Python keras:未启用“急切执行”时,Tensor对象不可编辑
我正在用Keras编写一个序列到序列的模型。出于某种原因,当我尝试在下面的函数中定义模型时:Python keras:未启用“急切执行”时,Tensor对象不可编辑,python,tensorflow,machine-learning,keras,rnn,Python,Tensorflow,Machine Learning,Keras,Rnn,我正在用Keras编写一个序列到序列的模型。出于某种原因,当我尝试在下面的函数中定义模型时: def define_GRU_models(encoder_input_dim, output_dim, activation, n_units): # define training encoder # ########################### # layer 1 encoder_inputs = Inp
def define_GRU_models(encoder_input_dim,
output_dim,
activation,
n_units):
# define training encoder #
###########################
# layer 1
encoder_inputs = Input(shape=encoder_input_dim)
l1_encoder = GRU(n_units,
name='l1_encoder',
return_sequences=True,
return_state=True)
l1_encoder_outputs, l1_encoder_state = l1_encoder(encoder_inputs)
# layer 2
l2_encoder = GRU(n_units,
name='l2_encoder',
return_state=True)
l2_encoder_outputs, l2_encoder_state = l2_encoder(l1_encoder_outputs)
# define training decoder #
###########################
# layer 1
decoder_inputs = Input(shape=(None, output_dim))
l1_decoder_gru = GRU(int(n_units/2),
name='l1_decoder_gru',
return_sequences=True,
return_state=False)
l1_decoder_outputs, _ = l1_decoder_gru(decoder_inputs)
# layer 2
l2_decoder_gru = GRU(n_units,
name='l2_decoder_gru',
return_sequences=True,
return_state=False)
l2_decoder_outputs, _ = l2_decoder_gru(l1_decoder_outputs, initial_state=l1_encoder_state)
# layer 3
l3_decoder_gru = GRU(n_units,
name='l3_decoder_gru',
return_sequences=True,
return_state=False)
l3_decoder_outputs, _ = l3_decoder_gru(l2_decoder_outputs, initial_state=l2_encoder_state)
# layer 4
l4_decoder_gru = GRU(int(n_units/2),
name='l4_decoder_gru',
return_state=False )
l4_decoder_outputs, _ = l4_decoder_gru(l3_decoder_outputs)
decoder_dense = Dense(output_dim, name='decoder_dense', activation=activation)
decoder_outputs = decoder_dense(l4_decoder_outputs)
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)
return model
我发现这个错误:
Tensor objects are not iterable when eager execution is not enabled. To iterate over this tensor use tf.map_fn.
对于该行(第一解码器层):
我似乎在其他任何地方都找不到解决办法。我做错了什么?因为它似乎与keras的例子兼容
顺便说一句,
我的功能输入是:
(168, 12), 24, 'softmax', 128
问题在于
'l1\u解码器\u gru'
不返回其状态(即返回\u状态=False
)。它只有一个分配给l1\u解码器\u输出的输出张量
。因此,要解决此问题,请删除作业左侧的,
部分:
l1_decoder_outputs = l1_decoder_gru(decoder_inputs)
或者,您可以为'l1\u decoder\u gru'
层将return\u state
参数设置为True
(当然,如果这样做有意义,并且您可能需要在模型的另一部分中使用此层的状态)。同样的情况也适用于您在模型中定义和使用的其他GRU层
l1_decoder_outputs = l1_decoder_gru(decoder_inputs)