dragen1860/MAML-Pytorch
dragen1860/MAML-Pytorch has 2,480 GitHub stars and 435 forks. GitHot measured -1 stars in 24 hours, -1 in 7 days, and -2 in 15 days. Last checked 2026-11-19 16:50 UTC. Last push 2019-05-16.
Gemessener Sternzuwachs
- in 24h
- -1
- in 7 days
- -1
- in 15 days
- -2
- in 1 month
- Verlauf wird gesammelt
Nettoänderungen in überlappenden Zeiträumen, keine Tagessummen. Fehlende Messwerte bleiben leer. Sterne zeigen Interesse, nicht Qualität.
Über uns
Elegant PyTorch implementation of paper Model-Agnostic Meta-Learning (MAML)
Maschinelles LernenREADME.md
OriginalMAML-Pytorch
PyTorch implementation of the supervised learning experiments from the paper: Model-Agnostic Meta-Learning (MAML).
Version 1.0: Both
MiniImagenetandOmniglotDatasets are supported! Have Fun~
Version 2.0: Re-write meta learner and basic learner. Solved some serious bugs in version 1.0.
For Tensorflow Implementation, please visit official HERE and simplier version HERE.
For First-Order Approximation Implementation, Reptile namely, please visit HERE.

Platform
- python: 3.x
- Pytorch: 0.4+
MiniImagenet
Howto
For 5-way 1-shot exp., it allocates nearly 6GB GPU memory.
miniimagenet/
├── images
├── n0210891500001298.jpg
├── n0287152500001298.jpg
...
├── test.csv
├── val.csv
└── train.csv
- modify the
pathinminiimagenet_train.py:
mini = MiniImagenet('miniimagenet/', mode='train', n_way=args.n_way, k_shot=args.k_spt,
k_query=args.k_qry,
batchsz=10000, resize=args.imgsz)
...
mini_test = MiniImagenet('miniimagenet/', mode='test', n_way=args.n_way, k_shot=args.k_spt,
k_query=args.k_qry,
batchsz=100, resize=args.imgsz)
to your actual data path.
- just run
python miniimagenet_train.pyand the running screenshot is as follows:
If your reproducation perf. is not so good, maybe you can enlarge your training epoch to get longer training. And MAML is notorious for its hard training. Therefore, this implementation only provide you a basic start point to begin your research.
and the performance below is true and achieved on my machine.
Benchmark
| Model | Fine Tune | 5-way Acc. | 20-way Acc. | ||
|---|---|---|---|---|---|
| 1-shot | 5-shot | 1-shot | 5-shot | ||
| Matching Nets | N | 43.56% | 55.31% | 17.31% | 22.69% |
| Meta-LSTM | 43.44% | 60.60% | 16.70% | 26.06% | |
| MAML | Y | 48.7% | 63.11% | 16.49% | 19.29% |
| Ours | Y | 46.2% | 60.3% | - | - |
Ominiglot
Howto
run python omniglot_train.py, the program will download omniglot dataset automatically.
decrease the value of args.task_num to fit your GPU memory capacity.
For 5-way 1-shot exp., it allocates nearly 3GB GPU memory.
Refer to this Rep.
@misc{MAML_Pytorch,
author = {Liangqu Long},
title = {MAML-Pytorch Implementation},
year = {2018},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/dragen1860/MAML-Pytorch}},
commit = {master}
}