如何在不获取 "Function call stack: pruned" 的情况下为标记化字符串生成 ELMo 嵌入？

Question

我正在尝试为成批的标记化字符串生成 ELMo 嵌入。但是我不断收到以下错误：

Traceback (most recent call last):
  File "/home/lorcan/.local/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 3326, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-2-0d50a997dad6>", line 17, in <module>
    embeddings = elmo(tokens=tokens2, sequence_len=lens2)['elmo']
  File "/home/lorcan/anaconda3/envs/ncr_elmo/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1605, in __call__
    return self._call_impl(args, kwargs)
  File "/home/lorcan/anaconda3/envs/ncr_elmo/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1645, in _call_impl
    return self._call_flat(args, self.captured_inputs, cancellation_manager)
  File "/home/lorcan/anaconda3/envs/ncr_elmo/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1746, in _call_flat
    ctx, args, cancellation_manager=cancellation_manager))
  File "/home/lorcan/anaconda3/envs/ncr_elmo/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 598, in call
    ctx=ctx)
  File "/home/lorcan/anaconda3/envs/ncr_elmo/lib/python3.6/site-packages/tensorflow/python/eager/execute.py", line 60, in quick_execute
    inputs, attrs, num_outputs)
tensorflow.python.framework.errors_impl.InvalidArgumentError:  Incompatible shapes: [4,5,1] vs. [4,9,1024]
     [[node mul (defined at /home/lorcan/anaconda3/envs/ncr_elmo/lib/python3.6/site-packages/tensorflow_hub/module_v2.py:106) ]] [Op:__inference_pruned_4853]
Function call stack:
pruned

这里出了什么问题？嵌入张量是不是太大了？我正在使用 Python 3.6.13 tensorflow==2.2.0、tensorflow-estimator==2.2.0 和 tensorflow-hub==0.12.0。

下面的代码重现了错误：

import tensorflow as tf
import tensorflow_hub as hub

elmo = hub.load('https://tfhub.dev/google/elmo/3').signatures['tokens']

tokens = tf.convert_to_tensor(
    [[b'fetal', b'derived', b'definitive', b'erythrocyte', b'', b'', b'', b'', b''],
     [b'splenic', b'red', b'pulp', b'macrophage', b'', b'', b'', b'', b''],
     [b'juxtaglomerular', b'complex', b'cell', b'', b'', b'', b'', b'', b''],
     [b'epithelial', b'cell', b'of', b'large', b'intestine', b'', b'', b'', b'']],
    tf.string)

lens = tf.convert_to_tensor([4, 4, 3, 5], tf.int32)

embeddings = elmo(tokens=tokens, sequence_len=lens)['elmo']

Answer 1

当删除 tokens 中的尾随空格时，它对我有用，这样至少有一个条目不会以 b'' 结尾，即

tokens = tf.convert_to_tensor(
    [[b'fetal', b'derived', b'definitive', b'erythrocyte', b''],
     [b'splenic', b'red', b'pulp', b'macrophage', b''],
     [b'juxtaglomerular', b'complex', b'cell', b'', b''],
     [b'epithelial', b'cell', b'of', b'large', b'intestine']],
    tf.string)

如何在不获取 "Function call stack: pruned" 的情况下为标记化字符串生成 ELMo 嵌入？

How do I produce ELMo embeddings for tokenised strings without getting "Function call stack: pruned"?

python-3.x

tensorflow

tensorflow-hub

elmo