正在更新中。。。。。。
参考博客:
https://www.mutepad.com/2019/05/24/maml-%E8%AE%BA%E6%96%87%E5%8F%8A%E4%BB%A3%E7%A0%81%E9%98%85%E8%AF%BB%E7%AC%94%E8%AE%B0/
知乎:https://www.mutepad.com/2019/05/24/maml-%E8%AE%BA%E6%96%87%E5%8F%8A%E4%BB%A3%E7%A0%81%E9%98%85%E8%AF%BB%E7%AC%94%E8%AE%B0/
代码:https://github.com/dragen1860/MAML-Pytorch
论文地址:https://link.zhihu.com/?target=https%3A//arxiv.org/abs/1703.03400
MAML-pytorch:
首先看下网络结构:
可以看到是一个标准的四层卷积神经网络,size均为3*3*32
,后接relu、batchnorm以及maxpooling,最后将卷及结果扁平化。
config = [
('conv2d', [32, 3, 3, 3, 1, 0]),
('relu', [True]),
('bn', [32]),
('max_pool2d', [2, 2, 0]),
('conv2d', [32, 32, 3, 3, 1, 0]),
('relu', [True]),
('bn', [32]),
('max_pool2d', [2, 2, 0]),
('conv2d', [32, 32, 3, 3