TransformerImplementation of Transformer model (originally from Attention is All You Need) applied to Time Series.
Stars: ✭ 273 (-83.36%)
Amazon Forest Computer VisionAmazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks
Stars: ✭ 346 (-78.92%)
Fast PytorchPytorch Tutorial, Pytorch with Google Colab, Pytorch Implementations: CNN, RNN, DCGAN, Transfer Learning, Chatbot, Pytorch Sample Codes
Stars: ✭ 346 (-78.92%)
Fraud DetectionCredit Card Fraud Detection using ML: IEEE style paper + Jupyter Notebook
Stars: ✭ 58 (-96.47%)
Kaggle CompetitionsThere are plenty of courses and tutorials that can help you learn machine learning from scratch but here in GitHub, I want to solve some Kaggle competitions as a comprehensive workflow with python packages. After reading, you can use this workflow to solve other real problems and use it as a template.
Stars: ✭ 86 (-94.76%)
Lstm chemImplementation of the paper - Generative Recurrent Networks for De Novo Drug Design.
Stars: ✭ 87 (-94.7%)
TimetkA toolkit for working with time series in R
Stars: ✭ 371 (-77.39%)
Data ScienceCollection of useful data science topics along with code and articles
Stars: ✭ 315 (-80.8%)
Practical PytorchGo to https://github.com/pytorch/tutorials - this repo is deprecated and no longer maintained
Stars: ✭ 4,329 (+163.8%)
Siridb ServerSiriDB is a highly-scalable, robust and super fast time series database. Build from the ground up SiriDB uses a unique mechanism to operate without a global index and allows server resources to be added on the fly. SiriDB's unique query language includes dynamic grouping of time series for easy analysis over large amounts of time series.
Stars: ✭ 438 (-73.31%)
TutorialsCatBoost tutorials repository
Stars: ✭ 563 (-65.69%)
Pytorch Pos TaggingA tutorial on how to implement models for part-of-speech tagging using PyTorch and TorchText.
Stars: ✭ 96 (-94.15%)
Seq2seq PytorchSequence to Sequence Models with PyTorch
Stars: ✭ 678 (-58.68%)
Practical seq2seqA simple, minimal wrapper for tensorflow's seq2seq module, for experimenting with datasets rapidly
Stars: ✭ 563 (-65.69%)
Uplot📈 A small, fast chart for time series, lines, areas, ohlc & bars
Stars: ✭ 6,808 (+314.87%)
Face Mask DetectionFace Mask Detection system based on computer vision and deep learning using OpenCV and Tensorflow/Keras
Stars: ✭ 774 (-52.83%)
Seq2seq Signal PredictionSignal forecasting with a Sequence-to-Sequence (seq2seq) Recurrent Neural Network (RNN) model in TensorFlow - Guillaume Chevalier
Stars: ✭ 890 (-45.76%)
PhildbTimeseries database
Stars: ✭ 25 (-98.48%)
HealthcheckHealth Check ✔ is a Machine Learning Web Application made using Flask that can predict mainly three diseases i.e. Diabetes, Heart Disease, and Cancer.
Stars: ✭ 35 (-97.87%)
Ml Dl ScriptsThe repository provides usefull python scripts for ML and data analysis
Stars: ✭ 119 (-92.75%)
Attentive Neural Processesimplementing "recurrent attentive neural processes" to forecast power usage (w. LSTM baseline, MCDropout)
Stars: ✭ 33 (-97.99%)
Anomaly detectionThis is a times series anomaly detection algorithm, implemented in Python, for catching multiple anomalies. It uses a moving average with an extreme student deviate (ESD) test to detect anomalous points.
Stars: ✭ 50 (-96.95%)
Mckinsey Smartcities Traffic PredictionAdventure into using multi attention recurrent neural networks for time-series (city traffic) for the 2017-11-18 McKinsey IronMan (24h non-stop) prediction challenge
Stars: ✭ 49 (-97.01%)
Doppelganger[IMC 2020 (Best Paper Finalist)] Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
Stars: ✭ 97 (-94.09%)
BtctradingTime Series Forecast with Bitcoin value, to detect upward/down trends with Machine Learning Algorithms
Stars: ✭ 99 (-93.97%)
Neural prophetNeuralProphet - A simple forecasting model based on Neural Networks in PyTorch
Stars: ✭ 1,125 (-31.44%)
Pycon Ua 2018Talk at PyCon UA 2018 (Kharkov, Ukraine)
Stars: ✭ 60 (-96.34%)
Linear Attention Recurrent Neural NetworkA recurrent attention module consisting of an LSTM cell which can query its own past cell states by the means of windowed multi-head attention. The formulas are derived from the BN-LSTM and the Transformer Network. The LARNN cell with attention can be easily used inside a loop on the cell state, just like any other RNN. (LARNN)
Stars: ✭ 119 (-92.75%)
DmmDeep Markov Models
Stars: ✭ 103 (-93.72%)
Brein Time UtilitiesLibrary which contains several time-dependent data and index structures (e.g., IntervalTree, BucketTimeSeries), as well as algorithms.
Stars: ✭ 94 (-94.27%)
Dog Breeds ClassificationSet of scripts and data for reproducing dog breed classification model training, analysis, and inference.
Stars: ✭ 105 (-93.6%)
CodesearchnetDatasets, tools, and benchmarks for representation learning of code.
Stars: ✭ 1,378 (-16.03%)
GriddbGridDB is a next-generation open source database that makes time series IoT and big data fast,and easy.
Stars: ✭ 1,587 (-3.29%)
Kaggle HousepricesKaggle Kernel for House Prices competition https://www.kaggle.com/massquantity/all-you-need-is-pca-lb-0-11421-top-4
Stars: ✭ 113 (-93.11%)
Ds bowl 2018Kaggle Data Science Bowl 2018
Stars: ✭ 116 (-92.93%)