Giters

sudharsan13296 / Hands-On-Meta-Learning-With-Python

Learning to Learn using One-Shot Learning, MAML, Reptile, Meta-SGD and more with Tensorflow

Home Page:https://www.amazon.com/Hands-Meta-Learning-Python-algorithms-ebook/dp/B07KJJHYKF/ref=sr_1_1?ie=UTF8&qid=1543222179&sr=8-1&keywords=meta+learning+hands+on

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Wrong directory path in the prototypical network demo notebook with omniglot

chen0040 opened this issue · comments

commented

The directory path in cell 13 of prototypical network omniglot demo (link) is wrong, it is missing "images" directory. As a result, the output of training is wrong (as can be seen in the notebook, the model is not learning at all during training since the train_data are all zero arrays due to it failing to load from the wrong directory. I was able to train the model correctly after fixing the wrong directory path in cell 13

commented

In section "Omniglot Character Set Classification Using Prototypical Network" , the accuracy in the model is always 0.16666 in the process of traning. So, Why does that happen? hope to get your reply，sincerely.