我想通过使用Kerastuner调整我的Keras模型。我遇到了一些调整批处理大小和epoch的代码片段,以及单独进行Kfold交叉验证的代码片段。我想同时做这些
批量大小和历元代码
class MyTuner(kerastuner.tuners.BayesianOptimization):
def run_trial(self, trial, *args, **kwargs):
# You can add additional HyperParameters for preprocessing and custom training loops
# via overriding `run_trial`
kwargs['batch_size'] = trial.hyperparameters.Int('batch_size', 32, 256, step=32)
kwargs['epochs'] = trial.hyperparameters.Int('epochs', 10, 30)
super(MyTuner, self).run_trial(trial, *args, **kwargs)
# Uses same arguments as the BayesianOptimization Tuner.
tuner = MyTuner(...)
# Don't pass epochs or batch_size here, let the Tuner tune them.
tuner.search(...)
交叉验证代码
import kerastuner
import numpy as np
from sklearn import model_selection
class CVTuner(kerastuner.engine.tuner.Tuner):
def run_trial(self, trial, x, y, batch_size=32, epochs=1):
cv = model_selection.KFold(5)
val_losses = []
for train_indices, test_indices in cv.split(x):
x_train, x_test = x[train_indices], x[test_indices]
y_train, y_test = y[train_indices], y[test_indices]
model = self.hypermodel.build(trial.hyperparameters)
model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs)
val_losses.append(model.evaluate(x_test, y_test))
self.oracle.update_trial(trial.trial_id, {'val_loss': np.mean(val_losses)})
self.save_model(trial.trial_id, model)
tuner = CVTuner(
hypermodel=my_build_model,
oracle=kerastuner.oracles.BayesianOptimization(
objective='val_loss',
max_trials=40))
x, y = ... # NumPy data
tuner.search(x, y, batch_size=64, epochs=30)
如何更改run_trial
以便这两种方法可以一起执行
目前没有回答
相关问题 更多 >
编程相关推荐