GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → markdtw → matching-networks

markdtw / matching-networks

Licence: other
Matching Networks for one-shot learning in tensorflow (NIPS'16)

Programming Languages

python
139335 projects - #7 most used programming language

Labels

tensorflowfew-shot-learning

Projects that are alternatives of or similar to matching-networks

attMPTI
[CVPR 2021] Few-shot 3D Point Cloud Semantic Segmentation
Stars: ✭ 118 (+118.52%)
Mutual labels:  few-shot-learning
LaplacianShot
Laplacian Regularized Few Shot Learning
Stars: ✭ 72 (+33.33%)
Mutual labels:  few-shot-learning
Black-Box-Tuning
ICML'2022: Black-Box Tuning for Language-Model-as-a-Service
Stars: ✭ 99 (+83.33%)
Mutual labels:  few-shot-learning
simple-cnaps
Source codes for "Improved Few-Shot Visual Classification" (CVPR 2020), "Enhancing Few-Shot Image Classification with Unlabelled Examples" (WACV 2022), and "Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning" (Neural Networks 2022 - in submission)
Stars: ✭ 88 (+62.96%)
Mutual labels:  few-shot-learning
sib meta learn
Code of Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
Stars: ✭ 56 (+3.7%)
Mutual labels:  few-shot-learning
Few-NERD
Code and data of ACL 2021 paper "Few-NERD: A Few-shot Named Entity Recognition Dataset"
Stars: ✭ 317 (+487.04%)
Mutual labels:  few-shot-learning
awesome-few-shot-meta-learning
awesome few shot / meta learning papers
Stars: ✭ 44 (-18.52%)
Mutual labels:  few-shot-learning
FSL-Mate
FSL-Mate: A collection of resources for few-shot learning (FSL).
Stars: ✭ 1,346 (+2392.59%)
Mutual labels:  few-shot-learning
FewShotDetection
(ECCV 2020) PyTorch implementation of paper "Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild"
Stars: ✭ 188 (+248.15%)
Mutual labels:  few-shot-learning
bruno
a deep recurrent model for exchangeable data
Stars: ✭ 34 (-37.04%)
Mutual labels:  few-shot-learning
FUSION
PyTorch code for NeurIPSW 2020 paper (4th Workshop on Meta-Learning) "Few-Shot Unsupervised Continual Learning through Meta-Examples"
Stars: ✭ 18 (-66.67%)
Mutual labels:  few-shot-learning
one-shot-steel-surfaces
One-Shot Recognition of Manufacturing Defects in Steel Surfaces
Stars: ✭ 29 (-46.3%)
Mutual labels:  few-shot-learning
ganbert
Enhancing the BERT training with Semi-supervised Generative Adversarial Networks
Stars: ✭ 205 (+279.63%)
Mutual labels:  few-shot-learning
few shot dialogue generation
Dialogue Knowledge Transfer Networks (DiKTNet)
Stars: ✭ 24 (-55.56%)
Mutual labels:  few-shot-learning
LearningToCompare-Tensorflow
Tensorflow implementation for paper: Learning to Compare: Relation Network for Few-Shot Learning.
Stars: ✭ 17 (-68.52%)
Mutual labels:  few-shot-learning
Learning-To-Compare-For-Text
Learning To Compare For Text , Few shot learning in text classification
Stars: ✭ 38 (-29.63%)
Mutual labels:  few-shot-learning
MLMAN
ACL 2019 paper:Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification
Stars: ✭ 59 (+9.26%)
Mutual labels:  few-shot-learning
renet
[ICCV'21] Official PyTorch implementation of Relational Embedding for Few-Shot Classification
Stars: ✭ 72 (+33.33%)
Mutual labels:  few-shot-learning
WARP
Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming. Outperforming `GPT-3` on SuperGLUE Few-Shot text classification. https://aclanthology.org/2021.acl-long.381/
Stars: ✭ 66 (+22.22%)
Mutual labels:  few-shot-learning
pytorch-meta-dataset
A non-official 100% PyTorch implementation of META-DATASET benchmark for few-shot classification
Stars: ✭ 39 (-27.78%)
Mutual labels:  few-shot-learning
View All Similar Projects ➔

Matching Networks for One Shot Learning

Tensorflow implementation of Matching Networks for One Shot Learning by Vinyals et al.

Prerequisites

Data

Preparation

  1. Download and extract omniglot dataset, modify omniglot_train and omniglot_test in utils.py to your location.

  2. First time training will generate omniglot.npy to the directory. The shape should be (1632, 80, 28, 28, 1) , meaning 1623 classes, 20 * 4 90-degree-transforms (0, 90, 180, 270), height, width, channel. 1200 classes used for training and 423 used for testing.

Train

python main.py --train

Train from a previous checkpoint at epoch X:

python main.py --train --modelpath=ckpt/model-X

Check out tunable hyper-parameters:

python main.py

Test

python main.py --eval

Notes

  • The model will test the evaluation accuracy after every epoch.
  • As the paper indicated, training on Omniglot with FCE does not do any better but I still implemented them (as far as I'm concerned there are no repos that fully implement the FCEs by far).
  • The authors did not mentioned the value of time steps K in FCE_f, in the sited paper, K is tested with 0, 1, 5, 10 as shown in table 1.
  • When using the data generated by myself (through utils.py), the evaluation accuracy at epoch 100 is around 82.00% (training accuracy 83.14%) without data augmentation.
  • Nevertheless, when using data provided by zergylord in his repo, this implementation can achieve up to 96.61% accuracy (training 97.22%) at epoch 100.
  • Issues are welcome!

Resources

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].