无法解释指标标识符 - scikeras.wrappers.KerasRegressor

Question

我正在尝试使用 scikeras.wrappers.KerasRegressor 调整超参数，我遇到了如下所述的问题：

代码：

    # define a func to create an instance of lstm_model
def create_lstm_model():
    
    model = Sequential([
            LSTM(5, input_shape = (Xtrain.shape[1], Xtrain.shape[2]), dropout = 0.1, activation = 'tanh', return_sequences = True),
            LSTM(10, dropout = 0.05, activation = 'tanh'),
            Dense(5, activation = 'relu'),
            Dense(1)
        ])
    model.compile(optimizer = tf.keras.optimizers.Adam(), loss = tf.keras.losses.MeanSquaredError(), metrics = [keras.metrics.MeanSquaredError()])
    
    return model

#create the sklearn model for the network
model = KerasRegressor(build_fn = create_lstm_model, verbose = 1)

#param grid
batches = [16, 32]
epochs = [3, 4]

param_grid = dict(batch_size = batches, epochs = epochs)

grid = GridSearchCV(estimator = model,
                    param_grid = param_grid,
                    cv = 3)
grid.fit(Xtrain, ytrain, validation_data = (Xvalidation, yvalidation))

错误：

    fn_or_cls = keras_metric_get(metric)
  File "/home/aaa/Desktop/aaa/aaa/2024-gold-price-prediction-with-lstm-model/.venv/lib/python3.10/site-packages/keras/src/metrics/__init__.py", line 204, in get
    raise ValueError(f"Could not interpret metric identifier: {identifier}")
ValueError: Could not interpret metric identifier: loss

我从更复杂的代码开始，并在故障排除期间将其简化到最低限度。我什至试图从模型函数中删除指标。

您对我的代码有什么问题有什么建议吗？

Answer 1

由于您使用不同的库来实现两个不同的任务，因此该错误可能是由于两个库中的 Keras 后端版本不匹配造成的；我建议使用损失的名称作为字符串。

model.compile(optimizer = tf.keras.optimizers.Adam(), loss = tf.keras.losses.MeanSquaredError(), metrics = ['mean_squared_error'])