无法评估从张量流中的复杂稀疏张量获得的密集张量

Question

我无法评估/打印/运行从 tensorflow 库中的复杂稀疏张量获得的密集张量。我目前在 macosx（仅限 cpu）中使用 tensorflow 的 build #234。

import tensorflow as tf

a = tf.SparseTensor(indices=[[0, 0, 0], [1, 2, 1]], values=[1.0+2j, 2.0], shape=[3, 4, 2])

b = tf.sparse_tensor_to_dense(a, default_value=0.0)

sess = tf.Session()

sess.run(b)

返回以下错误：

InvalidArgumentError (see above for traceback): No OpKernel was registered to support Op 'SparseToDense' with these attrs. Registered kernels:
device='CPU'; T in [DT_INT64]; Tindices in [DT_INT32]
device='CPU'; T in [DT_INT64]; Tindices in [DT_INT64]
device='CPU'; T in [DT_INT32]; Tindices in [DT_INT32]
device='CPU'; T in [DT_INT32]; Tindices in [DT_INT64]
device='CPU'; T in [DT_UINT16]; Tindices in [DT_INT32]
device='CPU'; T in [DT_UINT16]; Tindices in [DT_INT64]
device='CPU'; T in [DT_INT16]; Tindices in [DT_INT32]
device='CPU'; T in [DT_INT16]; Tindices in [DT_INT64]
device='CPU'; T in [DT_UINT8]; Tindices in [DT_INT32]
device='CPU'; T in [DT_UINT8]; Tindices in [DT_INT64]
device='CPU'; T in [DT_INT8]; Tindices in [DT_INT32]
device='CPU'; T in [DT_INT8]; Tindices in [DT_INT64]
device='CPU'; T in [DT_HALF]; Tindices in [DT_INT32]
device='CPU'; T in [DT_HALF]; Tindices in [DT_INT64]
device='CPU'; T in [DT_FLOAT]; Tindices in [DT_INT32]
device='CPU'; T in [DT_FLOAT]; Tindices in [DT_INT64]
device='CPU'; T in [DT_DOUBLE]; Tindices in [DT_INT32]
device='CPU'; T in [DT_DOUBLE]; Tindices in [DT_INT64]
device='CPU'; T in [DT_BOOL]; Tindices in [DT_INT32]
device='CPU'; T in [DT_BOOL]; Tindices in [DT_INT64]
device='CPU'; T in [DT_STRING]; Tindices in [DT_INT32]
device='CPU'; T in [DT_STRING]; Tindices in [DT_INT64]

 [[Node: SparseToDense_3 = SparseToDense[T=DT_COMPLEX128, Tindices=DT_INT64, validate_indices=true](SparseTensor_2/indices, SparseTensor_2/shape, SparseTensor_2/values, SparseToDense_3/default_value)]]

我也试过了：

br = tf.real(b)

sess.run(br)

但是，这会产生与上述相同的错误。

但请注意，以下操作正常：

x = tf.ones((3,3), dtype=tf.complex128)

sess.run(x)

提前感谢您的帮助！

Answer 1

看起来 tf.sparse_tensor_to_dense 还不支持复数。我已经尝试丢失 +2j 组件，并且它起作用了。我认为错误转储试图告诉您 sparse_tensor_to_dense 不支持复杂类型，并列出它支持的类型。