python - RNN 从哪里获取批量大小？

Question

我正在通过以下方式训练 RNN:

def create_rnn_model(stateful,length):
    model = Sequential()
    model.add(SimpleRNN(20,return_sequences=False,stateful=stateful,batch_input_shape=(1,length,1)))
    adam = optimizers.Adam(lr=0.001)
    model.add(Dense(1))
    model.compile(loss='mean_absolute_error', optimizer=adam, metrics=[root_mean_squared_error])
    print(model.summary())
    return model

和拟合

model_info = model_rnn_stateful.fit(x=x_train, y=y_train, validation_data=(x_test, y_test), batch_size=1, epochs=10,verbose=1)

并预测

predicted_rnn_stateful = model_rnn_stateful.predict(x_test)

但是当我预测它会抛出错误

ValueError: In a stateful network, you should only pass inputs with a number of samples that can be divided by the batch size. Found: 200 samples. Batch size: 32.

我没有指定 32。我不知道它来自哪里。我的批量大小仅为 1。感谢任何帮助。

编辑 我的脚本/IDE 中没有使用断点。谢谢

Answer 1

来自Keras documentation

• batch_size: Integer or None. Number of samples per gradient update. If unspecified, batch_size will default to 32.

1 可能是batch_size的错误值，因此它采用默认值32。尝试使用2或20作为batch_size