learned_optimization: Training and evaluating learned optimizers in JAX

Last update: Dec 30, 2022

Related tags

Overview

learned_optimization: Training and evaluating learned optimizers in JAX

learned_optimization is a research codebase for training learned optimizers. It implements hand designed and learned optimizers, tasks to meta-train and meta-test them on, and outer-training algorithms such as ES and PES.

Quick Start Colab Notebooks

Introduction notebook:
Creating custom tasks:

The fastest way to get started is to copy the Introduction notebook, and experiment using a free accelerator in colab (go to Runtime -> Change runtime type in colab to select a TPU or GPU backend).

Local Installation

We strongly recommend using virtualenv to work with this package.

pip3 install virtualenv
git clone [email protected]:google/learned_optimizers.git
cd learned_optimizers
python3 -m venv env
source env/bin/activate
pip install -e .

Then run the tests to make sure everything is functioning properly.

python3 -m nose

If something is broken please file an issue and we will take a look!

Disclaimer

learned_optimization is not an official Google product.

learned_optimization: Training and evaluating learned optimizers in JAX

Related tags

Overview

learned_optimization: Training and evaluating learned optimizers in JAX

Quick Start Colab Notebooks

Local Installation

Disclaimer

Owner

Google

Prototype-based Incremental Few-Shot Semantic Segmentation

U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection

Implementation of Segnet, FCN, UNet , PSPNet and other models in Keras.

PyImpetus is a Markov Blanket based feature subset selection algorithm that considers features both separately and together as a group in order to provide not just the best set of features but also the best combination of features

Reinforcement Learning with Q-Learning Algorithm on gym's frozen lake environment implemented in python

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing.

Code for Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions

Tensorflow/Keras Plug-N-Play Deep Learning Models Compilation

Code for our WACV 2022 paper "Hyper-Convolution Networks for Biomedical Image Segmentation"

This repository contains the implementations related to the experiments of a set of publicly available datasets that are used in the time series forecasting research space.

E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation

Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

Randomized Correspondence Algorithm for Structural Image Editing

Just playing with getting CLIP Guided Diffusion running locally, rather than having to use colab.

(ICCV 2021) PyTorch implementation of Paper "Progressive Correspondence Pruning by Consensus Learning"

ivadomed is an integrated framework for medical image analysis with deep learning.

Official PyTorch implementation and pretrained models of the paper Self-Supervised Classification Network

Image process framework based on plugin like imagej, it is esay to glue with scipy.ndimage, scikit-image, opencv, simpleitk, mayavi...and any libraries based on numpy

The official implementation of Theme Transformer

Implementation of the paper Scalable Intervention Target Estimation in Linear Models (NeurIPS 2021), and the code to generate simulation results.

learned_optimization: Training and evaluating learned optimizers in JAX

Related tags

Overview

learned_optimization: Training and evaluating learned optimizers in JAX

Quick Start Colab Notebooks

Local Installation

Disclaimer

Owner

Google

Prototype-based Incremental Few-Shot Semantic Segmentation

U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection

Implementation of Segnet, FCN, UNet , PSPNet and other models in Keras.

PyImpetus is a Markov Blanket based feature subset selection algorithm that considers features both separately and together as a group in order to provide not just the best set of features but also the best combination of features

Reinforcement Learning with Q-Learning Algorithm on gym's frozen lake environment implemented in python

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren*, Raymond A. Yeh*, Alexander G. Schwing.

Code for Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions

Tensorflow/Keras Plug-N-Play Deep Learning Models Compilation

Code for our WACV 2022 paper "Hyper-Convolution Networks for Biomedical Image Segmentation"

This repository contains the implementations related to the experiments of a set of publicly available datasets that are used in the time series forecasting research space.

E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation

Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

Randomized Correspondence Algorithm for Structural Image Editing

Just playing with getting CLIP Guided Diffusion running locally, rather than having to use colab.

(ICCV 2021) PyTorch implementation of Paper "Progressive Correspondence Pruning by Consensus Learning"

ivadomed is an integrated framework for medical image analysis with deep learning.

Official PyTorch implementation and pretrained models of the paper Self-Supervised Classification Network

Image process framework based on plugin like imagej, it is esay to glue with scipy.ndimage, scikit-image, opencv, simpleitk, mayavi...and any libraries based on numpy

The official implementation of Theme Transformer

Implementation of the paper Scalable Intervention Target Estimation in Linear Models (NeurIPS 2021), and the code to generate simulation results.

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing.