twitter/meta-learning-lstm

Name: meta-learning-lstm

Owner: Twitter, Inc.

Description: This repo contains the source code accompanying a scientific paper with the same name.

Created: 2016-10-11 06:57:42.0

Updated: 2018-01-15 10:40:01.0

Pushed: 2017-02-28 04:54:04.0

Homepage: null

Size: 295

Language: Lua

GitHub Committers

User	Most Recent Commit	# Commits

Other Committers

User	Email	Most Recent Commit	# Commits

README

meta-learning-lstm

This repo contains the code for the following paper: https://openreview.net/pdf?id=rJY0-Kcll

Dependencies

The following libaries are necessary:

• torch-autograd
• torch-ipc (use version from commit 'c1b2984c4c2dae085005d385996f4c0660173b27')
• torch-Dataset
• moses

Training

Splits corresponding to meta-training, meta-validation, and meta-testing are placed in data/miniImagenet/. Download corresponding imagenet images and place in folder called images and place folder in data/miniImagenet/.

To train a model:

rain/run-train.lua --task [1-shot or 5-shot task] --data config.imagenet --model [model name]

For example, to run matching-nets:

rain/run-train.lua --task config.5-shot-5-class --data config.imagenet --model config.baselines.train-matching-net

And, to run LSTM meta-learner for 5-shot task:

rain/run-train.lua --task config.5-shot-5-class --data config.imagenet --model config.lstm.train-imagenet-5shot

Contact

For questions about miniImagenet format, please contact Sachin Ravi at email given in the paper.