Model reset parameters

Hi,

I was working on cross validation/ splitting data using different seed points and then train a PyCOX model before averaging the result.

``for seed in SEEDS:

data, target = X1,Z1
X_train1,X_test,Z_train1,Z_test = train_test_split(data, target, test_size=0.25, random_state=seed)
X_train,X_val,Z_train,Z_val = train_test_split(X_train1,Z_train1, test_size=0.25, random_state=seed)

### there are some steps here and I posted the required sections.

log = model.fit(X_train, y_train, batch_size, epochs, callbacks,verbose, val_data=val, val_batch_size=batch_size)

##added the following to reset the parameters

for layer in model.children():
if hasattr(layer, 'reset_parameters'):
layer.reset_parameters()

For the first fold/split the result of c-index is always low and then after couple of SEEDS the performance kept growing up. Hence, i believe the training model was not re-initialized after training one fold.

Does anyone know how to fix this issue and reset/re-initialize model for every fold.

Thank you in advance.