All Projects → hiwonjoon → maml-tensorflow

hiwonjoon / maml-tensorflow

Licence: other
This repository implements the paper, Model-Agnostic Meta-Leanring for Fast Adaptation of Deep Networks.

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to maml-tensorflow

maml-rl-tf2
Implementation of Model-Agnostic Meta-Learning (MAML) applied on Reinforcement Learning problems in TensorFlow 2.
Stars: ✭ 16 (-5.88%)
Mutual labels:  maml, meta-learning
CS330-Stanford-Deep-Multi-Task-and-Meta-Learning
My notes and assignment solutions for Stanford CS330 (Fall 2019 & 2020) Deep Multi-Task and Meta Learning
Stars: ✭ 34 (+100%)
Mutual labels:  maml, meta-learning
tensorflow-maml
TensorFlow 2.0 implementation of MAML.
Stars: ✭ 79 (+364.71%)
Mutual labels:  maml, meta-learning
MeTAL
Official PyTorch implementation of "Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning" (ICCV2021 Oral)
Stars: ✭ 24 (+41.18%)
Mutual labels:  maml, meta-learning
mliis
Code for meta-learning initializations for image segmentation
Stars: ✭ 21 (+23.53%)
Mutual labels:  maml, meta-learning
PAML
Personalizing Dialogue Agents via Meta-Learning
Stars: ✭ 114 (+570.59%)
Mutual labels:  maml, meta-learning
MetaBIN
[CVPR2021] Meta Batch-Instance Normalization for Generalizable Person Re-Identification
Stars: ✭ 58 (+241.18%)
Mutual labels:  maml, meta-learning
meta-learning-progress
Repository to track the progress in Meta-Learning (MtL), including the datasets and the current state-of-the-art for the most common MtL problems.
Stars: ✭ 26 (+52.94%)
Mutual labels:  meta-learning
meta-SR
Pytorch implementation of Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs (Interspeech, 2020)
Stars: ✭ 58 (+241.18%)
Mutual labels:  meta-learning
geotrellis-server
Tools for building raster processing and display services
Stars: ✭ 65 (+282.35%)
Mutual labels:  maml
StyleSpeech
Official implementation of Meta-StyleSpeech and StyleSpeech
Stars: ✭ 161 (+847.06%)
Mutual labels:  meta-learning
pymfe
Python Meta-Feature Extractor package.
Stars: ✭ 89 (+423.53%)
Mutual labels:  meta-learning
MetaHeac
This is an official implementation for "Learning to Expand Audience via Meta Hybrid Experts and Critics for Recommendation and Advertising"(KDD2021).
Stars: ✭ 36 (+111.76%)
Mutual labels:  meta-learning
Nearest-Celebrity-Face
Tensorflow Implementation of FaceNet: A Unified Embedding for Face Recognition and Clustering to find the celebrity whose face matches the closest to yours.
Stars: ✭ 30 (+76.47%)
Mutual labels:  meta-learning
meta-interpolation
Source code for CVPR 2020 paper "Scene-Adaptive Video Frame Interpolation via Meta-Learning"
Stars: ✭ 75 (+341.18%)
Mutual labels:  meta-learning
metagenrl
MetaGenRL, a novel meta reinforcement learning algorithm. Unlike prior work, MetaGenRL can generalize to new environments that are entirely different from those used for meta-training.
Stars: ✭ 50 (+194.12%)
Mutual labels:  meta-learning
LearningToCompare-Tensorflow
Tensorflow implementation for paper: Learning to Compare: Relation Network for Few-Shot Learning.
Stars: ✭ 17 (+0%)
Mutual labels:  meta-learning
One-Shot-Learning-with-Siamese-Networks
Implementation of One Shot Learning using Convolutional Siamese Networks on Omniglot Dataset
Stars: ✭ 129 (+658.82%)
Mutual labels:  omniglot
mindware
An efficient open-source AutoML system for automating machine learning lifecycle, including feature engineering, neural architecture search, and hyper-parameter tuning.
Stars: ✭ 34 (+100%)
Mutual labels:  meta-learning
HebbianMetaLearning
Meta-Learning through Hebbian Plasticity in Random Networks: https://arxiv.org/abs/2007.02686
Stars: ✭ 77 (+352.94%)
Mutual labels:  meta-learning

MAML

Intro

This repository implements the paper, Model-Agnostic Meta-Leanring for Fast Adaptation of Deep Networks.

Requirements

  • Tensorflow (v1.3 or higher)
  • better_exceptions, tqdm, Pillow, etc.

Training statisitics

  • Sinusoid

    Sinusoide Result Red line - ground truth, Red dots - given observation, Blue line - predicted line after 1 sgd step

  • Omniglot

    • Omniglot Testing (multiple descent steps)

    Ominglot Result

    • valid_acc_{0,1} means accuracy after 1 and 2 SGD steps. The valid_acc is the accuracy after the weights are trained with 3 SGD steps.

Training

Download datasets

Downlaod Omniglot dataset from the link. Only images_background.zip and images_evalueation.zip are required.

Unzip on the directory (repository)/datasets/omniglot/, so the directory shoud looks like (repo)/datasets/omniglot/{images_background,images_evaluation}.

Run train

  • Run sinusoide: python sinusoide.py
  • Run omniglot: python omniglot.py

Change the hyperparameters accordingly as you want. Please check at the bottom of each script.

TODO

  • Mini Imagenet Training
  • Robotic Simulation.

Acknowledgement

  • Author's original implementation: link
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].