模型训练时报错Cast int64 to string is not supported

源码

import tensorflow as tf
import sys

# # Training samples path, change to your local path
# training_samples_file_path = tf.keras.utils.get_file("trainingSamples.csv",
#                                                      "file:///D:/workSpace/senro-tree-recommend/src/main"+
#                                                      "/resources/static/sampledata/trainingSamples2/part-00000-56521c27-aadd-4b1d-b7b3-417a39f0f3c8-c000.csv")
# # Test samples path, change to your local path
# test_samples_file_path = tf.keras.utils.get_file("testSamples.csv",
#                                                  "file:///D:/workSpace/senro-tree-recommend/src/main"+
#                                                  "/resources/static/sampledata/testSamples2/part-00000-8ec63f48-ecca-49cb-af35-25a6f6da3425-c000.csv")

# basePath=sys.argv[1]
basePath="D:/data/work/"
trainPath="file:///"+basePath+"sampledata/trainingSamples2"
testPath="file:///"+basePath+"sampledata/testSamples2"
tensorPath=basePath+"tensor"

# Training samples path, change to your local path
training_samples_file_path = tf.keras.utils.get_file("trainingSamples.csv",
                                                     trainPath)
# Test samples path, change to your local path
test_samples_file_path = tf.keras.utils.get_file("testSamples.csv",
                                                 testPath)


# load sample as tf dataset
def get_dataset(file_path):
    dataset = tf.data.experimental.make_csv_dataset(
        file_path,
        batch_size=12,
        label_name='label',
        na_value="0",
        num_epochs=1,
        ignore_errors=True)
    return dataset


# split as test dataset and training dataset
train_dataset = get_dataset(training_samples_file_path)
test_dataset = get_dataset(test_samples_file_path)

# item id embedding feature
# movie_col = tf.feature_column.categorical_column_with_identity(key='itemId', num_buckets=1001)
movie_col = tf.feature_column.categorical_column_with_hash_bucket(key='itemId', hash_bucket_size=1001)
movie_emb_col = tf.feature_column.embedding_column(movie_col, 10)

# user id embedding feature
# user_col = tf.feature_column.categorical_column_with_identity(key='userId', num_buckets=30001)
user_col = tf.feature_column.categorical_column_with_hash_bucket(key='userId', hash_bucket_size=30001)
user_emb_col = tf.feature_column.embedding_column(user_col, 10)

# define