下面是我的代码，用于微调Universal Sentence Encoder Multilingual Large2。我无法解决导致的错误。我尝试添加一个tf.keras.layers.Input层，导致同样的错误。对于如何为USEM2成功建立微调顺序模型的任何建议，将不胜感激。
import tensorflow as tf
import tensorflow_text
import tensorflow_hub as hub
module_url = "https://tfhub.dev/google/universal-sentence-encoder-multilingual-large/2"
embedding_layer = hub.KerasLayer(module_url, trainable=True, input_shape=[None,], dtype=tf.string)
hidden_layer = tf.keras.layers.Dense(32, activation='relu')
output_layer = tf.keras.layers.Dense(5, activation='softmax')
model = tf.keras.models.Sequential()
model.add(embedding_layer)
model.add(hidden_layer)
model.add(output_layer)
model.summary()
WARNING:tensorflow:Entity <tensorflow.python.saved_model.function_deserialization.RestoredFunction object at 0x7fdf34216390> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: Shape must be rank 1 but is rank 2 for 'text_preprocessor_1/SentenceTokenizer/SentencepieceTokenizeOp' (op: 'SentencepieceTokenizeOp') with input shapes: [], [?,?], [], [], [], [], [].
WARNING:tensorflow:Entity <tensorflow.python.saved_model.function_deserialization.RestoredFunction object at 0x7fdf34216390> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: Shape must be rank 1 but is rank 2 for 'text_preprocessor_1/SentenceTokenizer/SentencepieceTokenizeOp' (op: 'SentencepieceTokenizeOp') with input shapes: [], [?,?], [], [], [], [], [].
WARNING: Entity <tensorflow.python.saved_model.function_deserialization.RestoredFunction object at 0x7fdf34216390> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: Shape must be rank 1 but is rank 2 for 'text_preprocessor_1/SentenceTokenizer/SentencepieceTokenizeOp' (op: 'SentencepieceTokenizeOp') with input shapes: [], [?,?], [], [], [], [], [].
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-61-7ea0d071abf8> in <module>
1 model = tf.keras.models.Sequential()
2
----> 3 model.add(embedding_layer)
4 model.add(hidden_layer)
5 model.add(output)
~/pyenv36/lib/python3.6/site-packages/tensorflow_core/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
455 self._self_setattr_tracking = False # pylint: disable=protected-access
456 try:
--> 457 result = method(self, *args, **kwargs)
458 finally:
459 self._self_setattr_tracking = previous_value # pylint: disable=protected-access
~/pyenv36/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/sequential.py in add(self, layer)
176 # and create the node connecting the current layer
177 # to the input layer we just created.
--> 178 layer(x)
179 set_inputs = True
180
~/pyenv36/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/base_layer.py in __call__(self, inputs, *args, **kwargs)
840 not base_layer_utils.is_in_eager_or_tf_function()):
841 with auto_control_deps.AutomaticControlDependencies() as acd:
--> 842 outputs = call_fn(cast_inputs, *args, **kwargs)
843 # Wrap Tensors in `outputs` in `tf.identity` to avoid
844 # circular dependencies.
~/pyenv36/lib/python3.6/site-packages/tensorflow_core/python/autograph/impl/api.py in wrapper(*args, **kwargs)
235 except Exception as e: # pylint:disable=broad-except
236 if hasattr(e, 'ag_error_metadata'):
--> 237 raise e.ag_error_metadata.to_exception(e)
238 else:
239 raise
ValueError: in converted code:
relative to /home/neubig/pyenv36/lib/python3.6/site-packages:
tensorflow_hub/keras_layer.py:209 call *
result = f()
tensorflow_core/python/saved_model/load.py:436 _call_attribute
return instance.__call__(*args, **kwargs)
tensorflow_core/python/eager/def_function.py:457 __call__
result = self._call(*args, **kwds)
tensorflow_core/python/eager/def_function.py:494 _call
results = self._stateful_fn(*args, **kwds)
tensorflow_core/python/eager/function.py:1823 __call__
return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access
tensorflow_core/python/eager/function.py:1141 _filtered_call
self.captured_inputs)
tensorflow_core/python/eager/function.py:1230 _call_flat
flat_outputs = forward_function.call(ctx, args)
tensorflow_core/python/eager/function.py:540 call
executor_type=executor_type)
tensorflow_core/python/ops/functional_ops.py:859 partitioned_call
executor_type=executor_type)
tensorflow_core/python/ops/gen_functional_ops.py:672 stateful_partitioned_call
executor_type=executor_type, name=name)
tensorflow_core/python/framework/op_def_library.py:793 _apply_op_helper
op_def=op_def)
tensorflow_core/python/framework/func_graph.py:548 create_op
compute_device)
tensorflow_core/python/framework/ops.py:3429 _create_op_internal
op_def=op_def)
tensorflow_core/python/framework/ops.py:1773 __init__
control_input_ops)
tensorflow_core/python/framework/ops.py:1613 _create_c_op
raise ValueError(str(e))
ValueError: Shape must be rank 1 but is rank 2 for 'text_preprocessor_1/SentenceTokenizer/SentencepieceTokenizeOp' (op: 'SentencepieceTokenizeOp') with input shapes: [], [?,?], [], [], [], [], [].
答案 0 :(得分：0)
据我所知，到目前为止，tf.hub中的Universal Sentence Encoder Multilingual还不支持trainable=True。
但是，这些代码片段可以使模型进行推断：
使用V2
module_url = "https://tfhub.dev/google/universal-sentence-encoder-multilingual-large/2"
embedding_layer = hub.KerasLayer(module_url)
hidden_layer = tf.keras.layers.Dense(32, activation='relu')
output_layer = tf.keras.layers.Dense(5, activation='softmax')
inputs = tf.keras.layers.Input(shape=(1,), dtype=tf.string)
x = embedding_layer(tf.squeeze(tf.cast(inputs, tf.string)))["outputs"]
x = hidden_layer(x)
outputs = output_layer(x)
model = tf.keras.Model(inputs=inputs, outputs=outputs)
使用V3
module_url = "https://tfhub.dev/google/universal-sentence-encoder-multilingual-large/3"
embedding_layer = hub.KerasLayer(module_url)
hidden_layer = tf.keras.layers.Dense(32, activation='relu')
output_layer = tf.keras.layers.Dense(5, activation='softmax')
inputs = tf.keras.layers.Input(shape=(1,), dtype=tf.string)
x = embedding_layer(tf.squeeze(tf.cast(inputs, tf.string)))
x = hidden_layer(x)
outputs = output_layer(x)
model = tf.keras.Model(inputs=inputs, outputs=outputs)
推断
model.predict([["hello tf2"]])