MAML-TensorFlow
MAML-TensorFlow copied to clipboard
dragen1860
Faster and elegant TensorFlow Implementation of paper: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
If it is faster with ``` mv label+"*" label ``` ?
the code for main.py train iterations is 600000 but the guide you present is 60000 ? i can not understamd
It looks like the repo is set up to reproduce the bottom-left-most cell in Table 1 of the the MAML paper, which has 1-shot 5-way miniimagenet test accuracy of 48.70...
Hello, Thanks for the code. I have a question regarding testing strategy. I trained model and run the with --test parameter. During test time I can see from the output...
Metadata
Owner
Metadata
Faster and elegant TensorFlow Implementation of paper: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks