所以我正在尝试创建一个自动编码器，它将进行文本审查并找到较低维度的表示形式。我正在使用 keras，我希望我的损失函数将 AE 的输出与嵌入层的输出进行比较。不幸的是，它给了我以下错误。我很确定问题出在我的损失函数上，但我似乎无法解决这个问题。
自动编码器
print X_train.shape
input_i = Input(shape=(200,))
embedding = Embedding(input_dim=weights.shape[0],output_dim=weights.shape[1],
weights=[weights])(input_i)
encoded_h1 = Dense(64, activation='tanh')(embedding)
encoded_h2 = Dense(32, activation='tanh')(encoded_h1)
encoded_h3 = Dense(16, activation='tanh')(encoded_h2)
encoded_h4 = Dense(8, activation='tanh')(encoded_h3)
encoded_h5 = Dense(4, activation='tanh')(encoded_h4)
latent = Dense(2, activation='tanh')(encoded_h5)
decoder_h1 = Dense(4, activation='tanh')(latent)
decoder_h2 = Dense(8, activation='tanh')(decoder_h1)
decoder_h3 = Dense(16, activation='tanh')(decoder_h2)
decoder_h4 = Dense(32, activation='tanh')(decoder_h3)
decoder_h5 = Dense(64, activation='tanh')(decoder_h4)
output = Dense(weights.shape[1], activation='tanh')(decoder_h5)
autoencoder = Model(input_i,output)
encoder = Model(input_i,latent)
print autoencoder.summary()
import keras.backend as K
import tensorflow as tf
def embedded_mse(x_true, e_pred):
print output
print embedding
mse = K.mean(K.square(output - embedding))
print mse
return tf.Session().run(mse)
autoencoder.compile(optimizer='adadelta',
loss=embedded_mse)
autoencoder.fit(X_train,X_train,epochs=10,
batch_size=256, validation_split=.1)
输出
(100000, 200)
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_47 (InputLayer) (None, 200) 0
_________________________________________________________________
embedding_31 (Embedding) (None, 200, 100) 21833700
_________________________________________________________________
dense_528 (Dense) (None, 200, 64) 6464
_________________________________________________________________
dense_529 (Dense) (None, 200, 32) 2080
_________________________________________________________________
dense_530 (Dense) (None, 200, 16) 528
_________________________________________________________________
dense_531 (Dense) (None, 200, 8) 136
_________________________________________________________________
dense_532 (Dense) (None, 200, 4) 36
_________________________________________________________________
dense_533 (Dense) (None, 200, 2) 10
_________________________________________________________________
dense_534 (Dense) (None, 200, 4) 12
_________________________________________________________________
dense_535 (Dense) (None, 200, 8) 40
_________________________________________________________________
dense_536 (Dense) (None, 200, 16) 144
_________________________________________________________________
dense_537 (Dense) (None, 200, 32) 544
_________________________________________________________________
dense_538 (Dense) (None, 200, 64) 2112
_________________________________________________________________
dense_539 (Dense) (None, 200, 100) 6500
=================================================================
Total params: 21,852,306
Trainable params: 21,852,306
Non-trainable params: 0
_________________________________________________________________
None
Tensor("dense_539/Tanh:0", shape=(?, 200, 100), dtype=float32)
Tensor("embedding_31/Gather:0", shape=(?, 200, 100), dtype=float32)
Tensor("loss_48/dense_539_loss/Mean:0", shape=(), dtype=float32)
错误
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-155-a18e0c32f59b> in <module>()
1 autoencoder.compile(optimizer='adadelta',
----> 2 loss=embedded_mse)
3 autoencoder.fit(X_train,embedding,epochs=10,
4 batch_size=256, validation_split=.1)
/home/andrew/.local/lib/python2.7/site-packages/keras/engine/training.pyc in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors, **kwargs)
848 with K.name_scope(self.output_names[i] + '_loss'):
849 output_loss = weighted_loss(y_true, y_pred,
--> 850 sample_weight, mask)
851 if len(self.outputs) > 1:
852 self.metrics_tensors.append(output_loss)
/home/andrew/.local/lib/python2.7/site-packages/keras/engine/training.pyc in weighted(y_true, y_pred, weights, mask)
448 """
449 # score_array has ndim >= 2
--> 450 score_array = fn(y_true, y_pred)
451 if mask is not None:
452 # Cast the mask to floatX to avoid float64 upcasting in theano
<ipython-input-153-73211fc383a5> in embedded_mse(x_true, e_pred)
7 print mse
8
----> 9 return tf.Session().run(mse)
/home/andrew/.local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in run(self, fetches, feed_dict, options, run_metadata)
893 try:
894 result = self._run(None, fetches, feed_dict, options_ptr,
--> 895 run_metadata_ptr)
896 if run_metadata:
897 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/home/andrew/.local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _run(self, handle, fetches, feed_dict, options, run_metadata)
1122 if final_fetches or final_targets or (handle and feed_dict_tensor):
1123 results = self._do_run(handle, final_targets, final_fetches,
-> 1124 feed_dict_tensor, options, run_metadata)
1125 else:
1126 results = []
/home/andrew/.local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1319 if handle is None:
1320 return self._do_call(_run_fn, self._session, feeds, fetches, targets,
-> 1321 options, run_metadata)
1322 else:
1323 return self._do_call(_prun_fn, self._session, handle, feeds, fetches)
/home/andrew/.local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_call(self, fn, *args)
1338 except KeyError:
1339 pass
-> 1340 raise type(e)(node_def, op, message)
1341
1342 def _extend_graph(self):
InvalidArgumentError: You must feed a value for placeholder tensor 'input_47' with dtype float and shape [?,200]
[[Node: input_47 = Placeholder[dtype=DT_FLOAT, shape=[?,200], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op u'input_47', defined at:
File "/usr/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"__main__", fname, loader, pkg_name)
File "/usr/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/home/andrew/.local/lib/python2.7/site-packages/ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "/home/andrew/.local/lib/python2.7/site-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/home/andrew/.local/lib/python2.7/site-packages/ipykernel/kernelapp.py", line 477, in start
ioloop.IOLoop.instance().start()
File "/home/andrew/.local/lib/python2.7/site-packages/zmq/eventloop/ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "/home/andrew/.local/lib/python2.7/site-packages/tornado/ioloop.py", line 888, in start
handler_func(fd_obj, events)
File "/home/andrew/.local/lib/python2.7/site-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/home/andrew/.local/lib/python2.7/site-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "/home/andrew/.local/lib/python2.7/site-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "/home/andrew/.local/lib/python2.7/site-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "/home/andrew/.local/lib/python2.7/site-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/home/andrew/.local/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "/home/andrew/.local/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 235, in dispatch_shell
handler(stream, idents, msg)
File "/home/andrew/.local/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "/home/andrew/.local/lib/python2.7/site-packages/ipykernel/ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/home/andrew/.local/lib/python2.7/site-packages/ipykernel/zmqshell.py", line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/home/andrew/.local/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2718, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/home/andrew/.local/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2822, in run_ast_nodes
if self.run_code(code, result):
File "/home/andrew/.local/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2882, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-152-7732fda181fc>", line 2, in <module>
input_i = Input(shape=(200,))
File "/home/andrew/.local/lib/python2.7/site-packages/keras/engine/topology.py", line 1436, in Input
input_tensor=tensor)
File "/home/andrew/.local/lib/python2.7/site-packages/keras/legacy/interfaces.py", line 87, in wrapper
return func(*args, **kwargs)
File "/home/andrew/.local/lib/python2.7/site-packages/keras/engine/topology.py", line 1347, in __init__
name=self.name)
File "/home/andrew/.local/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 442, in placeholder
x = tf.placeholder(dtype, shape=shape, name=name)
File "/home/andrew/.local/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1548, in placeholder
return gen_array_ops._placeholder(dtype=dtype, shape=shape, name=name)
File "/home/andrew/.local/lib/python2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 2094, in _placeholder
name=name)
File "/home/andrew/.local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
op_def=op_def)
File "/home/andrew/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/andrew/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1204, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'input_47' with dtype float and shape [?,200]
[[Node: input_47 = Placeholder[dtype=DT_FLOAT, shape=[?,200], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
你的问题有一些问题(例如，什么是weights，在Embedding和最终Dense层参数中使用？)。不过，我认为更简单的方法是解开嵌入和自动编码部分(它们是独立的)，首先构建一个简单的嵌入模型，然后使用其输出(带有predict)来馈送您的自动编码器。这样你就不必定义自定义损失(顺便说一句，print此类函数中的语句不是一个好主意)。
在不知道数据详细信息的情况下，以下 2 个模型可以正常编译：
嵌入模型(根据文档快速改编)
model = Sequential()
model.add(Embedding(1000, 64))
model.compile('rmsprop', 'mse')
自动编码器：
input_i = Input(shape=(200,100))
encoded_h1 = Dense(64, activation='tanh')(input_i)
encoded_h2 = Dense(32, activation='tanh')(encoded_h1)
encoded_h3 = Dense(16, activation='tanh')(encoded_h2)
encoded_h4 = Dense(8, activation='tanh')(encoded_h3)
encoded_h5 = Dense(4, activation='tanh')(encoded_h4)
latent = Dense(2, activation='tanh')(encoded_h5)
decoder_h1 = Dense(4, activation='tanh')(latent)
decoder_h2 = Dense(8, activation='tanh')(decoder_h1)
decoder_h3 = Dense(16, activation='tanh')(decoder_h2)
decoder_h4 = Dense(32, activation='tanh')(decoder_h3)
decoder_h5 = Dense(64, activation='tanh')(decoder_h4)
output = Dense(100, activation='tanh')(decoder_h5)
autoencoder = Model(input_i,output)
autoencoder.compile('adadelta','mse')
根据您的情况调整上述模型参数后，这应该可以正常工作：
X_embedded = model.predict(X_train)
autoencoder.fit(X_embedded,X_embedded,epochs=10,
batch_size=256, validation_split=.1)