Keras调谐器贝叶斯优化图误差

Question

本文试图利用keras调谐器库中提供的贝叶斯优化算法对卷积神经网络进行优化。

当我执行行：tuner_cnn.search(datagen.flow(X_trainRusReshaped,Y_trainRusHot), epochs=50, batch_size=256)时，我会遇到以下错误：InvalidArgumentError: Graph execution error

单向热编码y_train和y_test如下所示：

y_train = to_categorical(y_train)
y_test = to_categorical(y_test)

X_trainShape = X_train.shape[1]*X_train.shape[2]*X_train.shape[3]
X_testShape = X_test.shape[1]*X_test.shape[2]*X_test.shape[3]
X_trainFlat = X_train.reshape(X_train.shape[0], X_trainShape)
X_testFlat = X_test.reshape(X_test.shape[0], X_testShape)
# One-hot-encoding
Y_trainRusHot = to_categorical(Y_trainRus, num_classes = 2)
Y_testRusHot = to_categorical(Y_testRus, num_classes = 2)

我这样定义我的模特儿建造者：

datagen = ImageDataGenerator(
    featurewise_center=True,
    featurewise_std_normalization=True,
    rotation_range=180,
    horizontal_flip=True,vertical_flip = True)

def model_builder(hp):
  model = Sequential()
  #model.add(Input(shape=(50,50,3)))
  for i in range(hp.Int('num_blocks', 1, 2)):
    hp_padding=hp.Choice('padding_'+ str(i), values=['valid', 'same'])
    hp_filters=hp.Choice('filters_'+ str(i), values=[32, 64])

    model.add(Conv2D(hp_filters, (3, 3), padding=hp_padding, activation='relu', kernel_initializer='he_uniform', input_shape=(50, 50, 3)))
    model.add(MaxPooling2D((2, 2)))
    model.add(Dropout(hp.Choice('dropout_'+ str(i), values=[0.0, 0.1, 0.2])))
    model.add(Flatten())

    hp_units = hp.Int('units', min_value=25, max_value=150, step=25)
    model.add(Dense(hp_units, activation='relu', kernel_initializer='he_uniform'))
    model.add(Dense(10,activation="softmax"))
    hp_learning_rate = hp.Choice('learning_rate', values=[1e-2, 1e-3])
    hp_optimizer=hp.Choice('Optimizer', values=['Adam', 'SGD'])

    if hp_optimizer == 'Adam':
      hp_learning_rate = hp.Choice('learning_rate', values=[1e-2, 1e-3])

    elif hp_optimizer == 'SGD':
      hp_learning_rate = hp.Choice('learning_rate', values=[1e-2, 1e-3])
      nesterov=True
      momentum=0.9

    model.compile(loss=keras.losses.binary_crossentropy, optimizer=tf.keras.optimizers.Adam(learning_rate=hp_learning_rate), metrics=['accuracy'])
    return model

执行调谐器搜索：

tuner_cnn = kt.tuners.BayesianOptimization(
    model_builder,
    objective='val_loss',
    max_trials=100,
    directory='.',
    project_name='tuning-cnn')

tuner_cnn.search(datagen.flow(X_trainRusReshaped,Y_trainRusHot), epochs=50, batch_size=256)

我还试着做：

tuner_cnn.search(X_trainRusReshaped, Y_trainRusHot, epochs=80, validation_data=(X_testRusReshaped, Y_testRusHot), callbacks=[stop_early])

但这两种方法都行不通。有什么想法吗？

Answer 1

从完整的错误信息中，我能够缩小问题的来源。问题是您的上一个Dense层有10 units，这意味着您期望10 classes (您甚至选择了正确的激活函数，给定units的数量)。然而，Binary CrossEntropy作为loss。

所以要么使用10 classes，要么使用categorical或sparse categorical CrossEntropy，要么使用2 classes，因此损失确实是Binary CrossEntropy。