code/inference.py [14:26]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG)

#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    sum_embeddings = torch.sum(token_embeddings * input_mask_expanded, 1)
    sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-9)
    return sum_embeddings / sum_mask

def embed_tformer(model, tokenizer, sentences):
    encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=256, return_tensors='pt')
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



inference.py [14:26]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG)

#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    sum_embeddings = torch.sum(token_embeddings * input_mask_expanded, 1)
    sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-9)
    return sum_embeddings / sum_mask

def embed_tformer(model, tokenizer, sentences):
    encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=256, return_tensors='pt')
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -