问题
I have created a binary classifier with Tensorflow BERT language model. Here is the link. After the model is trained, it saves the model and produces the following files.
Prediction code.
from tensorflow.contrib import predictor
#MODEL_FILE = 'graph.pbtxt'
with tf.Session() as sess:
predict_fn = predictor.from_saved_model(f'/content/drive/My Drive/binary_class/bert/graph.pbtxt')
predictions = predict_fn(pred_sentences)
print(predictions)
Error
OSError: SavedModel file does not exist at: /content/drive/My Drive/binary_class/bert/graph.pbtxt/{saved_model.pbtxt|saved_model.pb}
After digging in this issue. I came across tf.train.Saver() class for saving the model. I changed the estimator train code to following to save the model. I referred this link. I guess tensorflow estimators can be saved with it.
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init_op)
# Do some work with the model.
saver = tf.train.Saver()
estimator.train(input_fn=train_input_fn, max_steps=num_train_steps)
# Save the variables to disk.
save_path = saver.save(sess, f'/content/drive/My Drive/binary_class/bert/tmp/model.ckpt')
And here is the error.
Beginning Training!
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-38-0c9f9b70d76b> in <module>()
9 sess.run(init_op)
10 # Do some work with the model.
---> 11 saver = tf.train.Saver()
12 estimator.train(input_fn=train_input_fn, max_steps=num_train_steps)
13 # Save the variables to disk.
2 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py in _build(self, checkpoint_path, build_save, build_restore)
860 return
861 else:
--> 862 raise ValueError("No variables to save")
863 self._is_empty = False
864
ValueError: No variables to save
The variables, weights are created in create_model function. What should I change to save my trained model?
Updates: Code to save the model. I am not sure about the feature_spec and feature tensor.
feature_spec = {'x': tf.VarLenFeature(tf.string)}
def serving_input_receiver_fn():
serialized_tf_example = tf.placeholder(dtype=tf.string,
shape=[1], # batch size
name='input_example_tensor')
receiver_tensors = {'examples': serialized_tf_example}
features = tf.parse_example(serialized_tf_example, feature_spec)
return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)
# Export the estimator
export_path = f'/content/drive/My Drive/binary_class/bert/'
estimator.export_saved_model(
export_path,
serving_input_receiver_fn=serving_input_receiver_fn)
I got this error :-
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-55-209298910d1e> in <module>()
16 estimator.export_saved_model(
17 export_path,
---> 18 serving_input_receiver_fn=serving_input_receiver_fn)
4 frames
/usr/local/lib/python3.6/dist-packages/tensorflow_estimator/python/estimator/estimator.py in export_saved_model(self, export_dir_base, serving_input_receiver_fn, assets_extra, as_text, checkpoint_path, experimental_mode)
730 as_text=as_text,
731 checkpoint_path=checkpoint_path,
--> 732 strip_default_attrs=True)
733
734 def experimental_export_all_saved_models(
/usr/local/lib/python3.6/dist-packages/tensorflow_estimator/python/estimator/estimator.py in _export_all_saved_models(self, export_dir_base, input_receiver_fn_map, assets_extra, as_text, checkpoint_path, strip_default_attrs)
854 builder, input_receiver_fn_map, checkpoint_path,
855 save_variables, mode=ModeKeys.PREDICT,
--> 856 strip_default_attrs=strip_default_attrs)
857 save_variables = False
858
/usr/local/lib/python3.6/dist-packages/tensorflow_estimator/python/estimator/estimator.py in _add_meta_graph_for_mode(self, builder, input_receiver_fn_map, checkpoint_path, save_variables, mode, export_tags, check_variables, strip_default_attrs)
927 labels=getattr(input_receiver, 'labels', None),
928 mode=mode,
--> 929 config=self.config)
930
931 export_outputs = export_lib.export_outputs_for_mode(
/usr/local/lib/python3.6/dist-packages/tensorflow_estimator/python/estimator/estimator.py in _call_model_fn(self, features, labels, mode, config)
1144
1145 logging.info('Calling model_fn.')
-> 1146 model_fn_results = self._model_fn(features=features, **kwargs)
1147 logging.info('Done calling model_fn.')
1148
<ipython-input-17-119a3167bf33> in model_fn(features, labels, mode, params)
5 """The `model_fn` for TPUEstimator."""
6
----> 7 input_ids = features["input_ids"]
8 input_mask = features["input_mask"]
9 segment_ids = features["segment_ids"]
KeyError: 'input_ids'
回答1:
The create_model function present in notebook takes some arguments. These features are passed to the model.
By updating the serving_input_fn function to following, the serving function works as expected.
Updated Code
def serving_input_receiver_fn():
feature_spec = {
"input_ids" : tf.FixedLenFeature([MAX_SEQ_LENGTH], tf.int64),
"input_mask" : tf.FixedLenFeature([MAX_SEQ_LENGTH], tf.int64),
"segment_ids" : tf.FixedLenFeature([MAX_SEQ_LENGTH], tf.int64),
"label_ids" : tf.FixedLenFeature([], tf.int64)
}
serialized_tf_example = tf.placeholder(dtype=tf.string,
shape=[None],
name='input_example_tensor')
print(serialized_tf_example.shape)
receiver_tensors = {'example': serialized_tf_example}
features = tf.parse_example(serialized_tf_example, feature_spec)
return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)
export_path = '/content/drive/My Drive/binary_class/bert/'
estimator._export_to_tpu = False # this is important
estimator.export_saved_model(export_dir_base=export_path,serving_input_receiver_fn=serving_input_receiver_fn)
来源：https://stackoverflow.com/questions/56831583/saving-and-doing-inference-with-tensorflow-bert-model