I've just started to learn Meta Learning reading the book Hands-On Meta Learning with Python.
I think I know the answer for my question, but I'm a little confuse about how to implement the algorithm with Keras.
This piece of code is from an example that uses U-NET:
from sklearn.model_selection import train_test_split # Split train and valid X_train, X_valid, y_train, y_valid = train_test_split(train_data, test_data, test_size=0.1, random_state=42) results = model.fit(X_train, y_train, batch_size=32, epochs=50,\ validation_data=(X_valid, y_valid))
My problem is with the fit method.
Reading the book I read:
...train on the support set and test on the query set...
So here, in a meta learning model, the
train_data is the Support Set, and the
test_data is the query set, isn't it?