对于LSTM，我使用tensorflow.keras.utils.timeseries_dataset_from_array()创建时间序列。对于某些特性，我希望使用Keras预处理层进行one-hot编码。
下面的代码：

n_timesteps = 20
n_categorical_features = 1

from tensorflow.keras.layers import Input, IntegerLookup, CategoryEncoding

cat_inp = keras.layers.Input(shape=(n_timesteps, n_categorical_features), name = "categorical_input")
index = IntegerLookup()
index.adapt(X["br"])
encoder = CategoryEncoding(num_tokens=index.vocabulary_size(), output_mode = "one_hot")(cat_inp)

然而，最后一行给了我错误ValueError: Exception encountered when calling layer "category_encoding_22" (type CategoryEncoding). When output_mode is not 'int' , maximum supported output rank is 2. Received output_mode one_hot and input shape (None, 20, 1), which would result in output rank 3.问题似乎是CategoryEncoding不支持输入Tensor的形状（None，n_timesteps，n_categorical_features）。
如何对timeseries_dataset_from_array()产生的输入Tensor进行one-hot编码？