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 input for keras model
inputs = {
    'itemId': tf.keras.layers.Input(name='itemId', shape=(), dtype='string'),
    'userId': tf.keras.layers.Input(name='userId', shape=(), dtype='string'),
    'rating': tf.keras.layers.Input(name='rating', shape=(), dtype='float32'),
    'timestamp': tf.keras.layers.Input(name='timestamp', shape=(), dtype='int32'),
    'releaseYear': tf.keras.layers.Input(name='releaseYear', shape=(), dtype='int32'),
    'movieGenre1': tf.keras.layers.Input(name='movieGenre1', shape=(), dtype='string'),
    'movieGenre2': tf.keras.layers.Input(name='movieGenre2', shape=(), dtype='string'),
    'movieGenre3': tf.keras.layers.Input(name='movieGenre3', shape=(), dtype='string'),
    # 'movieGenre4': tf.keras.layers.Input(name='movieGenre4', shape=(), dtype='string'),
    # 'movieGenre5': tf.keras.layers.Input(name='movieGenre5', shape=(), dtype='string'),

    'movieAvgRating': tf.keras.layers.Input(name='movieAvgRating', shape=(), dtype='float32'),
    'movieRatingStddev': tf.keras.layers.Input(name='movieRatingStddev', shape=(), dtype='float32'),
    'movieRatingCount': tf.keras.layers.Input(name='movieRatingCount', shape=(), dtype='int32'),
    'userRatedMovie1': tf.keras.layers.Input(name='userRatedMovie1', shape=(), dtype='int32'),
    'userRatedMovie2': tf.keras.layers.Input(name='userRatedMovie2', shape=(), dtype='int32'),
    'userRatedMovie3': tf.keras.layers.Input(name='userRatedMovie3', shape=(), dtype='int32'),
    'userRatedMovie4': tf.keras.layers.Input(name='userRatedMovie4', shape=(), dtype='int32'),
    'userRatedMovie5': tf.keras.layers.Input(name='userRatedMovie5', shape=(), dtype='int32'),

    'userAvgReleaseYear': tf.keras.layers.Input(name='userAvgReleaseYear', shape=(), dtype='float32'),
    'userReleaseYearStddev': tf.keras.layers.Input(name='userReleaseYearStddev', shape=(), dtype='float32'),
    'userAvgRating': tf.keras.layers.Input(name='userAvgRating', shape=(), dtype='float32'),
    'userRatingStddev': tf.keras.layers.Input(name='userRatingStddev', shape=(), dtype='float32'),
    'userRatingCount': tf.keras.layers.Input(name='userRatingCount', shape=(), dtype='int32'),
    'userGenre1': tf.keras.layers.Input(name='userGenre1', shape=(), dtype='string'),
    'userGenre2': tf.keras.layers.Input(name='userGenre2', shape=(), dtype='string'),
    'userGenre3': tf.keras.layers.Input(name='userGenre3', shape=(), dtype='string'),
    'userGenre4': tf.keras.layers.Input(name='userGenre4', shape=(), dtype='string'),
    'userGenre5': tf.keras.layers.Input(name='userGenre5', shape=(), dtype='string'),
}


# neural cf model arch two. only embedding in each tower, then MLP as the interaction layers
def neural_cf_model_1(feature_inputs, item_feature_columns, user_feature_columns, hidden_units):
    item_tower = tf.keras.layers.DenseFeatures(item_feature_columns)(feature_inputs)
    user_tower = tf.keras.layers.DenseFeatures(user_feature_columns)(feature_inputs)
    interact_layer = tf.keras.layers.concatenate([item_tower, user_tower])
    for num_nodes in hidden_units:
        interact_layer = tf.keras.layers.Dense(num_nodes, activation='relu')(interact_layer)
    output_layer = tf.keras.layers.Dense(1, activation='sigmoid')(interact_layer)
    neural_cf_model = tf.keras.Model(feature_inputs, output_layer)
    return neural_cf_model


# neural cf model arch one. embedding+MLP in each tower, then dot product layer as the output
def neural_cf_model_2(feature_inputs, item_feature_columns, user_feature_columns, hidden_units):
    item_tower = tf.keras.layers.DenseFeatures(item_feature_columns)(feature_inputs)
    for num_nodes in hidden_units:
        item_tower = tf.keras.layers.Dense(num_nodes, activation='relu')(item_tower)

    user_tower = tf.keras.layers.DenseFeatures(user_feature_columns)(feature_inputs)
    for num_nodes in hidden_units:
        user_tower = tf.keras.layers.Dense(num_nodes, activation='relu')(user_tower)

    output = tf.keras.layers.Dot(axes=1)([item_tower, user_tower])
    output = tf.keras.layers.Dense(1, activation='sigmoid')(output)

    neural_cf_model = tf.keras.Model(feature_inputs, output)
    return neural_cf_model


# neural cf model architecture
model = neural_cf_model_1(inputs, [movie_emb_col], [user_emb_col], [10, 10])

# compile the model, set loss function, optimizer and evaluation metrics
model.compile(
    loss='binary_crossentropy',
    optimizer='adam',
    metrics=['accuracy', tf.keras.metrics.AUC(curve='ROC'), tf.keras.metrics.AUC(curve='PR')])

# train the model
model.fit(train_dataset, epochs=5)

# evaluate the model
test_loss, test_accuracy, test_roc_auc, test_pr_auc = model.evaluate(test_dataset)
print('\n\nTest Loss {}, Test Accuracy {}, Test ROC AUC {}, Test PR AUC {}'.format(test_loss, test_accuracy,
                                                                                   test_roc_auc, test_pr_auc))

# print some predict results
predictions = model.predict(test_dataset)
for prediction, goodRating in zip(predictions[:12], list(test_dataset)[0][1][:12]):
    print("Predicted good rating: {:.2%}".format(prediction[0]),
          " | Actual rating label: ",
          ("Good Rating" if bool(goodRating) else "Bad Rating"))

tf.keras.models.save_model(
    model,
    tensorPath,
    overwrite=True,
    include_optimizer=True,
    save_format=None,
    signatures=None,
    options=None
)

报错信息如下： 

D:\packagepath\python3.7.5\python.exe D:/data/pythonProject/neuralCF2.py
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
2022-03-08 15:32:04.011173: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Epoch 1/5
2022-03-08 15:32:05.163598: W tensorflow/core/framework/op_kernel.cc:1722] OP_REQUIRES failed at cast_op.cc:121 : UNIMPLEMENTED: Cast int64 to string is not supported
Traceback (most recent call last):
  File "D:/data/pythonProject/neuralCF2.py", line 127, in 
    model.fit(train_dataset, epochs=5)
  File "D:\packagepath\python3.7.5\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "D:\packagepath\python3.7.5\lib\site-packages\tensorflow\python\eager\execute.py", line 55, in quick_execute
    inputs, attrs, num_outputs)
tensorflow.python.framework.errors_impl.UnimplementedError: Graph execution error:

Detected at node 'model/Cast_5' defined at (most recent call last):
    File "D:/data/pythonProject/neuralCF2.py", line 127, in 
      model.fit(train_dataset, epochs=5)
    File "D:\packagepath\python3.7.5\lib\site-packages\keras\utils\traceback_utils.py", line 64, in error_handler
      return fn(*args, **kwargs)
    File "D:\packagepath\python3.7.5\lib\site-packages\keras\engine\training.py", line 1384, in fit
      tmp_logs = self.train_function(iterator)
    File "D:\packagepath\python3.7.5\lib\site-packages\keras\engine\training.py", line 1021, in train_function
      return step_function(self, iterator)
    File "D:\packagepath\python3.7.5\lib\site-packages\keras\engine\training.py", line 1010, in step_function
      outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "D:\packagepath\python3.7.5\lib\site-packages\keras\engine\training.py", line 1000, in run_step
      outputs = model.train_step(data)
    File "D:\packagepath\python3.7.5\lib\site-packages\keras\engine\training.py", line 859, in train_step
      y_pred = self(x, training=True)
    File "D:\packagepath\python3.7.5\lib\site-packages\keras\utils\traceback_utils.py", line 64, in error_handler
      return fn(*args, **kwargs)
    File "D:\packagepath\python3.7.5\lib\site-packages\keras\engine\base_layer.py", line 1096, in __call__
      outputs = call_fn(inputs, *args, **kwargs)
    File "D:\packagepath\python3.7.5\lib\site-packages\keras\utils\traceback_utils.py", line 92, in error_handler
      return fn(*args, **kwargs)
    File "D:\packagepath\python3.7.5\lib\site-packages\keras\engine\functional.py", line 452, in call
      inputs, training=training, mask=mask)
    File "D:\packagepath\python3.7.5\lib\site-packages\keras\engine\functional.py", line 571, in _run_internal_graph
      y = self._conform_to_reference_input(y, ref_input=x)
    File "D:\packagepath\python3.7.5\lib\site-packages\keras\engine\functional.py", line 671, in _conform_to_reference_input
      tensor = tf.cast(tensor, dtype=ref_input.dtype)
Node: 'model/Cast_5'
Cast int64 to string is not supported
	 [[{{node model/Cast_5}}]] [Op:__inference_train_function_2550]

Process finished with exit code 1

 

各位大佬求救！！！