InvalidArgumentError

[TyrionChou]

作者好，我想问一下这个问题，如下：
Caused by op u'attention_decoder/train_loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits', defined at:
File "train.py", line 171, in
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 126, in run
_sys.exit(main(argv))
File "train.py", line 74, in main
image_placeholder, groundtruth_text_placeholder, FLAGS.single_seq)
File "/root/WTR/AON_zh/model_aon.py", line 334, in inference
train_output_dict, pred_output_dict, train_logits, train_target = _attention_based_decoder(encoded_sequence, groundtruth_text)
File "/root/WTR/AON_zh/model_aon.py", line 294, in _attention_based_decoder
name='train_loss'
File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/seq2seq/python/ops/loss.py", line 92, in sequence_loss
labels=targets, logits=logits_flat)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/nn_ops.py", line 2050, in sparse_softmax_cross_entropy_with_logits
precise_logits, labels, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_nn_ops.py", line 7479, in sparse_softmax_cross_entropy_with_logits
labels=labels, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 3392, in create_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1718, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): logits and labels must have the same first dimension, got logits shape [3200,3258] and labels shape [3424]
[[Node: attention_decoder/train_loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits = SparseSoftmaxCrossEntropyWithLogits[T=DT_FLOAT, Tlabels=DT_INT64, _device="/job:localhost/replica:0/task:0/device:GPU:0"](attention_decoder/train_loss/Reshape, attention_decoder/train_loss/Reshape_1)]]

[TyrionChou]

这个问题出现在训练到1000步的时候，之前都可以训练，每训练到1000步就会出现这个问题！