machine-learning - 使用自动编码器的 1 的不兼容形状

Question

我正在尝试在时间序列上使用自动编码器。当我对数据使用填充时，一切正常，但是当我使用可变数据长度时，我遇到了一些小数据形状问题: 形状不兼容:[1,125,4] 与 [1,126,4]

input_series = Input(shape=(None, 4))

x = Conv1D(4, 2, activation='relu', padding='same')(input_series)
x = MaxPooling1D(1, padding='same')(x)
x = Conv1D(4, 3, activation='relu', padding='same')(x)
x = MaxPooling1D(1, padding='same')(x)
x = Conv1D(4, 3, activation='relu', padding='same')(x)
encoder = MaxPooling1D(1, padding='same', name='encoder')(x)


x = Conv1D(4, 3, activation='relu', padding='same')(encoder)
x = UpSampling1D(1)(x)
x = Conv1D(4, 3, activation='relu', padding='same')(x)
x = UpSampling1D(1)(x)
x = Conv1D(16, 2, activation='relu')(x)
x = UpSampling1D(1)(x)
decoder = Conv1D(4, 2, activation='sigmoid', padding='same')(x)

autoencoder = Model(input_series, decoder)
autoencoder.compile(loss='mse', optimizer='adam')
autoencoder.summary()

摘要:

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_25 (InputLayer)        (None, None, 4)           0         
_________________________________________________________________
conv1d_169 (Conv1D)          (None, None, 4)           36        
_________________________________________________________________
max_pooling1d_49 (MaxPooling (None, None, 4)           0         
_________________________________________________________________
conv1d_170 (Conv1D)          (None, None, 4)           52        
_________________________________________________________________
max_pooling1d_50 (MaxPooling (None, None, 4)           0         
_________________________________________________________________
conv1d_171 (Conv1D)          (None, None, 4)           52        
_________________________________________________________________
encoder (MaxPooling1D)       (None, None, 4)           0         
_________________________________________________________________
conv1d_172 (Conv1D)          (None, None, 4)           52        
_________________________________________________________________
up_sampling1d_73 (UpSampling (None, None, 4)           0         
_________________________________________________________________
conv1d_173 (Conv1D)          (None, None, 4)           52        
_________________________________________________________________
up_sampling1d_74 (UpSampling (None, None, 4)           0         
_________________________________________________________________
conv1d_174 (Conv1D)          (None, None, 16)          144       
_________________________________________________________________
up_sampling1d_75 (UpSampling (None, None, 16)          0         
_________________________________________________________________
conv1d_175 (Conv1D)          (None, None, 4)           132       
=================================================================
Total params: 520
Trainable params: 520
Non-trainable params: 0
_________________________________________________________________

错误:

Epoch 1/50
---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
C:\ProgramData\Anaconda3\lib\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:

C:\ProgramData\Anaconda3\lib\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 

C:\ProgramData\Anaconda3\lib\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: Incompatible shapes: [1,125,4] vs. [1,126,4]
     [[Node: loss_22/conv1d_175_loss/sub = Sub[T=DT_FLOAT, _class=["loc:@training_18/Adam/gradients/loss_22/conv1d_175_loss/sub_grad/Reshape"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv1d_175/Sigmoid, _arg_conv1d_175_target_0_1/_4489)]]
     [[Node: loss_22/mul/_4613 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_1245_loss_22/mul", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

During handling of the above exception, another exception occurred:

InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-101-a6e405699326> in <module>()
      6     train_generator(X_train),
      7     epochs=50,
----> 8     steps_per_epoch=len(X_train))
      9 
     10 

C:\ProgramData\Anaconda3\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
     89                 warnings.warn('Update your `' + object_name +
     90                               '` call to the Keras 2 API: ' + signature, stacklevel=2)
---> 91             return func(*args, **kwargs)
     92         wrapper._original_function = func
     93         return wrapper

C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
   2228                     outs = self.train_on_batch(x, y,
   2229                                                sample_weight=sample_weight,
-> 2230                                                class_weight=class_weight)
   2231 
   2232                     if not isinstance(outs, list):

C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py in train_on_batch(self, x, y, sample_weight, class_weight)
   1881             ins = x + y + sample_weights
   1882         self._make_train_function()
-> 1883         outputs = self.train_function(ins)
   1884         if len(outputs) == 1:
   1885             return outputs[0]

C:\ProgramData\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py in __call__(self, inputs)
   2480         session = get_session()
   2481         updated = session.run(fetches=fetches, feed_dict=feed_dict,
-> 2482                               **self.session_kwargs)
   2483         return updated[:len(self.outputs)]
   2484 

C:\ProgramData\Anaconda3\lib\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)

C:\ProgramData\Anaconda3\lib\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 = []

C:\ProgramData\Anaconda3\lib\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)

C:\ProgramData\Anaconda3\lib\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):

InvalidArgumentError: Incompatible shapes: [1,125,4] vs. [1,126,4]
     [[Node: loss_22/conv1d_175_loss/sub = Sub[T=DT_FLOAT, _class=["loc:@training_18/Adam/gradients/loss_22/conv1d_175_loss/sub_grad/Reshape"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv1d_175/Sigmoid, _arg_conv1d_175_target_0_1/_4489)]]
     [[Node: loss_22/mul/_4613 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_1245_loss_22/mul", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

Caused by op 'loss_22/conv1d_175_loss/sub', defined at:
  File "C:\ProgramData\Anaconda3\lib\runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "C:\ProgramData\Anaconda3\lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel_launcher.py", line 16, in <module>
    app.launch_new_instance()
  File "C:\ProgramData\Anaconda3\lib\site-packages\traitlets\config\application.py", line 658, in launch_instance
    app.start()
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelapp.py", line 478, in start
    self.io_loop.start()
  File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\ioloop.py", line 177, in start
    super(ZMQIOLoop, self).start()
  File "C:\ProgramData\Anaconda3\lib\site-packages\tornado\ioloop.py", line 888, in start
    handler_func(fd_obj, events)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events
    self._handle_recv()
  File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv
    self._run_callback(callback, msg)
  File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback
    callback(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 283, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 233, in dispatch_shell
    handler(stream, idents, msg)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 399, in execute_request
    user_expressions, allow_stdin)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\ipkernel.py", line 208, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 537, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2728, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2850, in run_ast_nodes
    if self.run_code(code, result):
  File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2910, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-100-ddd3b57d5f0b>", line 22, in <module>
    autoencoder.compile(loss='mse', optimizer='adam')
  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py", line 830, in compile
    sample_weight, mask)
  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py", line 429, in weighted
    score_array = fn(y_true, y_pred)
  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\losses.py", line 14, in mean_squared_error
    return K.mean(K.square(y_pred - y_true), axis=-1)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\math_ops.py", line 979, in binary_op_wrapper
    return func(x, y, name=name)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 8582, in sub
    "Sub", x=x, y=y, name=name)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3392, in create_op
    op_def=op_def)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1718, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): Incompatible shapes: [1,125,4] vs. [1,126,4]
     [[Node: loss_22/conv1d_175_loss/sub = Sub[T=DT_FLOAT, _class=["loc:@training_18/Adam/gradients/loss_22/conv1d_175_loss/sub_grad/Reshape"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv1d_175/Sigmoid, _arg_conv1d_175_target_0_1/_4489)]]
     [[Node: loss_22/mul/_4613 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_1245_loss_22/mul", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

Answer 1

您的其中一个 Conv1D 层未使用 padding='same'。

但是有一些非常奇怪的事情:为什么要使用 MaxPooling 和 pool_size=1 ？它什么也不做。

<小时/>

现在假设您使用pool_size=2，那么无论如何您都需要填充输入，因为您需要长度为 8 (2³) 倍数的输入才能最终得到上采样后形状相同。

<小时/>

对于可变长度自动编码器，这里有一个示例:Variable length output in keras

对于所有效果，LSTM 层处理形状的方式与 Conv1D 层完全相同。