如何检查Keras中的lambda层是否被捕捉 - Tensorflow

Question

因此，当我在Keras中运行以下代码时，模型起作用：

def transformer_code(inputLayer):
    hparams = transformer.transformer_base()
    encoder=transformer.TransformerEncoder(hparams,  mode=tf.estimator.ModeKeys.TRAIN)
    x = keras.backend.expand_dims(inputLayer, axis=2)
    y = encoder({"inputs": x, "targets": 0, "target_space_id": 0})
    y = keras.backend.squeeze(y[0], 2)
    return y

def trainModel(args, trainInput, trianOutput, testInput, testOutput, taskName, tags):
inputLayer = keras.layers.Input(shape=(len(trainInput[0]),
            len(trainInput[0][0])), dtype='float32')

inputAfterDense = keras.layers.Dense(512, activation='relu')(inputLayer)

crfLayer = CRF(len(tags), sparse_target=True, name='result')

y = keras.layers.Lambda(transformer_code)(inputAfterDense )
modelPred = crfLayer(y)

model = keras.Model(inputs=inputLayer, outputs=modelPred)
model.compile(
    optimizer='adam',
    loss = {'result': crfLayer.loss_function},
    metrics={'result': crfLayer.accuracy}
    )
print 'finish model setting'
print model.summary()

但如果我去掉致密层

inputAfterDense=路缘石.层.密（512，activation='relu'）（输入层）

训练中断，预测精度一直接近零。在

我怀疑lambda层没有被Keras抓到？我怎么检查？在

Answer 1

我不确定您现在是否已经解决了您的问题，但它可能是Lambda层不是最合适的变压器层类型。根据文件：

For simple, stateless custom operations, you are probably better off using layers.core.Lambda layers. But for any custom operation that has trainable weights, you should implement your own layer.

因此，最好编写自己的Keras层。在