Question

我正在研究Alex Gordan的Attention_ocr项目。我遵循指南并根据Alex的answer以FSNS格式存储我的数据。

但是，当我运行命令时： python train.py --dataset_name = rctw

发生错误，错误消息显示如下：

Caused by op u'save/Assign_175', defined at:
  File "train.py", line 209, in <module>
    app.run()
  File "/usr/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 44, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "train.py", line 205, in main
    train(total_loss, init_fn, hparams)
  File "train.py", line 153, in train
    init_fn=init_fn)
  File "/usr/lib/python2.7/site-packages/tensorflow/contrib/slim/python/slim/learning.py", line 688, in train
    saver = saver or tf_saver.Saver()
  File "/usr/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1040, in __init__
    self.build()
  File "/usr/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1070, in build
    restore_sequentially=self._restore_sequentially)
  File "/usr/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 675, in build
    restore_sequentially, reshape)
  File "/usr/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 414, in _AddRestoreOps
    assign_ops.append(saveable.restore(tensors, shapes))
  File "/usr/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 155, in restore
    self.op.get_shape().is_fully_defined())
  File "/usr/lib/python2.7/site-packages/tensorflow/python/ops/gen_state_ops.py", line 47, in assign
    use_locking=use_locking, name=name)
  File "/usr/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 763, in apply_op
    op_def=op_def)
  File "/usr/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2327, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/usr/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1226, in __init__
    self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [3794,3506] rhs shape= [422,134]
     [[Node: save/Assign_175 = Assign[T=DT_FLOAT, _class=["loc:@AttentionOcr_v1/sequence_logit_fn/SQLR/LSTM/attention_decoder/weights"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/gpu:0"](AttentionOcr_v1/sequence_logit_fn/SQLR/LSTM/attention_decoder/weights/Momentum, save/RestoreV2_175/_15)]]
     [[Node: save/RestoreV2_141/_168 = _Send[T=DT_FLOAT, client_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_715_save/RestoreV2_141", _device="/job:localhost/replica:0/task:0/cpu:0"](save/RestoreV2_141)]]

由于我使用python / datasets / fsns.py作为示例来创建我的rctw.py，并将其作为fsns包含在datasets / init.py中，为什么会出现此错误？也许你的项目中有一些硬编码，所以他们总是称之为“134 charset”

希望作者或任何其他人的回应。

Answer 1

代码使用存储在我的tmp路径中的预训练模型，我清理/ tmp来解决它。

跟踪Attention_ocr时的InvalidArgumentError：Assign需要两个张量的形状匹配

1 个答案: