Tensorflow ValueError:数据基数不明确：x大小：1500500请提供共享相同第一维度的数据
我的seq2seq模型非常适合数据，但当我传递开始令牌并使用编码器状态初始化模型时，推断模型上的预测方法会给出上述错误 据我所知，编码器状态是维度（1500300），传递的令牌是（1,1300）。 这是我有史以来第一个seq2seq模型，我在互联网上寻找任何类似的问题，并将我的模型与官方keras文档上的keras seq2seq模型进行了比较 代码：Tensorflow ValueError:数据基数不明确：x大小：1500500请提供共享相同第一维度的数据,tensorflow,keras,deep-learning,recurrent-neural-network,seq2seq,Tensorflow,Keras,Deep Learning,Recurrent Neural Network,Seq2seq,我的seq2seq模型非常适合数据，但当我传递开始令牌并使用编码器状态初始化模型时，推断模型上的预测方法会给出上述错误 据我所知，编码器状态是维度（1500300），传递的令牌是（1,1300）。 这是我有史以来第一个seq2seq模型，我在互联网上寻找任何类似的问题，并将我的模型与官方keras文档上的keras seq2seq模型进行了比较 代码： encoder_inputs=Input(shape=(max_art_len,)) encoder_emb=Embedding(art_voc
encoder_inputs=Input(shape=(max_art_len,))
encoder_emb=Embedding(art_vocab_size,100,trainable=True,name='Encoder_Embedding_layer')
(encoder_inputs)
encoder_lstm1=LSTM(300,return_sequences=True,return_state=True,name='Encoder_LSTM1')
enclstm1_outputs,enclstm1_h,enclstm1_c=encoder_lstm1(encoder_emb)
decoder_inputs=Input(shape=(None,))
decoder_em=Embedding(sum_vocab_size,100,trainable=True,name='Decoder_Embedding_layer')
decoder_emb=decoder_em(decoder_inputs)
decoder_lstm1=LSTM(300,return_sequences=True,return_state=True,name='Decoder_LSTM1')
declstm1_output,declstm1_h,declstm1_c=decoder_lstm1(decoder_emb,initial_state=[enclstm1_h,enclstm1_c])
output_layer=TimeDistributed(Dense(sum_vocab_size,activation='softmax',name='softmax'))
output=output_layer(declstm1_output)
model=Model([encoder_inputs,decoder_inputs],output)
model.summary()
infencoder_model=Model(inputs=[encoder_inputs],outputs=[enclstm1_h,enclstm1_c])
infdecoder_model_state_input_h=Input(shape=(300,),name='infdec_I1')
infdecoder_model_state_input_c=Input(shape=(300,),name='infdec_I2')
infdeclstm1_output,infdec_h,infdec_c=decoder_lstm1(decoder_emb,initial_state=[infdecoder_model_state_input_h,
infdecoder_model_state_input_c
])
infdec_output=output_layer(infdeclstm1_output)
infdecoder_model=Model(inputs=[decoder_inputs]+[infdecoder_model_state_input_h,infdecoder_model_state_input_c],
outputs=[infdec_output]+[infdec_h,infdec_c])
def decode_sequence(inp_seq):
enc_h,enc_c=infencoder_model.predict(inp_seq)
tar_seq=np.zeros((1,1))
tar_seq[0,0]=sum_wordindex['start']
stop_loop=False
decoded_string=''
while not stop_loop:
dec_out,dec_h,dec_c=infdecoder_model.predict([tar_seq]+[enc_h,enc_c])
tar_token_index=np.argmax(dec_out[0,-1,:])
tar_token_word=sum_wordindex[tar_token_index]
if tar_token_word =='end' or len(decoded_string)>=max_art_len:
stop_loop=True
else:
decoded_string+=tar_token_word
tar_seq=np.zeros((1,1))
tar_seq[0,0]=tar_token_index
enc_h=dec_h
enc_c=dec_c
return decoded_string
def seq2art(inp_seq):
art=''
for i in range(len(inp_seq)):
if inp_seq[i]==0:
break
art+=reverse_art_index[inp_seq[i]]+' '
return art
def seq2sum(inp_seq):
summary=''
for i in range(len(inp_seq)):
if inp_seq[i]==0:
break
word=reverse_sum_index[inp_seq[i]]
summary+=word+' '
return summary
print('Example Articel : '+'\n',seq2art(padded_X_val[2]))
print('Example Summary : '+'\n',seq2sum(padded_Y_val[2]))
print('Predicted Summary : '+'\n',decode_sequence(padded_X_val[2]))
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-43-9ef680a87bdf> in <module>
1 print('Example Articel : '+'\n',seq2art(padded_X_val[2]))
2 print('Example Summary : '+'\n',seq2sum(padded_Y_val[2]))
----> 3 print('Predicted Summary : '+'\n',decode_sequence(padded_X_val[2]))
<ipython-input-41-c41e0caee91d> in decode_sequence(inp_seq)
11 while not stop_loop:
12
---> 13 dec_out,dec_h,dec_c=infdecoder_model.predict([tar_seq]+
[enc_h,enc_c])
14
15 tar_token_index=np.argmax(dec_out[0,-1,:])
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
128 raise ValueError('{} is not supported in multi-worker mode.'.format(
129 method.__name__))
--> 130 return method(self, *args, **kwargs)
131
132 return tf_decorator.make_decorator(
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in predict(self, x, batch_size, verbose, steps, callbacks, max_queue_size, workers, use_multiprocessing)
1577 use_multiprocessing=use_multiprocessing,
1578 model=self,
-> 1579 steps_per_execution=self._steps_per_execution)
1580
1581 # Container that configures and calls `tf.keras.Callback`s.
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/data_adapter.py in __init__(self, x, y, sample_weight, batch_size, steps_per_epoch, initial_epoch, epochs, shuffle, class_weight, max_queue_size, workers, use_multiprocessing, model, steps_per_execution)
1115 use_multiprocessing=use_multiprocessing,
1116 distribution_strategy=ds_context.get_strategy(),
-> 1117 model=model)
1118
1119 strategy = ds_context.get_strategy()
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/data_adapter.py in __init__(self, x, y, sample_weights, sample_weight_modes, batch_size, epochs, steps, shuffle, **kwargs)
280 label, ", ".join(str(i.shape[0]) for i in nest.flatten(data)))
281 msg += "Please provide data which shares the same first dimension."
--> 282 raise ValueError(msg)
283 num_samples = num_samples.pop()
284
ValueError: Data cardinality is ambiguous:
x sizes: 1, 500, 500
Please provide data which shares the same first dimension.
encoder_inputs=Input(shape=(max_art_len,))
encoder_emb=Embedding(art_vocab_size,100,trainable=True,name='Encoder_Embedding_layer')
(encoder_inputs)
encoder_lstm1=LSTM(300,return_sequences=True,return_state=True,name='Encoder_LSTM1')
enclstm1_outputs,enclstm1_h,enclstm1_c=encoder_lstm1(encoder_emb)
decoder_inputs=Input(shape=(None,))
decoder_em=Embedding(sum_vocab_size,100,trainable=True,name='Decoder_Embedding_layer')
decoder_emb=decoder_em(decoder_inputs)
decoder_lstm1=LSTM(300,return_sequences=True,return_state=True,name='Decoder_LSTM1')
declstm1_output,declstm1_h,declstm1_c=decoder_lstm1(decoder_emb,initial_state=[enclstm1_h,enclstm1_c])
output_layer=TimeDistributed(Dense(sum_vocab_size,activation='softmax',name='softmax'))
output=output_layer(declstm1_output)
model=Model([encoder_inputs,decoder_inputs],output)
model.summary()
infencoder_model=Model(inputs=[encoder_inputs],outputs=[enclstm1_h,enclstm1_c])
infdecoder_model_state_input_h=Input(shape=(300,),name='infdec_I1')
infdecoder_model_state_input_c=Input(shape=(300,),name='infdec_I2')
infdeclstm1_output,infdec_h,infdec_c=decoder_lstm1(decoder_emb,initial_state=[infdecoder_model_state_input_h,
infdecoder_model_state_input_c
])
infdec_output=output_layer(infdeclstm1_output)
infdecoder_model=Model(inputs=[decoder_inputs]+[infdecoder_model_state_input_h,infdecoder_model_state_input_c],
outputs=[infdec_output]+[infdec_h,infdec_c])
def decode_sequence(inp_seq):
enc_h,enc_c=infencoder_model.predict(inp_seq)
tar_seq=np.zeros((1,1))
tar_seq[0,0]=sum_wordindex['start']
stop_loop=False
decoded_string=''
while not stop_loop:
dec_out,dec_h,dec_c=infdecoder_model.predict([tar_seq]+[enc_h,enc_c])
tar_token_index=np.argmax(dec_out[0,-1,:])
tar_token_word=sum_wordindex[tar_token_index]
if tar_token_word =='end' or len(decoded_string)>=max_art_len:
stop_loop=True
else:
decoded_string+=tar_token_word
tar_seq=np.zeros((1,1))
tar_seq[0,0]=tar_token_index
enc_h=dec_h
enc_c=dec_c
return decoded_string
def seq2art(inp_seq):
art=''
for i in range(len(inp_seq)):
if inp_seq[i]==0:
break
art+=reverse_art_index[inp_seq[i]]+' '
return art
def seq2sum(inp_seq):
summary=''
for i in range(len(inp_seq)):
if inp_seq[i]==0:
break
word=reverse_sum_index[inp_seq[i]]
summary+=word+' '
return summary
print('Example Articel : '+'\n',seq2art(padded_X_val[2]))
print('Example Summary : '+'\n',seq2sum(padded_Y_val[2]))
print('Predicted Summary : '+'\n',decode_sequence(padded_X_val[2]))
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-43-9ef680a87bdf> in <module>
1 print('Example Articel : '+'\n',seq2art(padded_X_val[2]))
2 print('Example Summary : '+'\n',seq2sum(padded_Y_val[2]))
----> 3 print('Predicted Summary : '+'\n',decode_sequence(padded_X_val[2]))
<ipython-input-41-c41e0caee91d> in decode_sequence(inp_seq)
11 while not stop_loop:
12
---> 13 dec_out,dec_h,dec_c=infdecoder_model.predict([tar_seq]+
[enc_h,enc_c])
14
15 tar_token_index=np.argmax(dec_out[0,-1,:])
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
128 raise ValueError('{} is not supported in multi-worker mode.'.format(
129 method.__name__))
--> 130 return method(self, *args, **kwargs)
131
132 return tf_decorator.make_decorator(
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in predict(self, x, batch_size, verbose, steps, callbacks, max_queue_size, workers, use_multiprocessing)
1577 use_multiprocessing=use_multiprocessing,
1578 model=self,
-> 1579 steps_per_execution=self._steps_per_execution)
1580
1581 # Container that configures and calls `tf.keras.Callback`s.
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/data_adapter.py in __init__(self, x, y, sample_weight, batch_size, steps_per_epoch, initial_epoch, epochs, shuffle, class_weight, max_queue_size, workers, use_multiprocessing, model, steps_per_execution)
1115 use_multiprocessing=use_multiprocessing,
1116 distribution_strategy=ds_context.get_strategy(),
-> 1117 model=model)
1118
1119 strategy = ds_context.get_strategy()
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/data_adapter.py in __init__(self, x, y, sample_weights, sample_weight_modes, batch_size, epochs, steps, shuffle, **kwargs)
280 label, ", ".join(str(i.shape[0]) for i in nest.flatten(data)))
281 msg += "Please provide data which shares the same first dimension."
--> 282 raise ValueError(msg)
283 num_samples = num_samples.pop()
284
ValueError: Data cardinality is ambiguous:
x sizes: 1, 500, 500
Please provide data which shares the same first dimension.
---------------------------------------------------------------------------
ValueError回溯（最近一次调用上次）
在里面
1打印（'示例文章：'+'\n'，序号2art（填充的X值[2]））
2打印（'示例摘要：'+'\n'，seq2sum（填充的Y值[2]））
---->3打印（'预测摘要：'+'\n'，解码序列（填充的X值[2]））
在解码序列中（输入顺序）
11不停止循环时：
12
--->13 dec_out，dec_h，dec_c=infdecoder_model.预测（[tar_seq]+
[附件h，附件c]）
14
15 tar_token_index=np.argmax（dec_out[0，-1，：]）
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in_method_包装（self，*args，**kwargs）
128 raise VALUERROR（“{}在多工作模式下不受支持。”。格式(
129方法（名称）
-->130返回方法（self、*args、**kwargs）
131
132返回tf_decorator.make_decorator(
/predict中的opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py（self、x、批处理大小、冗余、步骤、回调、最大队列大小、工人、使用多处理）
1577使用多处理=使用多处理，
1578型号=自我，
->1579每执行一步=自我。_每执行一步）
1580
1581#配置和调用'tf.keras.Callback'的容器。
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/data_adapter.py in_____init___（self，x，y，sample_weight，batch_size，steps_per_epoch，initial_epoch，epoch，shufflue，class_weight，max_queue_size，worker，use_多处理，model，steps_per_execution）
1115使用多处理=使用多处理，
1116 distribution_strategy=ds_context.get_strategy（），
->1117型号=型号）
1118
1119 strategy=ds_context.get_strategy（）
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/data\u adapter.py in\uuuuuuu init\uuuuuuuuu（self，x，y，sample\u weights，sample\u weight\u modes，batch\u size，epoch，steps，shuffle，**kwargs）
280标签，“，”.join（str（i.shape[0]），用于嵌套中的i.flatte（数据）））
281 msg+=“请提供共享相同第一维度的数据。”
-->282提升值错误（msg）
283 num_samples=num_samples.pop（）
284
ValueError:数据基数不明确：
x尺寸：1500500
请提供共享相同第一维度的数据。