a question about paper

[yangyangjuanjuan]

Hello, I read the paper "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks" and not clear about how the comparison was done between MAML and a pretrained network. Could you clarify my doubts? It says "P(T) is continuous, where the amplitude varies within [0.1, 5.0]", does it mean amplitude follows a uniform distribution? And I am also not clear about how MAML model was applied on test after training. According to the described algorithm, MAML need a batch of tasks to adjust its parameters, when do the comparison, there is only one sinusoid curve.

Thank you!

[ucasiggcas]

大佬你好，

1.我个人理解是这个p(T)是模型的某种分布 2.我也没看懂怎么测试的，甚至训练怎么进行的都不清楚，至少文章中的图没有复现，代码不对应

[cpzys2018]

大佬你好，

1.我个人理解是这个p(T)是模型的某种分布 2.我也没看懂怎么测试的，甚至训练怎么进行的都不清楚，至少文章中的图没有复现，代码不对应

训练的时候遇到问题 ： sample larger than population 你怎么解决

[ed830418]

@cpzys2018 我也碰到這個問題，但是解決了。 utils.py line 16

sampler = lambda x: random.sample(x, nb_samples) 改成: sampler = lambda x: random.sample(x, nb_samples if len(x) > nb_samples else len(x))