我一直在尝试使用以下代码运行神经网络：
model=Sequential()
model.add(Dense(output_dim=40, input_dim=90, init="glorot_uniform"))
model.add(Activation("tanh"))
model.add(Dense(output_dim=10, init="glorot_uniform"))
model.add(Activation("linear"))
model.compile(loss="mean_absolute_percentage_error", optimizer="rmsprop")
model.fit(X=predictor_train, y=target_train, nb_epoch=2, batch_size=90,show_accuracy=True)
我无法确定这个错误的含义：
raise ValueError(base_exc_str)
ValueError: Dimension mismatch; shapes are (98, 10), (98, 1)
据我所知，这些形状应该是相等的，如
(98,10),(98,10)或(98,1),(98,1)，这可能会导致问题。是这样吗？如果是的话，有人知道在代码或数据集中可以在哪里解决这个问题吗？那个10和1是什么意思？
如果不是，有人能向我解释发生了什么吗？ 额外信息: 变量predictor_train:
predictor_train.shape = (98, 90)
type(predictor_train) = numpy.ndarray
predictor_train.dtype = float64
len(predictor_train) = 98
predictor_train = [[ -9.28079499e+03 -5.44726790e+03 9.77551565e+03 ..., -2.94089612e+01
1.05007607e+01 9.32395201e+00]
[ -9.32333218e+03 -4.06918099e+03 8.84849310e+03 ..., 3.02589395e+01
1.32480085e+01 7.35936371e+00]
[ -9.08950902e+03 -2.59672093e+03 6.78783637e+03 ..., -7.22732280e+00
-8.72789507e+00 -3.38694330e+01]
...,
[ 6.00971088e+03 4.82090785e+02 2.06287833e+03 ..., 5.07504624e+00
-1.08715262e+01 -4.44630971e+00]
[ 6.02593657e+03 1.04561016e+03 1.19684456e+03 ..., 2.10305449e+01
-1.00583976e+01 -5.45816394e-01]
[ 6.11828134e+03 1.50004864e+03 3.00936969e+02 ..., -1.66676535e+01
6.07002336e+00 3.00131153e+00]]
变量 target_train：
target_train.shape = (98,)
type(target_train) = pandas.core.series.Series
target_train.dtype = float64
len(target_train) = 98
target_train =
Date
2007-07-01 0.009137
2007-08-01 0.010607
2007-09-01 0.007146
...
2015-06-01 -0.008642
2015-07-01 -0.008642
2015-08-01 -0.008642
Freq: MS, Name: Actual, dtype: float64
完整回溯信息：
Traceback (most recent call last):
File "/Users/santanna_santanna/PycharmProjects/Predictive Models/teste2.py", line 1479, in Pred
model.fit(X=predictor_train, y=target_train, nb_epoch=2, batch_size=90,show_accuracy=True)
File "/Library/Python/2.7/site-packages/keras/models.py", line 581, in fit
shuffle=shuffle, metrics=metrics)
File "/Library/Python/2.7/site-packages/keras/models.py", line 239, in _fit
outs = f(ins_batch)
File "/Library/Python/2.7/site-packages/keras/backend/theano_backend.py", line 365, in __call__
return self.function(*inputs)
File "/Library/Python/2.7/site-packages/theano/compile/function_module.py", line 595, in __call__
outputs = self.fn()
File "/Library/Python/2.7/site-packages/theano/gof/vm.py", line 233, in __call__
link.raise_with_op(node, thunk)
File "/Library/Python/2.7/site-packages/theano/gof/vm.py", line 229, in __call__
thunk()
File "/Library/Python/2.7/site-packages/theano/gof/op.py", line 768, in rval
r = p(n, [x[0] for x in i], o)
File "/Library/Python/2.7/site-packages/theano/tensor/elemwise.py", line 808, in perform
raise ValueError(base_exc_str)
ValueError: Dimension mismatch; shapes are (98, 10), (98, 1)
Apply node that caused the error: Elemwise{Sub}[(0, 0)](Elemwise{Add}[(0, 0)].0, <TensorType(float32, matrix)>)
Inputs types: [TensorType(float32, matrix), TensorType(float32, matrix)]
Inputs shapes: [(98, 10), (98, 1)]
Inputs strides: [(40, 4), (4, 4)]
Inputs values: ['not shown', 'not shown']
HINT: Re-running with most Theano optimization disabled could give you a back-trace of when this node was created. This can be done with by setting the Theano flag 'optimizer=fast_compile'. If that does not work, Theano optimizations can be disabled with 'optimizer=None'.
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.