У меня есть этот код для поисковой системы semanti c, созданной с использованием предварительно обученной модели bert. Я хочу преобразовать эту модель в tflite для ее развертывания в Google mlkit. Я хочу знать, как это преобразовать. Я хочу знать, возможно ли вообще преобразовать это в tflite. Это может быть потому, что он упоминается на официальном сайте tenorflow: https://www.tensorflow.org/lite/convert. Но я не знаю с чего начать
Код:
from sentence_transformers import SentenceTransformer
# Load the BERT model. Various models trained on Natural Language Inference (NLI) https://github.com/UKPLab/sentence-transformers/blob/master/docs/pretrained-models/nli-models.md and
# Semantic Textual Similarity are available https://github.com/UKPLab/sentence-transformers/blob/master/docs/pretrained-models/sts-models.md
model = SentenceTransformer('bert-base-nli-mean-tokens')
# A corpus is a list with documents split by sentences.
sentences = ['Absence of sanity',
'Lack of saneness',
'A man is eating food.',
'A man is eating a piece of bread.',
'The girl is carrying a baby.',
'A man is riding a horse.',
'A woman is playing violin.',
'Two men pushed carts through the woods.',
'A man is riding a white horse on an enclosed ground.',
'A monkey is playing drums.',
'A cheetah is running behind its prey.']
# Each sentence is encoded as a 1-D vector with 78 columns
sentence_embeddings = model.encode(sentences)
print('Sample BERT embedding vector - length', len(sentence_embeddings[0]))
print('Sample BERT embedding vector - note includes negative values', sentence_embeddings[0])
#@title Sematic Search Form
# code adapted from https://github.com/UKPLab/sentence-transformers/blob/master/examples/application_semantic_search.py
query = 'Nobody has sane thoughts' #@param {type: 'string'}
queries = [query]
query_embeddings = model.encode(queries)
# Find the closest 3 sentences of the corpus for each query sentence based on cosine similarity
number_top_matches = 3 #@param {type: "number"}
print("Semantic Search Results")
for query, query_embedding in zip(queries, query_embeddings):
distances = scipy.spatial.distance.cdist([query_embedding], sentence_embeddings, "cosine")[0]
results = zip(range(len(distances)), distances)
results = sorted(results, key=lambda x: x[1])
print("\n\n======================\n\n")
print("Query:", query)
print("\nTop 5 most similar sentences in corpus:")
for idx, distance in results[0:number_top_matches]:
print(sentences[idx].strip(), "(Cosine Score: %.4f)" % (1-distance))