tensorflow: [TF2.0.0]ValueError: The two structures don't have the same nested structure.

I can run my code in tensorflow==2.0.0b1, but when I update tensorflow to 2.0.0; I got an error; This is my code:

import tensorflow as tf
from tensorflow import feature_column

print('tf version:', tf.__version__)

feature_description = {
    'h_k_u_watchanch_his': tf.io.VarLenFeature(tf.string),
    'a_gender': tf.io.FixedLenFeature(shape=(1,), dtype=tf.int64),
    'l_label': tf.io.FixedLenFeature([], tf.int64)
}
feature_columns = []
thal = feature_column.categorical_column_with_hash_bucket(
    'h_k_u_watchanch_his', hash_bucket_size=100
)
thal_one_hot = feature_column.embedding_column(thal, dimension=10, combiner='mean')
feature_columns.append(thal_one_hot)

dataSet = tf.data.TFRecordDataset(
    "/Users/lyx/projects/recommend/embedding/tmp/PUSH.TFRecords/dt=20191012/hour=10/part-r-00000")


def _parse_function(serilized_example):
    feature = tf.io.parse_single_example(
        serilized_example,
        feature_description
    )
    label = feature.get('l_label')
    return feature, label


parsed_dataset = dataSet.map(_parse_function)

input1 = tf.keras.Input(shape=(), name='h_k_u_watchanch_his', sparse=True, dtype=tf.string)
input2 = tf.keras.Input(shape=(), name='a_gender', dtype=tf.int64)

input_layers = {'h_k_u_watchanch_his': input1, 'a_gender': input2}
feature_layer = tf.keras.layers.DenseFeatures(feature_columns, name='DenseFeatures')(input_layers)
outputs = tf.keras.layers.Dense(1, activation='sigmoid')(feature_layer)
model = tf.keras.Model(inputs=[input1, input2], outputs=outputs)

model.compile(
    optimizer='adam',
    loss='binary_crossentropy',
    metrics=['accuracy']
)

model.fit(
    x=parsed_dataset,
    validation_data=parsed_dataset,
    epochs=5,
)

loss, accuracy = model.evaluate(parsed_dataset)
print("Accuracy", accuracy)

Error output:

tf version: 2.0.0
2019-10-18 09:59:10.095365: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2019-10-18 09:59:10.118556: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fbcd9c21e00 executing computations on platform Host. Devices:
2019-10-18 09:59:10.118572: I tensorflow/compiler/xla/service/service.cc:175]   StreamExecutor device (0): Host, Default Version
Traceback (most recent call last):
  File "/usr/local/lib/python3.7/site-packages/tensorflow_core/python/util/nest.py", line 318, in assert_same_structure
    expand_composites)
ValueError: The two structures don't have the same nested structure.

First structure: type=TensorSpec str=TensorSpec(shape=(1,), dtype=tf.int64, name=None)

Second structure: type=SparseTensor str=SparseTensor(indices=Tensor("h_k_u_watchanch_his/indices:0", shape=(None, 1), dtype=int64), values=Tensor("h_k_u_watchanch_his/values:0", shape=(None,), dtype=string), dense_shape=Tensor("h_k_u_watchanch_his/shape:0", shape=(1,), dtype=int64))

More specifically: Substructure "type=SparseTensor str=SparseTensor(indices=Tensor("h_k_u_watchanch_his/indices:0", shape=(None, 1), dtype=int64), values=Tensor("h_k_u_watchanch_his/values:0", shape=(None,), dtype=string), dense_shape=Tensor("h_k_u_watchanch_his/shape:0", shape=(1,), dtype=int64))" is a sequence, while substructure "type=TensorSpec str=TensorSpec(shape=(1,), dtype=tf.int64, name=None)" is not

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/lyx/projects/recommend/embedding/tmp/test.py", line 52, in <module>
    epochs=5,
  File "/usr/local/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 728, in fit
    use_multiprocessing=use_multiprocessing)
  File "/usr/local/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 224, in fit
    distribution_strategy=strategy)
  File "/usr/local/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 547, in _process_training_inputs
    use_multiprocessing=use_multiprocessing)
  File "/usr/local/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 594, in _process_inputs
    steps=steps)
  File "/usr/local/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 2497, in _standardize_user_data
    nest.assert_same_structure(a, b, expand_composites=True)
  File "/usr/local/lib/python3.7/site-packages/tensorflow_core/python/util/nest.py", line 325, in assert_same_structure
    % (str(e), str1, str2))
ValueError: The two structures don't have the same nested structure.

First structure: type=TensorSpec str=TensorSpec(shape=(1,), dtype=tf.int64, name=None)

Second structure: type=SparseTensor str=SparseTensor(indices=Tensor("h_k_u_watchanch_his/indices:0", shape=(None, 1), dtype=int64), values=Tensor("h_k_u_watchanch_his/values:0", shape=(None,), dtype=string), dense_shape=Tensor("h_k_u_watchanch_his/shape:0", shape=(1,), dtype=int64))

More specifically: Substructure "type=SparseTensor str=SparseTensor(indices=Tensor("h_k_u_watchanch_his/indices:0", shape=(None, 1), dtype=int64), values=Tensor("h_k_u_watchanch_his/values:0", shape=(None,), dtype=string), dense_shape=Tensor("h_k_u_watchanch_his/shape:0", shape=(1,), dtype=int64))" is a sequence, while substructure "type=TensorSpec str=TensorSpec(shape=(1,), dtype=tf.int64, name=None)" is not
Entire first structure:
.
Entire second structure:
.

Looking forward to your reply!