kylepeterson777

GTM-Transformer

Official Implementation of paper: Well Googled is Half Done: Multimodal Forecasting of New FashionProduct Sales with Image-based Google Trends

flickr_scraper

Simple Flickr Image Scraper

LM_Memorization

Training data extraction on GPT-2

GFPGAN

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

OpenAIClipTutorial

multimodal

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

Multimodal-Transformer

[ACL'19] [PyTorch] Multimodal Transformer

mmfashion

Open-source toolbox for visual fashion analysis based on PyTorch

DeepFashion-MultiModal

A large-scale high-quality human dataset with rich multi-modal annotations

Multi-stream-CNN

Matlab example of Multi-stream-CNN

scikit-feature

open-source feature selection repository in python

tpot

A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.

mixmatch

IIC

Invariant Information Clustering for Unsupervised Image Classification and Segmentation

FusionNet-Pytorch

FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics

cvat

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

HybridSN

A keras based implementation of Hybrid-Spectral-Net as in IEEE GRSL paper "HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification".

RMDL

RMDL: Random Multimodel Deep Learning for Classification

tpu

Reference models and tools for Cloud TPUs.

yolact

A simple, fully convolutional model for real-time instance segmentation.

ELT

Ensemble Learning Toolbox

stockpredictionai

In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator. We use LSTM for the obvious reason that we are trying to predict time series data. Why we use GAN and specifically CNN as a discriminator? That is a good question: there are special sections on that later.

q-learning-trader

tabular q learning for trading

Event-Driven-Stock-Prediction-using-Deep-Learning

A deep learning method for event driven stock market prediction. Deep learning is useful for event-driven stock price movement prediction by proposing a novel neural tensor network for learning event embedding, and using a deep convolutional neural network to model the combined influence of long-term events and short-term events on stock price movements

darts

Differentiable architecture search for convolutional and recurrent networks

Tariq-Wall-2018-PLOS-MEDICINE

Code for building ML classifiers described in the paper

pylivetrader

Python live trade execution library with zipline interface.

research_public

Quantitative research and educational materials

DeepOSM

Train a deep learning net with OpenStreetMap features and satellite imagery.