如何从加载的 BERT tensorflow model 进行预测

Question

I was trying to make a prediction from a loaded tensorflow model. Though I'm not sure if it's correct how I previously saved it, specifically I have doubts about code inside serving_input_fn() function (MAX_SEQ_LENGTH=128):

def serving_input_fn():   
    feature_spec = {   "input_ids" : tf.FixedLenFeature([None,MAX_SEQ_LENGTH], tf.int64),                
                     "input_mask" : tf.FixedLenFeature([None,MAX_SEQ_LENGTH], tf.int64),       
                   "segment_ids" : tf.FixedLenFeature([None,MAX_SEQ_LENGTH], tf.int64),       
                   "label_ids" :  tf.FixedLenFeature([None], tf.int64)    }   

    serialized_tf_example = tf.placeholder(dtype=tf.string,shape=[None],name='input_example_tensor')   
    receiver_tensors = {'example': serialized_tf_example}   
    features = tf.parse_example(serialized_tf_example, feature_spec) 

    return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)  

estimator.export_saved_model('gs://bucket/trained_model', serving_input_receiver_fn=serving_input_fn)

When I try to predict from loaded model:

from tensorflow.contrib import predictor
predict_fn = predictor.from_saved_model(LOAD_PATH)
input_features_test = convert_examples_to_features( test_examples,label_list, MAX_SEQ_LENGTH, tokenizer)
predictions = predict_fn({'example':input_features_test[0]})

it returns this error:

ValueError: Cannot feed value of shape () for Tensor 'input_example_tensor:0', which has shape '(?,)'

How should I change serving_input_fn() method?

If you want to reproduce it: github_repo (you should download variables from here and put it in trained_model/1608370941/ folder)

This is the tutorial I followed to fine tuned BERT model on google cloud TPU.

Answer 1

I saved the model using following serving_input_fn() function (found in this tutorial ):

def serving_input_fn():
    label_ids = tf.placeholder(tf.int32, [None], name='label_ids')
    input_ids = tf.placeholder(tf.int32, [None, MAX_SEQ_LENGTH], name='input_ids')
    input_mask = tf.placeholder(tf.int32, [None, MAX_SEQ_LENGTH], name='input_mask')
    segment_ids = tf.placeholder(tf.int32, [None, MAX_SEQ_LENGTH], name='segment_ids')
    input_fn = tf.estimator.export.build_raw_serving_input_receiver_fn({
        'label_ids': label_ids,
        'input_ids': input_ids,
        'input_mask': input_mask,
        'segment_ids': segment_ids,
    })()
    return input_fn

Then I loaded it using the code mentioned below:

from tensorflow.contrib import predictor
predict_fn = predictor.from_saved_model(LOAD_PATH_GCP)

I converted input string to BERT model input features with following method:

def convert_single_string_to_input_dict(example_string_prep, vocab_file_path, max_seq_length):
  
  #Inizialize BERT tokenizer
  tokenizer = tokenization.FullTokenizer(vocab_file_path, do_lower_case=True)
  token_a = tokenizer.tokenize(example_string_prep)

  tokens = []
  segments_ids = []
  segment_ids = []

  tokens.append("[CLS]")
  segment_ids.append(0)
  for token in token_a:
    tokens.append(token)
    segment_ids.append(0)

  tokens.append('[SEP]')
  segment_ids.append(0)
    
  input_ids = tokenizer.convert_tokens_to_ids(tokens)
  input_mask = [1] * len(input_ids)

  while len(input_ids) < max_seq_length:
    input_ids.append(0)
    input_mask.append(0)
    segment_ids.append(0)

  label_id = [0]
  padding = [0] * max_seq_length

  print(len(input_ids),len(input_mask),len(segment_ids),len(label_id))

  return {"input_ids":[input_ids,padding], "input_mask":[input_mask,padding], "segment_ids":[segment_ids,padding], "label_ids":label_id}

Finally I made a prediction using loaded model:

MAX_SEQ_LENGTH = 128
VOCAB_FILE_PATH = 'path/to/vocab'

example_features = convert_single_string_to_input_dict(example_string, VOCAB_FILE_PATH, MAX_SEQ_LENGTH)

prediction = predict_fn(example_features)['probabilities'][0]
prediction_dict = {'POS': round(prediction[1],4), 'NEG': round(prediction[0],4)}
pprint(f"prediction: {prediction_dict}")