1

我想用 Keras 调谐器对 Keras 模型进行超参数调整。

import tensorflow as tf
from tensorflow import keras
import keras_tuner as kt

def model_builder(hp):

  model = keras.Sequential()
  model.add(keras.layers.Flatten(input_shape=(28, 28)))

  hp_units = hp.Int('units', min_value=32, max_value=512, step=32)
  model.add(keras.layers.Dense(units=hp_units, activation='relu'))
  model.add(keras.layers.Dense(10))

  hp_learning_rate = hp.Choice('learning_rate', values=[1e-2, 1e-3, 1e-4])

  model.compile(optimizer=keras.optimizers.Adam(learning_rate=hp_learning_rate),
                loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
                metrics=['accuracy'])

  return model

tuner = kt.Hyperband(model_builder,
                     objective='val_accuracy',
                     max_epochs=10,
                     factor=3)

tuner.search(train_X, train_y, epochs=50)

到目前为止，一切都很好。但是，我还想定义一些模型参数（如输入图像尺寸）作为输入参数model_builder，我一无所知，该怎么做：

def model_builder(hp, img_dim1, img_dim2):

  model = keras.Sequential()
  model.add(keras.layers.Flatten(input_shape=(img_dim1, img_dim2)))
...

和

tuner = kt.Hyperband(model_builder(img_dim1, img_dim2),
                     objective='val_accuracy',
                     max_epochs=10,
                     factor=3)

似乎不起作用。如何喂给img_dim1, img_dim2模型以外的东西hp？

4

1 回答 1

0

一个简单的解决方案是在 python 中使用“部分函数”，如下所示：

from functools import partial

#...

model_builder_ready = partial(model_builder, img_dim1 = value1, img_dim2 = value2)

tuner = kt.Hyperband(model_builder_ready,
                     objective='val_accuracy',
                     max_epochs=10,
                     factor=3)
于 2021-10-31T22:18:26.370 回答