Áron Hoffmann

`SafeDataset.__getitem__` memoizes the dataset items, with no parameter to change this. This makes the assumption that the dataset will always fit in the memory. Remove the `@memoize` line, and the...

I tried adding a bool attribute to the `memoize` class, that would make its `__call__` skip the lookup. The idea is that you could use it as a property of...

`periphery scan -- -sdk iphonesimulator` worked for me. (My workspace and scheme are specified in the .yml file)

I had the same issue. The problem is that you are using the TensorFlow version of Keras (`from tensorflow import keras`), while the library uses the standalone version (`import keras`)....

That works for me too. I realised that it gave me 0.0 because my label tensor was sparse (as opposed to one-hot)