def augment_data_ext(x, y):
return data.augment_data_extended(x,
y,
saturation=aug_sat,
use_grayscale=aug_gs,
blur_amount=aug_blur,
num_random_rotations=aug_rr)
def cross_val(model, model_name, epochs=100, batch_size=8, verbose=2):
x, y = data.get_training_data()
kf = KFold(n_splits=5, shuffle=True, random_state=random_state)
histories = []
index = 0
best_losses = []
current_name = ''
for train_index, test_index in kf.split(x):
x_train, x_test = x[train_index], x[test_index]
y_train, y_test = y[train_index], y[test_index]
print('augment data')
x_train, y_train = data.augment_data_extended(x_train,
y_train,
num_random_rotations=3)
current_name = model_name + '_crossval-k' + str(index)
crt_history = fit(model,
x_train,
y_train,
epochs=epochs,
validation_data=(x_test, y_test),
checkpoint_suffix=current_name,
batch_size=batch_size,
verbose=verbose)
histories.append(crt_history)
best_epoch = get_min_index(crt_history.history['loss'])
best_loss = crt_history.history['loss'][best_epoch]
best_losses.append(best_loss)
model.load_weights(current_name + '.h5')
index += 1
# get used metrics
keys = histories[0].history.keys()
# average of metrics over all data splits
average = {}
for h in histories:
best_index = get_min_index(h.history['loss'])
for k in keys:
if k not in average:
average[k] = h.history[k][best_index]
else:
average[k] += h.history[k][best_index]
for k in average:
average[k] /= len(histories)
print("\nCross-Validation")
print("model_name: " + model_name)
print("optimizer: " + str(model.optimizer))
print("loss: " + str(model.loss))
print("epoches: 100, early_stopping_patience = 9")
print("cross_val_seed: " + str(random_state))
print("AVERAGE-METRICS")
print(average)
# reload best model weights
#best_model_index = get_min_index(best_losses)
#model.load_weights("cps/ckp_" + model_name + '_crossval-k' + str(best_model_index) + ".h5")
#print("best model: cps/ckp_" + model_name + '_crossval-k' + str(best_model_index) + ".h5")
create_sub(model, model_name)