python - 如何保存最好的 hyperopt 优化的 keras 模型及其权重？

Question

我使用 hyperopt 优化了我的 keras 模型。现在我们如何将最佳优化的 keras 模型及其权重保存到磁盘。

我的代码:

from hyperopt import fmin, tpe, hp, STATUS_OK, Trials
from sklearn.metrics import roc_auc_score
import sys

X = []
y = []
X_val = []
y_val = []

space = {'choice': hp.choice('num_layers',
                    [ {'layers':'two', },
                    {'layers':'three',
                    'units3': hp.uniform('units3', 64,1024), 
                    'dropout3': hp.uniform('dropout3', .25,.75)}
                    ]),

            'units1': hp.choice('units1', [64,1024]),
            'units2': hp.choice('units2', [64,1024]),

            'dropout1': hp.uniform('dropout1', .25,.75),
            'dropout2': hp.uniform('dropout2',  .25,.75),

            'batch_size' : hp.uniform('batch_size', 20,100),

            'nb_epochs' :  100,
            'optimizer': hp.choice('optimizer',['adadelta','adam','rmsprop']),
            'activation': 'relu'
        }

def f_nn(params):   
    from keras.models import Sequential
    from keras.layers.core import Dense, Dropout, Activation
    from keras.optimizers import Adadelta, Adam, rmsprop

    print ('Params testing: ', params)
    model = Sequential()
    model.add(Dense(output_dim=params['units1'], input_dim = X.shape[1])) 
    model.add(Activation(params['activation']))
    model.add(Dropout(params['dropout1']))

    model.add(Dense(output_dim=params['units2'], init = "glorot_uniform")) 
    model.add(Activation(params['activation']))
    model.add(Dropout(params['dropout2']))

    if params['choice']['layers']== 'three':
        model.add(Dense(output_dim=params['choice']['units3'], init = "glorot_uniform")) 
        model.add(Activation(params['activation']))
        model.add(Dropout(params['choice']['dropout3']))    

    model.add(Dense(1))
    model.add(Activation('sigmoid'))
    model.compile(loss='binary_crossentropy', optimizer=params['optimizer'])

    model.fit(X, y, nb_epoch=params['nb_epochs'], batch_size=params['batch_size'], verbose = 0)

    pred_auc =model.predict_proba(X_val, batch_size = 128, verbose = 0)
    acc = roc_auc_score(y_val, pred_auc)
    print('AUC:', acc)
    sys.stdout.flush() 
    return {'loss': -acc, 'status': STATUS_OK}


trials = Trials()
best = fmin(f_nn, space, algo=tpe.suggest, max_evals=100, trials=trials)
print 'best: '
print best

Answer 1

Trials 类对象存储许多与 hyperopt 的每次迭代相关的信息。我们也可以要求这个对象保存训练好的模型。您必须对代码库进行一些小的更改才能实现此目的。

-- return {'loss': -acc, 'status': STATUS_OK}
++ return {'loss':loss, 'status': STATUS_OK, 'Trained_Model': model}

注意:'Trained_Model' 只是一个键，您可以使用任何其他字符串。

best = fmin(f_nn, space, algo=tpe.suggest, max_evals=100, trials=trials)
model = getBestModelfromTrials(trials)

从 trials 对象中检索经过训练的模型:

import numpy as np
from hyperopt import STATUS_OK
def getBestModelfromTrials(trials):
    valid_trial_list = [trial for trial in trials
                            if STATUS_OK == trial['result']['status']]
    losses = [ float(trial['result']['loss']) for trial in valid_trial_list]
    index_having_minumum_loss = np.argmin(losses)
    best_trial_obj = valid_trial_list[index_having_minumum_loss]
    return best_trial_obj['result']['Trained_Model']

注意:我在 Scikit-Learn 类(class)中使用了这种方法。