tensorflow - 如何处理keras : erro:slice index 0 of dimension 0 out of bounds

Question

我使用 keras(tensorflow backend) 来构建我的 lstm 网络，这是我的代码:

from keras.models import Sequential,Model
from keras.layers import LSTM,Conv1D,Dense,MaxPooling1D,GlobalMaxPooling1D,Input,Concatenate
from keras.optimizers import Adam

x_input = Input(shape=(None,x_train.shape[-1]),name='input')
x_mid = Conv1D(32,4, activation='relu')(x_input)
x_mid = MaxPooling1D(3)(x_mid)
x_mid = Conv1D(32,4,activation = 'relu')(x_mid)
x_mid = LSTM(32,dropout=0.1, recurrent_dropout=0.2,activation='relu')(x_mid)
x_mid = Dense(1,activation='sigmoid')(x_mid)
other_input = Input(shape=(x_blend_train.shape[-1],),name='clfs_input')
merge_x = concatenate(inputs= [x_mid,other_input],axis = -1)
output = Dense(32,activation='relu')(merge_x)
output = Dense(1,activation='sigmoid')(output)
model = Model(inputs=[x_input,other_input],outputs=output)
model.compile(optimizer='adam',loss=['binary_crossentropy'],metrics=['acc'])
model.summary()

这就是我的网络的样子

Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input (InputLayer)              (None, None, 49)     0                                            
__________________________________________________________________________________________________
conv1d_56 (Conv1D)              (None, None, 32)     6304        input[0][0]                      
__________________________________________________________________________________________________
max_pooling1d_26 (MaxPooling1D) (None, None, 32)     0           conv1d_56[0][0]                  
__________________________________________________________________________________________________
conv1d_57 (Conv1D)              (None, None, 32)     4128        max_pooling1d_26[0][0]           
__________________________________________________________________________________________________
lstm_26 (LSTM)                  (None, 32)           8320        conv1d_57[0][0]                  
__________________________________________________________________________________________________
dense_59 (Dense)                (None, 1)            33          lstm_26[0][0]                    
__________________________________________________________________________________________________
clfs_input (InputLayer)         (None, 1)            0                                            
__________________________________________________________________________________________________
concatenate_20 (Concatenate)    (None, 2)            0           dense_59[0][0]                   
                                                                 clfs_input[0][0]                 
__________________________________________________________________________________________________
dense_60 (Dense)                (None, 32)           96          concatenate_20[0][0]             
__________________________________________________________________________________________________
dense_61 (Dense)                (None, 1)            33          dense_60[0][0]                   
==================================================================================================

我的数据形状是:

x_train.shape: (1350, 14, 49) x_blend_train.shape: (1350, 1) y_train.shape: (1350, 1)

我的 tensorflow 和 keras 版本是:

tensorflow version:'1.8.0-rc1' keras version:'2.1.6'

当我使用

model.fit( x={'input':x_train,'clfs_input':x_blend_train}, y=y_train, batch_size=64, epochs=10)

计算机向我返回错误:

InvalidArgumentError: slice index 0 of dimension 0 out of bounds.
     [[Node: lstm_25/strided_slice_13 = StridedSlice[Index=DT_INT32, T=DT_FLOAT, begin_mask=0, ellipsis_mask=0, end_mask=0, new_axis_mask=0, shrink_axis_mask=1, _device="/job:localhost/replica:0/task:0/device:CPU:0"](lstm_25/transpose, loss_11/dense_58_loss/Const_2, lstm_25/strided_slice_9/stack_2, lstm_25/strided_slice_9/stack_2)]]

以及有关错误的更多详细信息:

Epoch 1/10
---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1321     try:
-> 1322       return fn(*args)
   1323     except errors.OpError as e:

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata)
   1306       return self._call_tf_sessionrun(
-> 1307           options, feed_dict, fetch_list, target_list, run_metadata)
   1308 

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata)
   1408           self._session, options, feed_dict, fetch_list, target_list,
-> 1409           run_metadata)
   1410     else:

InvalidArgumentError: slice index 0 of dimension 0 out of bounds.
     [[Node: lstm_25/strided_slice_13 = StridedSlice[Index=DT_INT32, T=DT_FLOAT, begin_mask=0, ellipsis_mask=0, end_mask=0, new_axis_mask=0, shrink_axis_mask=1, _device="/job:localhost/replica:0/task:0/device:CPU:0"](lstm_25/transpose, loss_11/dense_58_loss/Const_2, lstm_25/strided_slice_9/stack_2, lstm_25/strided_slice_9/stack_2)]]

During handling of the above exception, another exception occurred:

InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-66-c2316b8cd20c> in <module>()
----> 1 model.fit( x={'input':x_train,'clfs_input':x_blend_train}, y=y_train, batch_size=64, epochs=10)
      2 y_pred = model.predict({'input':x_train,'clfs_input':x_blend_test})

/opt/conda/lib/python3.6/site-packages/Keras-2.1.6-py3.6.egg/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
   1031                                         initial_epoch=initial_epoch,
   1032                                         steps_per_epoch=steps_per_epoch,
-> 1033                                         validation_steps=validation_steps)
   1034 
   1035     def evaluate(self, x=None, y=None,

/opt/conda/lib/python3.6/site-packages/Keras-2.1.6-py3.6.egg/keras/engine/training_arrays.py in fit_loop(model, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch, steps_per_epoch, validation_steps)
    193                     ins_batch[i] = ins_batch[i].toarray()
    194 
--> 195                 outs = f(ins_batch)
    196                 if not isinstance(outs, list):
    197                     outs = [outs]

/opt/conda/lib/python3.6/site-packages/Keras-2.1.6-py3.6.egg/keras/backend/tensorflow_backend.py in __call__(self, inputs)
   2489         session = get_session()
   2490         updated = session.run(fetches=fetches, feed_dict=feed_dict,
-> 2491                               **self.session_kwargs)
   2492         return updated[:len(self.outputs)]
   2493 

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
    898     try:
    899       result = self._run(None, fetches, feed_dict, options_ptr,
--> 900                          run_metadata_ptr)
    901       if run_metadata:
    902         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
   1133     if final_fetches or final_targets or (handle and feed_dict_tensor):
   1134       results = self._do_run(handle, final_targets, final_fetches,
-> 1135                              feed_dict_tensor, options, run_metadata)
   1136     else:
   1137       results = []

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1314     if handle is None:
   1315       return self._do_call(_run_fn, feeds, fetches, targets, options,
-> 1316                            run_metadata)
   1317     else:
   1318       return self._do_call(_prun_fn, handle, feeds, fetches)

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1333         except KeyError:
   1334           pass
-> 1335       raise type(e)(node_def, op, message)
   1336 
   1337   def _extend_graph(self):

我不知道如何处理这个错误，我尝试使用谷歌在 github 中找到答案并查看问题，但我没有找到可以帮助我的东西。我期待着你的帮助。

Answer 1

让我们进行一次观察，看看会发生什么。单个观察具有以下形状:(14 , 49)。
在第一个 Conv1D 层之后，它将变为 (11,32)(内核大小为 4，步幅为 1)。在第一个 Maxpooling1D 层之后，它将转到 (3 , 32) (因为您没有设置步幅，它将默认为您的池大小为 3)。如果我们查看您的第二个 conv1D 层，它的内核大小等于 4，这大于数据帧的第一个维度的数量。

我建议将第一行设置为:

x_input = Input(shape=(x_train.shape[-2],x_train.shape[-1]),name='input')

这将使您可以更轻松地查看输入的形状在每一层中的变化情况。