tensorflow - keras.layers.TimeDistributed with Huggingface Transformer 给出 NotImplementedError

Question

我想以下列方式将 Bert 应用于一系列句子，但我得到了 NotImplementedError

如何重现：

import tensorflow as tf
from transformers import BertTokenizer, TFBertModel
inputs = tf.keras.Input(shape=(50, 64), dtype='int32')
model = TFBertModel.from_pretrained('bert-base-uncased')
outputs = tf.keras.layers.TimeDistributed(model)(inputs)

NotImplementedError                       Traceback (most recent call last)
<ipython-input-5-631f3cd2e8b2> in <module>
----> 1 outputs = tf.keras.layers.TimeDistributed(model)(inputs)

而代码可以正常工作

inputs = tf.keras.Input(shape=(10, 128, 128, 3))
conv_2d_layer = tf.keras.layers.Conv2D(64, (3, 3))
outputs = tf.keras.layers.TimeDistributed(conv_2d_layer)(inputs)

我在这里有什么遗漏吗？

标签： tensorflowkerastensorflow2.0huggingface-transformers