for i in range(y_word_max_len):    sub_decoder_input = gather(main_decoder,(i))    # print(sub_decoder_input)    sub_decoder_input_repeated = RepeatVector(y_char_max_len)(sub_decoder_input)    sub_decoder = LSTM(256,return_sequences=True,name='sub_decoder')(sub_decoder_input_repeated)    sub_decoder_output = TimeDistributed(Dense(58,activation='softmax'),name='sub_decoder_output')(sub_decoder)    sub_decoder_output_reshaped = Reshape((1,y_char_max_len,58))(sub_decoder_output)    print("Sub decoder output is ",sub_decoder_output_reshaped)

我已经编写了上述代码片段，其中 y_word_max_len = 9

并且 main_decoder 是一个形状为 (None,9,256) 的张量

并且 y_char_max_len = 7

58 是我的输出大小，代码执行后输出的结果是

Sub decoder output is Tensor(“reshape_2/Reshape:0”, shape=(?, 1, 7, 58), dtype=float32)

Sub decoder output is Tensor(“reshape_3/Reshape:0”, shape=(?, 1, 7, 58), dtype=float32)

Sub decoder output is Tensor(“reshape_4/Reshape:0”, shape=(?, 1, 7, 58), dtype=float32)

Sub decoder output is Tensor(“reshape_5/Reshape:0”, shape=(?, 1, 7, 58), dtype=float32)

Sub decoder output is Tensor(“reshape_6/Reshape:0”, shape=(?, 1, 7, 58), dtype=float32)

Sub decoder output is Tensor(“reshape_7/Reshape:0”, shape=(?, 1, 7, 58), dtype=float32)

Sub decoder output is Tensor(“reshape_8/Reshape:0”, shape=(?, 1, 7, 58), dtype=float32)

Sub decoder output is Tensor(“reshape_9/Reshape:0”, shape=(?, 1, 7, 58), dtype=float32)

Sub decoder output is Tensor(“reshape_10/Reshape:0”, shape=(?, 1, 7, 58), dtype=float32)

现在我想将所有获得的9个张量拼接成一个结果张量，形状为

shape (?,9,7,58)

我该如何在Keras中实现这一点？谢谢

回答：

添加一个Concatenate层：

joined = Concatenate(axis=1)([sub1, sub2, sub3, sub4, sub5....])

为此，最好是创建一个子张量列表，并使用循环将结果添加到这个列表中：

subTensors = []for ..... :    #calculations    subTensors.append(sub_decoder_output_reshaped)joined = Concatenate(axis=1)(subTensors)