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 | Most Recent Commit | # Commits |
---|
This repo contains the code for the following paper: https://openreview.net/pdf?id=rJY0-Kcll
The following libaries are necessary:
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
For questions about miniImagenet format, please contact Sachin Ravi at email given in the paper.