我的原始MLP模型如下：
def create_model(n_hidden_1, n_hidden_2, num_classes, num_features): # create the model model = Sequential() model.add(tf.keras.layers.InputLayer(input_shape=(num_features,))) model.add(tf.keras.layers.Dense(n_hidden_1, activation='sigmoid')) model.add(tf.keras.layers.Dense(n_hidden_2, activation='sigmoid')) model.add(tf.keras.layers.Dense(num_classes, activation='softmax')) # instantiate the optimizer opt = keras.optimizers.SGD(learning_rate=LEARNING_RATE) # compile the model model.compile( optimizer=opt, loss="categorical_crossentropy", metrics="categorical_accuracy" ) # return model return model为了调整上述模型，我创建了一个Keras-tuner模型如下：
def _model(hp): model = keras.Sequential() model.add(tf.keras.layers.InputLayer(input_shape=(6))) model.add(tf.keras.layers.Dense( hp.Int("dense_1_units", min_value=32, max_value=2048, step=32, default=128), activation="sigmoid" )) model.add(tf.keras.layers.Dense( hp.Int("dense_2_units", min_value=32, max_value=2048, step=32, default=128), activation="sigmoid" )) model.add(tf.keras.layers.Dense(3, activation="softmax")) model.compile( optimizer=tf.keras.optimizers.SGD( hp.Choice("learning_rate", values=[1e-1, 1e-2, 1e-3]) ), loss="categorical_crossentropy", metrics="categorical_accuracy" ) return model tuner = RandomSearch( _model, objective="val_accuracy", max_trials=10, overwrite=True, directory="tuner_random_directory", project_name="tuner_random_project_name", )我收到了以下输出：
user@server:~/ $ python3 tuner.pytraining data size : 1120988validation data size : 280246Search space summaryDefault search space size: 3dense_1_units (Int){'default': 128, 'conditions': [], 'min_value': 32, 'max_value': 2048, 'step': 32, 'sampling': None}dense_2_units (Int){'default': 128, 'conditions': [], 'min_value': 32, 'max_value': 2048, 'step': 32, 'sampling': None}learning_rate (Choice){'default': 0.1, 'conditions': [], 'values': [0.1, 0.01, 0.001], 'ordered': True}Search: Running Trial #1Hyperparameter |Value |Best Value So Fardense_1_units |1504 |?dense_2_units |1440 |?learning_rate |0.1 |?Epoch 1/235031/35031 [==============================] - 811s 23ms/step - loss: 0.5475 - categorical_accuracy: 0.7495 - val_loss: 0.5155 - val_categorical_accuracy: 0.7599WARNING:tensorflow:Can save best model only with val_accuracy available, skipping.Epoch 2/235031/35031 [==============================] - 807s 23ms/step - loss: 0.5091 - categorical_accuracy: 0.7650 - val_loss: 0.4943 - val_categorical_accuracy: 0.7751WARNING:tensorflow:Can save best model only with val_accuracy available, skipping.Traceback (most recent call last): File "my_tuner_app_tuner_random.py", line 229, in <module> tuner.search(train_x, train_y, epochs=2, validation_data=(validate_x, validate_y)) File "/home/user/.local/lib/python3.7/site-packages/keras_tuner/engine/base_tuner.py", line 144, in search self.run_trial(trial, *fit_args, **fit_kwargs) File "/home/user/.local/lib/python3.7/site-packages/keras_tuner/engine/multi_execution_tuner.py", line 103, in run_trial trial.trial_id, metrics=averaged_metrics, step=self._reported_step File "/home/user/.local/lib/python3.7/site-packages/keras_tuner/engine/oracle.py", line 224, in update_trial self._check_objective_found(metrics) File "/home/user/.local/lib/python3.7/site-packages/keras_tuner/engine/oracle.py", line 407, in _check_objective_found objective_names, metrics.keys()ValueError: Objective value missing in metrics reported to the Oracle, expected: ['val_accuracy'], found: dict_keys(['loss', 'categorical_accuracy', 'val_loss', 'val_categorical_accuracy'])user@server:~/ $为什么我会收到一个警告和一个值错误？
我如何解决这些问题？
回答：
我猜测您收到这个警告和错误的原因是，您必须在RandomSearch目标中使用与您的模型和Keras Tuner模型完全相同的度量标准，即categorical_accuracy。因此，您可以尝试：
tuner = RandomSearch( _model, objective="val_categorical_accuracy", max_trials=10, overwrite=True, directory="tuner_random_directory", project_name="tuner_random_project_name",)因为您希望最大化验证集的分类准确率。
