python - 在 for 循环中创建新的 Sequential 模型（使用 Keras）

Question

我想尝试用不同的超参数训练我的模型，所以我设置了一系列嵌套的 for 循环来遍历它们。

model = None
batch_generator = None

for sequence_length in all_sequence_length:
    for label_periods in all_label_periods:
        for num_layers in all_num_layers:
            for num_units in all_num_units:
                loadFiles()
                createmodel()
                trainmodel()

第一次迭代创建了一个这样的模型：

Layer (type)                 Output Shape              Param #
=================================================================
cu_dnnlstm_1 (CuDNNLSTM)     (None, 100, 75)           45300
_________________________________________________________________
dropout_1 (Dropout)          (None, 100, 75)           0
_________________________________________________________________
cu_dnnlstm_2 (CuDNNLSTM)     (None, 100, 75)           45600
_________________________________________________________________
dropout_2 (Dropout)          (None, 100, 75)           0
_________________________________________________________________
cu_dnnlstm_3 (CuDNNLSTM)     (None, 100, 75)           45600
_________________________________________________________________
dropout_3 (Dropout)          (None, 100, 75)           0
_________________________________________________________________
cu_dnnlstm_4 (CuDNNLSTM)     (None, 100, 75)           45600
_________________________________________________________________
dropout_4 (Dropout)          (None, 100, 75)           0
_________________________________________________________________
cu_dnnlstm_5 (CuDNNLSTM)     (None, 100, 75)           45600
_________________________________________________________________
dropout_5 (Dropout)          (None, 100, 75)           0
_________________________________________________________________
dense_1 (Dense)              (None, 3)                 228
=================================================================

然后我打电话model.fit_generator()来训练模型并且执行得很好。然后在下一次循环迭代中再次创建模型，摘要如下所示：

Layer (type)                 Output Shape              Param #
=================================================================
cu_dnnlstm_6 (CuDNNLSTM)     (None, 100, 75)           45300
_________________________________________________________________
dropout_6 (Dropout)          (None, 100, 75)           0
_________________________________________________________________
cu_dnnlstm_7 (CuDNNLSTM)     (None, 100, 75)           45600
_________________________________________________________________
dropout_7 (Dropout)          (None, 100, 75)           0
_________________________________________________________________
cu_dnnlstm_8 (CuDNNLSTM)     (None, 100, 75)           45600
_________________________________________________________________
dropout_8 (Dropout)          (None, 100, 75)           0
_________________________________________________________________
cu_dnnlstm_9 (CuDNNLSTM)     (None, 100, 75)           45600
_________________________________________________________________
dropout_9 (Dropout)          (None, 100, 75)           0
_________________________________________________________________
cu_dnnlstm_10 (CuDNNLSTM)     (None, 100, 75)           45600
_________________________________________________________________
dropout_10 (Dropout)          (None, 100, 75)           0
_________________________________________________________________
dense_2 (Dense)              (None, 3)                 228
=================================================================

您会看到层 ID 增加了，这让我很惊讶，因为我为模型变量创建了一个新的 Sequential 模型，所以我希望得到与第一个相同的摘要。

当我打电话时，model.fit_generator()我收到此错误：

InvalidArgumentError（参见上面的回溯）：您必须为占位符张量“cu_dnnlstm_1_input”提供一个值，其 dtype 为 float 和 shape [?,100,74]

您会看到它需要一个 输入cu_dnnlstm_1_input，这是第一次迭代模型的输入，而不是第二个模型的 cu_dnnlstm_6 输入。我创建模型的代码是在一个函数中完成的：

def createmodel():

    global model

    model = Sequential()
    model.add( CuDNNLSTM(units=num_units, return_sequences=True, input_shape=(sequence_length, features_size) ) )

    for _ in range(num_layers):
        model.add( Dropout(dropout_rate) )
        model.add( CuDNNLSTM(units=num_units, return_sequences=True) )

    model.add( Dropout(dropout_rate) )
    model.add( CuDNNLSTM(units=num_units, return_sequences=False) )

    model.add( Dropout(dropout_rate) )
    model.add( Dense(labels_size) )

    model.compile(loss='mean_absolute_error', optimizer='adam')

    model.summary()

使用此函数训练模型：

def trainmodel():

    global model

    model.fit_generator(generator=batch_generator,
        epochs=num_epochs,
        steps_per_epoch=num_steps_per_epoch,
        validation_data=validation_data_tuple,
        callbacks=callbacks)

谁能发现我的“故意”错误？

标签： pythonneural-networkkeras

Answer 1

我想这是因为 Keras 试图在同一个张量流图上创建不同的模型。由于您的模型具有不同的架构，因此无法做到这一点。

尝试导入张量流：

import tensorflow as tf

并以这种方式修改您的循环：

for sequence_length in all_sequence_length:
    for label_periods in all_label_periods:
        for num_layers in all_num_layers:
            for num_units in all_num_units:
                graph = tf.Graph()
                with tf.Session(graph=graph):
                    loadFiles()
                    createmodel()
                    trainmodel()