Python 训练注意力时无效的辩论者\u ocr:Assign需要两个张量的形状匹配

我在做Alex Gordan的项目。 我已经按照指南，按照Alex的要求，以FSNS格式存储我的数据

但是，当我运行命令时： python train.py——数据集_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)]]

由操作u'save/Assign_175'引起，定义于：
文件“train.py”，第209行，在
app.run（）
文件“/usr/lib/python2.7/site packages/tensorflow/python/platform/app.py”，第44行，正在运行
_系统出口（主（_sys.argv[：1]+标志_passthrough））
文件“train.py”，第205行，在main中
列车（总损耗、初始损耗、hparams）
列车中第153行的文件“train.py”
init_fn=init_fn）
文件“/usr/lib/python2.7/site packages/tensorflow/contrib/slim/python/slim/learning.py”，第688行，列车中
saver=saver或tf_saver.saver（）
文件“/usr/lib/python2.7/site packages/tensorflow/python/training/saver.py”，第1040行，在__
self.build（）
文件“/usr/lib/python2.7/site packages/tensorflow/python/training/saver.py”，第1070行，内部版本
按顺序还原=自。_按顺序还原）
文件“/usr/lib/python2.7/site packages/tensorflow/python/training/saver.py”，第675行，内部版本
恢复（按顺序，重塑）
文件“/usr/lib/python2.7/site packages/tensorflow/python/training/saver.py”，第414行，在_AddRestoreOps中
赋值操作追加（可保存还原（张量、形状））
文件“/usr/lib/python2.7/site packages/tensorflow/python/training/saver.py”，第155行，在restore中
self.op.get_shape（）是完全定义的（）
文件“/usr/lib/python2.7/site packages/tensorflow/python/ops/gen_state_ops.py”，第47行，在assign中
使用锁定=使用锁定，名称=名称）
文件“/usr/lib/python2.7/site packages/tensorflow/python/framework/op_def_library.py”，第763行，在apply_op
op_def=op_def）
文件“/usr/lib/python2.7/site packages/tensorflow/python/framework/ops.py”，第2327行，在create_op中
初始值=自身值。\默认值\初始值，初始值=初始值）
文件“/usr/lib/python2.7/site packages/tensorflow/python/framework/ops.py”，第1226行，在__
self.\u traceback=\u extract\u stack（）
InvalidArgumentError（回溯见上文）：Assign要求两个张量的形状匹配。左侧形状=[37943506]右侧形状=[422134]
[[Node:save/Assign\u 175=Assign[T=DT\u FLOAT，\u class=[“loc:@AttentionOcr\u v1/sequence\u logit\u fn/SQLR/LSTM/attention\u decoder/weights”]，使用锁定=true，验证形状=true，\u device=“/job:localhost/replica:0/task:0/gpu:0”]（AttentionOcr\u v1/sequence\u logit\u fn/SQLR/LSTM/attention\u解码器/weights/moment，save/RestoreV2\u 175/]15]
[[Node:save/RestoreV2_141/\u 168=\u 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_device_化身=1，tensor__name=“edge715_save/restorev2141”，“_device=“/job:localhost/replica:0/task:0/cpu:0]”（save/RestoreV2）]

既然我使用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，为什么会发生此错误？也许你的项目中有一些硬代码，所以他们总是称之为“134字符集”

---

希望得到作者或其他人的回复。

代码使用了存储在我的tmp路径中的预训练模型，我清理/tmp来解决它