TensorFlow: TypeError: Expected int64, hat eine Liste mit Tensoren vom Typ '_Message' statt

Question

Meine TensorFlow Version ist 1.0. Wenn ich den folgenden Code:

train_file='~/tf_code/train' 
filename_queue = tf.train.string_input_producer([train_file],num_epochs=None) 
reader = tf.TFRecordReader() 
_, ex = reader.read(filename_queue) 

sequence_features = { 
    "x":tf.FixedLenSequenceFeature([], dtype = tf.int64), 
    "tomatch_indices_1D":tf.FixedLenSequenceFeature([], dtype = tf.int64) 
} 

context_parsed, sequence_parsed = tf.parse_single_sequence_example(
    serialized=ex, 
    context_features={}, 
    sequence_features=sequence_features 
) 

indices = tf.cast(sequence_parsed['tomatch_indices_1D'],tf.int64) 
indices = tf.reshape(indices, (-1,3)) 
x = sequence_parsed['x'] 
lens = tf.shape(x)[0] 
tomatch_sparse = tf.SparseTensor(indices, tf.ones((tf.shape(indices)[0],)), 
    dense_shape=(lens,lens,lens)) 
tomatch = tf.sparse_tensor_to_dense(tomatch_sparse, validate_indices=False) 
print(tomatch) 

Dann habe ich diesen Fehler auf tf.SparseTensor():

Traceback (most recent call last): 
    File "/Users/qingping/tf_code/SequenceExample/example_test.py", line 284, in <module> 
    stack_test() 
    File "/Users/qingping/tf_code/SequenceExample/example_test.py", line 276, in stack_test 
    tomatch_sparse = tf.SparseTensor(indices, tf.ones((tf.shape(indices)[0],)), dense_shape=(lens,lens,lens)) 
    File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/sparse_tensor.py", line 127, in __init__ 
    dense_shape, name="dense_shape", dtype=dtypes.int64) 
    File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 637, in convert_to_tensor 
    as_ref=False) 
    File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 702, in internal_convert_to_tensor 
    ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref) 
    File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 110, in _constant_tensor_conversion_function 
    return constant(v, dtype=dtype, name=name) 
    File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 99, in constant 
    tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape)) 
    File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 367, in make_tensor_proto 
    _AssertCompatible(values, dtype) 
    File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 302, in _AssertCompatible 
    (dtype.name, repr(mismatch), type(mismatch).__name__)) 
TypeError: Expected int64, got list containing Tensors of type '_Message' instead. 

Wenn ich SparseTensor von gelesenen Daten (Indizes) von Datei erstellen möchten, und Die Dichte von SparseTensor ist vielfältig, was soll ich tun? Vielen Dank!

Answer 1

Ich denke, die schlechte Fehlermeldung auftritt, wenn TensorFlow das Tupel von tf.int32 Tensoren (lens, lens, lens) zu einem einzigen tf.int64 Tensor als dense_shape Argument der tf.SparseTensor zu konvertieren versucht.

Der Standard-Rückgabewert von tf.shape() ist tf.int32. Sie können durch Hinzufügen eines expliziten out_type Argument dieses Problem lösen, wenn Sie lens berechnen, wie folgt:

lens = tf.shape(x, out_type=tf.int64)[0]