Question

self.embed = Sequential([Embedding(9488, output_dim=512,input_length=14),
                                Activation('relu'),
                                    Dropout(0.5)], name='embed.0')

self.fc_embed = Sequential([Dense(512, input_shape=(10,2048)),
                                    Activation('relu'),
                                    Dropout(0.5)], name='fc_embed.0')

inputs_bedding = Input(shape=(10,))
xt = self.embed(inputs_bedding)

input_feats = Input(shape=(10,2048))
fc_feats = self.fc_embed(input_feats)

fc_feats_new = K.reshape(fc_feats, [fc_feats.shape[1], fc_feats.shape[2]])
xt_new = K.reshape(xt, [xt.shape[1], xt.shape[2]])

 prev_h = state[0][-1] (shape is (10,512))
 att_lstm_input = Concatenate([prev_h, fc_feats_new, xt_new], axis=1)
 lstm, h_att, c_att = LSTM(units=512, name='core.att_lstm', return_state=True)(att_lstm_input)
 model = Model([input_feats, inputs_att, inputs_bedding], lstm)
 model.summary()

这是我得到的错误：

File "copy_eval.py", line 165, in <module>
model1 = TopDownModel.forward(fc_feats, att_feats, seq, att_masks)

文件“ /home/ubuntu/misc/customize_keras.py”，向前127行 lstm，h_att，c_att = LSTM（单位= 512，名称='core.att_lstm'，return_state = True）（att_lstm_input）调用中的文件“ /usr/local/lib/python2.7/dist-packages/keras/layers/recurrent.py”，第500行返回超级（RNN，自我）。调用（输入，** kwargs）在调用中，文件“ /usr/local/lib/python2.7/dist-packages/keras/engine/topology.py”，第575行 self.assert_input_compatibility（输入）在assert_input_compatibility中的文件“ /usr/local/lib/python2.7/dist-packages/keras/engine/topology.py”，行448 str（输入）+'。图层的所有输入' ValueError：层core.att_lstm的输入不是符号张量。收到的类型：。完整输入：[]。该层的所有输入都应为张量。

要获得更多输入，如何将它们合并为一个输出？

Answer 1

串联应用作图层，如下所示：

att_lstm_input = Concatenate(axis=1)([prev_h, fc_feats_new, xt_new])

Keras中的更多输入和一个输出问题

1 个答案: