your data and select which models you want to test.
Haste is a CUDA implementation of fused LSTM and GRU layers with built-in DropConnect and Zoneout regularization.
This is a framework for running common deep learning models for point cloud analysis tasks against classic benchmark. It heavily relies on pytorch geometric and hydra core.
Bot Framework Composer is an integrated development tool for developers and multi-disciplinary teams to build bots and conversational experiences with the Microsoft Bot Framework.
Learning from Graph data using Keras and Tensorflow.