TypeError：缺少所需的位置参数。当使用Kerastuner调整Ann深学习模型时

Question

我正在使用人造神经网络（ANN）模型进行超参数调整刚刚使用 kerastuner 我想使用它来进行二进制分类。以下是我的代码：

import tensorflow as tf
from tensorflow import keras
from keras import Input
from keras.models import Sequential
from keras.layers import Dense, Flatten, Dropout, BatchNormalization
import keras_tuner as kt
from keras_tuner.tuners import RandomSearch
from keras_tuner.tuners import Hyperband
from keras_tuner import HyperModel

def build_model(hp):
    
    # Create a Sequential model
    model = tf.keras.Sequential()
    
    # Input Layer: The now model will take as input arrays of shape (None, 67). My dataset has 67 columns.
    model.add(tf.keras.Input(shape = (67,)))
    
    # Tune number of hidden layers and number of neurons 
    for i in range(hp.Int('num_layers', 1, 3)):
        hp_units = hp.Int(f'units_{i}', min_value = 32, max_value = 512, step = 32)
        model.add(Dense(units = hp_units, activation = 'relu'))
    
    # Output Layer
    model.add(Dense(units = 1, activation='sigmoid'))
    
    # Compile the model
    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.binary_crossentropy(), 
                  metrics = ["accuracy"]
                 )
    
    return model


# HyperBand algorithm from keras tuner
hpb_tuner = kt.Hyperband(
    hypermodel = build_model, 
    objective = 'val_accuracy', 
    max_epochs = 50, 
    factor = 3,
    seed = 42,
    executions_per_trial = 3,
    directory = 'ANN_Parameters_Tuning', 
    project_name = 'Medical Claim'
)

然后，我面对下面的问题：

TypeError                                 Traceback (most recent call last)
<ipython-input-114-b58f291b49ae> in <module>
      1 # HyperBand algorithm from keras tuner
      2 
----> 3 hpb_tuner = kt.Hyperband(
      4     hypermodel = build_model,
      5     objective = 'val_accuracy',

~\anaconda3\envs\medicalclaim\lib\site-packages\keras_tuner\tuners\hyperband.py in __init__(self, hypermodel, objective, max_epochs, factor, hyperband_iterations, seed, hyperparameters, tune_new_entries, allow_new_entries, **kwargs)
    373             allow_new_entries=allow_new_entries,
    374         )
--> 375         super(Hyperband, self).__init__(
    376             oracle=oracle, hypermodel=hypermodel, **kwargs
    377         )

~\anaconda3\envs\medicalclaim\lib\site-packages\keras_tuner\engine\tuner.py in __init__(self, oracle, hypermodel, max_model_size, optimizer, loss, metrics, distribution_strategy, directory, project_name, logger, tuner_id, overwrite, executions_per_trial)
    108             )
    109 
--> 110         super(Tuner, self).__init__(
    111             oracle=oracle,
    112             hypermodel=hypermodel,

~\anaconda3\envs\medicalclaim\lib\site-packages\keras_tuner\engine\base_tuner.py in __init__(self, oracle, hypermodel, directory, project_name, logger, overwrite)
    101         self._display = tuner_utils.Display(oracle=self.oracle)
    102 
--> 103         self._populate_initial_space()
    104 
    105         if not overwrite and tf.io.gfile.exists(self._get_tuner_fname()):

~\anaconda3\envs\medicalclaim\lib\site-packages\keras_tuner\engine\base_tuner.py in _populate_initial_space(self)
    130 
    131         while True:
--> 132             self.hypermodel.build(hp)
    133 
    134             # Update the recored scopes.

<ipython-input-113-ac44a2da327d> in build_model(hp)
     18     hp_learning_rate = hp.Choice('learning_rate', values = [1e-2, 1e-3, 1e-4])
     19     model.compile(optimizer = keras.optimizers.Adam(learning_rate = hp_learning_rate), 
---> 20                   loss = keras.losses.binary_crossentropy(),
     21                   metrics = ["accuracy"]
     22                  )

~\anaconda3\envs\medicalclaim\lib\site-packages\tensorflow\python\util\traceback_utils.py in error_handler(*args, **kwargs)
    151     except Exception as e:
    152       filtered_tb = _process_traceback_frames(e.__traceback__)
--> 153       raise e.with_traceback(filtered_tb) from None
    154     finally:
    155       del filtered_tb

~\anaconda3\envs\medicalclaim\lib\site-packages\tensorflow\python\util\dispatch.py in op_dispatch_handler(*args, **kwargs)
   1088         if iterable_params is not None:
   1089           args, kwargs = replace_iterable_params(args, kwargs, iterable_params)
-> 1090         result = api_dispatcher.Dispatch(args, kwargs)
   1091         if result is not NotImplemented:
   1092           return result

TypeError: Missing required positional argument

即使我使用Randomsearch来自Kerastuner的也具有与上述追溯相同的错误。以下是我的RandomSearch的代码：

# RandomSearch algorithm from keras tuner
random_tuner = RandomSearch(
    hypermodel = build_model, 
    objective = 'val_accuracy', 
    max_trials = 50, 
    seed = 42,
    overwrite = True,
    executions_per_trial = 3,
    directory = 'ANN_Parameters_Tuning', 
    project_name = 'Medical Claim'
)