deep learning with kfold cross validation

Question

I am new into neural networks, I want to use K-fold cross-validation to train my neural network. I want to use 5 folds 50 epochs and a batch size of 64 I found a function in scikit for k-fold cross validation

model_selection.cross_val_score(model_kfold, x_train, y_train, cv=5)

and my code without cross validation is

history = alexNet_model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1,validation_data=(x_validation, y_validation))

I don't know how to implement this with batch size and epochs in python using keras and scikit. any idea?

Answer 1

Be sure to use test data when validating your model, not the same training data. Using training data to validate will bias your results.

In your example, I would use the KerasClassifier module instead of the numpy KFolds module.

from keras.wrappers.scikit_learn import KerasClassifier

After you've imported the module, your code would be (with results output:

evaluator=KerasClassifier(build_fn=baseline_model, epochs=50, batch_size=64)
kfold=KFold(n_splits=5, shuffle=True, random_state=random_seed)

results=cross_val_score(evaluator, x_test, onehot_y_test, cv=kfold)
print("Model: %.2f%% (%.2F%%)" % (results.mean()*100, results.std()*100))