我正在用python和Keras编码神经网络。我想在网络中添加一个密集层。
在此密集层之后，我将使用一些transposed convolutions，因此我需要像这样重塑初始输入：
labels = np.array([1,2,3,4,5])
train_data_initial = np.array([[1,2,4],[2,4,8],[3,6,9],[4,8,16],[5,10,20]])
input_ = labels.reshape(5,1,1,1)
train_data = train_data_initial.reshape(5,3,1,1)
当我想在密集层中使用此输入时，按照documentation中给出的示例，会出现以下错误：
ValueError: setting an array element with a sequence.
这是我的代码：
import numpy as np
import tensorflow as tf
from keras.models import Sequential
from keras.layers import Dense
from keras.initializers import RandomNormal, Constant
from keras import losses
from keras import optimizers
sess = tf.Session()
# Datas
labels = np.array([1,2,3,4,5])
train_data_initial = np.array([[1,2,4],[2,4,8],[3,6,9],[4,8,16],[5,10,20]])
input_ = labels.reshape(5,1,1,1)
train_data = train_data_initial.reshape(5,3,1,1)
# Definition of the model
model = Sequential()
tf.reset_default_graph()
model.add(Dense((5,3,1,1), activation= None, kernel_initializer = RandomNormal(mean=0.0, stddev=0.001, seed=None), bias_initializer = Constant(value = 0.1), input_shape=(1,1,1,)))
# Here there will have some Conv2DTranspose
model.compile(loss=losses.mean_squared_error, optimizer= optimizers.Adam(lr=0.01))
model.fit(input_,train_data, 5, 10)
以及返回的完整错误消息：
ValueError Traceback (most recent call last)
<ipython-input-1-7d1f10e177f1> in <module>()
31 tf.reset_default_graph()
32
---> 33 model.add(Dense((5,3,1,1), activation= None, kernel_initializer = RandomNormal(mean=0.0, stddev=0.001, seed=None), bias_initializer = Constant(value = 0.1), input_shape=(1,1,1,)))
34
35 # Here there will have some Conv2DTranspose
/usr/local/lib/python3.5/dist-packages/keras/engine/sequential.py in add(self, layer)
164 # and create the node connecting the current layer
165 # to the input layer we just created.
--> 166 layer(x)
167 set_inputs = True
168 else:
/usr/local/lib/python3.5/dist-packages/keras/engine/base_layer.py in __call__(self, inputs, **kwargs)
430 '`layer.build(batch_input_shape)`')
431 if len(input_shapes) == 1:
--> 432 self.build(input_shapes[0])
433 else:
434 self.build(input_shapes)
/usr/local/lib/python3.5/dist-packages/keras/layers/core.py in build(self, input_shape)
870 name='kernel',
871 regularizer=self.kernel_regularizer,
--> 872 constraint=self.kernel_constraint)
873 if self.use_bias:
874 self.bias = self.add_weight(shape=(self.units,),
/usr/local/lib/python3.5/dist-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
/usr/local/lib/python3.5/dist-packages/keras/engine/base_layer.py in add_weight(self, name, shape, dtype, initializer, regularizer, trainable, constraint)
247 if dtype is None:
248 dtype = K.floatx()
--> 249 weight = K.variable(initializer(shape),
250 dtype=dtype,
251 name=name,
/usr/local/lib/python3.5/dist-packages/keras/initializers.py in __call__(self, shape, dtype)
82 def __call__(self, shape, dtype=None):
83 return K.random_normal(shape, self.mean, self.stddev,
---> 84 dtype=dtype, seed=self.seed)
85
86 def get_config(self):
/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py in random_normal(shape, mean, stddev, dtype, seed)
4052 seed = np.random.randint(10e6)
4053 return tf.random_normal(shape, mean=mean, stddev=stddev,
-> 4054 dtype=dtype, seed=seed)
4055
4056
/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/random_ops.py in random_normal(shape, mean, stddev, dtype, seed, name)
70 """
71 with ops.name_scope(name, "random_normal", [shape, mean, stddev]) as name:
---> 72 shape_tensor = _ShapeTensor(shape)
73 mean_tensor = ops.convert_to_tensor(mean, dtype=dtype, name="mean")
74 stddev_tensor = ops.convert_to_tensor(stddev, dtype=dtype, name="stddev")
/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/random_ops.py in _ShapeTensor(shape)
41 else:
42 dtype = None
---> 43 return ops.convert_to_tensor(shape, dtype=dtype, name="shape")
44
45
/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py in convert_to_tensor(value, dtype, name, preferred_dtype)
1012 name=name,
1013 preferred_dtype=preferred_dtype,
-> 1014 as_ref=False)
1015
1016
/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py in internal_convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, ctx)
1102
1103 if ret is None:
-> 1104 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
1105
1106 if ret is NotImplemented:
/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/constant_op.py in _constant_tensor_conversion_function(v, dtype, name, as_ref)
233 as_ref=False):
234 _ = as_ref
--> 235 return constant(v, dtype=dtype, name=name)
236
237
/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name, verify_shape)
212 tensor_value.tensor.CopyFrom(
213 tensor_util.make_tensor_proto(
--> 214 value, dtype=dtype, shape=shape, verify_shape=verify_shape))
215 dtype_value = attr_value_pb2.AttrValue(type=tensor_value.tensor.dtype)
216 const_tensor = g.create_op(
/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py in make_tensor_proto(values, dtype, shape, verify_shape)
431 else:
432 _AssertCompatible(values, dtype)
--> 433 nparray = np.array(values, dtype=np_dt)
434 # check to them.
435 # We need to pass in quantized values as tuples, so don't apply the shape
ValueError: setting an array element with a sequence.
谢谢您的帮助
答案 0 :(得分：0)
抛出错误是因为Dense()期望第一个参数是整数，并且该参数是输出空间的维数。但是，如果要重塑形状，则应添加另一层。
num_dense_units = 32
model.add(Dense(num_dense_units, activation= None, kernel_initializer = RandomNormal(mean=0.0, stddev=0.001, seed=None), bias_initializer = Constant(value = 0.1), input_shape=(1,1,1,)))
model.add(Reshape((5,3,1,1)))