Stars
Prefect is a workflow orchestration framework for building resilient data pipelines in Python.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
This repository contains various examples of machine learning workflows.
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models
Simple and comprehensive tutorials in TensorFlow
The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.
Recurrent Geometric Networks for end-to-end differentiable learning of protein structure
Keras implementation of BERT with pre-trained weights
Jupyter notebooks for the code samples of the book "Deep Learning with Python"
Open standard for machine learning interoperability
A crash course in six episodes for software developers who want to become machine learning practitioners.
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
StyleGAN - Official TensorFlow Implementation
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)
Hadoop utilities to perform some PCA and IRLS using the MAHOUT libraries.
In-memory sparse matrix multiplication implemented in Java.
A web application for querying annotated microarray data projected in the top principal components
A web application for curation of MAGE-TAB documents.
A revision of my highschool project to draw the mandelbrot
Treelign is an application that visualizes a phylogenetic tree next to alignment data. It uses each position on the alignment to trace the tree to determine if the site is consistent or not.
SPlicing Interactive Environment - A tool used to view next generation sequence data with the primary purpose of identify patterns for alternative splicing.