def pretrained_model_score(self, model_name, expected_score):
model = SentenceTransformer(model_name)
sts_reader = STSDataReader('../examples/datasets/stsbenchmark')
test_data = SentencesDataset(
examples=sts_reader.get_examples("sts-test.csv"), model=model)
test_dataloader = DataLoader(test_data, shuffle=False, batch_size=8)
evaluator = EmbeddingSimilarityEvaluator(test_dataloader)
score = model.evaluate(evaluator) * 100
print(model_name,
"{:.2f} vs. exp: {:.2f}".format(score, expected_score))
assert abs(score - expected_score) < 0.1
def main():
model = SentenceTransformer('bert-base-nli-mean-tokens')
sts_reader = STSDataReader('datasets/stsbenchmark')
test_data = SentencesDataset(
examples=sts_reader.get_examples('sts-test.csv'),
model=model,
dataset_cache_id='sts-eval')
test_dataloader = DataLoader(test_data, shuffle=False, batch_size=16)
evaluator = EmbeddingSimilarityEvaluator(test_dataloader)
model.evaluate(evaluator)
def nlptrain(premodel,ver,tr_data,te_data):
#### Just some code to print debug information to stdout
logging.basicConfig(format='%(asctime)s - %(message)s',
datefmt='%Y-%m-%d %H:%M:%S',
level=logging.INFO,
handlers=[LoggingHandler()])
#### /print debug information to stdout
# Read the dataset
model_name = 'roberta-large-nli-stsb-mean-tokens'
train_batch_size = 16
num_epochs = 4
model_save_path = ver
sts_reader = STSDataReader('kt_datasets/kt_benchmark', normalize_scores=True)
# Load a pre-trained sentence transformer model
model = SentenceTransformer(premodel)
# Convert the dataset to a DataLoader ready for training
logging.info("")
train_data = SentencesDataset(sts_reader.get_examples(tr_data), model)
train_dataloader = DataLoader(train_data, shuffle=True, batch_size=train_batch_size)
train_loss = losses.CosineSimilarityLoss(model=model)
logging.info("")
dev_data = SentencesDataset(examples=sts_reader.get_examples(te_data), model=model)
dev_dataloader = DataLoader(dev_data, shuffle=False, batch_size=train_batch_size)
evaluator = EmbeddingSimilarityEvaluator(dev_dataloader)
# Configure the training. We skip evaluation in this example
warmup_steps = math.ceil(len(train_data)*num_epochs/train_batch_size*0.1) #10% of train data for warm-up
logging.info("Warmup-steps: {}".format(warmup_steps))
# Train the model
model.fit(train_objectives=[(train_dataloader, train_loss)],
evaluator=evaluator,
epochs=num_epochs,
evaluation_steps=1000,
warmup_steps=warmup_steps,
output_path=model_save_path)
list=['model saved in '+ ver+' directory']
return(list)
import logging
from datetime import datetime
#### Just some code to print debug information to stdout
logging.basicConfig(format='%(asctime)s - %(message)s',
datefmt='%Y-%m-%d %H:%M:%S',
level=logging.INFO,
handlers=[LoggingHandler()])
#### /print debug information to stdout
# Read the dataset
train_batch_size = 16
num_epochs = 4
model_save_path = 'output/training_stsbenchmark_roberta-' + datetime.now(
).strftime("%Y-%m-%d_%H-%M-%S")
sts_reader = STSDataReader('datasets/stsbenchmark', normalize_scores=True)
# Use XLNet for mapping tokens to embeddings
word_embedding_model = models.RoBERTa('roberta-base')
# Apply mean pooling to get one fixed sized sentence vector
pooling_model = models.Pooling(
word_embedding_model.get_word_embedding_dimension(),
pooling_mode_mean_tokens=True,
pooling_mode_cls_token=False,
pooling_mode_max_tokens=False)
model = SentenceTransformer(modules=[word_embedding_model, pooling_model])
# Convert the dataset to a DataLoader ready for training
logging.info("Read STSbenchmark train dataset")
logging.basicConfig(format='%(asctime)s - %(message)s',
datefmt='%Y-%m-%d %H:%M:%S',
level=logging.INFO,
handlers=[LoggingHandler()])
#### /print debug information to stdout
# Read the dataset
#model_name = 'bert-base-nli-stsb-mean-tokens'
model_name = "../saved_models"
train_batch_size = 32
num_epochs = 4
model_save_path = 'output/quora_continue_training-' + model_name + '-' + datetime.now(
).strftime("%Y-%m-%d_%H-%M-%S")
sts_reader = STSDataReader('../data/quora',
normalize_scores=True,
s1_col_idx=4,
s2_col_idx=5,
score_col_idx=6,
max_score=1)
# Load a pre-trained sentence transformer model
model = SentenceTransformer(model_name)
# Convert the dataset to a DataLoader ready for training
logging.info("Read Quora train dataset")
train_data = SentencesDataset(sts_reader.get_examples('train.csv'), model)
train_dataloader = DataLoader(train_data,
shuffle=True,
batch_size=train_batch_size)
train_loss = losses.CosineSimilarityLoss(model=model)
logging.info("Read Quora dev dataset")
from datetime import datetime
#### Just some code to print debug information to stdout
logging.basicConfig(format='%(asctime)s - %(message)s',
datefmt='%Y-%m-%d %H:%M:%S',
level=logging.INFO,
handlers=[LoggingHandler()])
#### /print debug information to stdout
# Read the dataset
model_name = 'roberta-large-nli-stsb-mean-tokens'
train_batch_size = 16
num_epochs = 4
model_save_path = 'output/train1-' + model_name + '-' + datetime.now(
).strftime("%Y-%m-%d_%H-%M-%S")
sts_reader = STSDataReader('kt_datasets/kt_benchmark', normalize_scores=True)
# Load a pre-trained sentence transformer model
model = SentenceTransformer('output/retkt')
# Convert the dataset to a DataLoader ready for training
logging.info("")
train_data = SentencesDataset(sts_reader.get_examples('kt1.csv'), model)
train_dataloader = DataLoader(train_data,
shuffle=True,
batch_size=train_batch_size)
train_loss = losses.CosineSimilarityLoss(model=model)
logging.info("")
dev_data = SentencesDataset(examples=sts_reader.get_examples('kt1.csv'),
model=model)
import os
dirname = os.path.dirname(os.path.dirname(__file__))
#### Just some code to print debug information to stdout
logging.basicConfig(format='%(asctime)s - %(message)s',
datefmt='%Y-%m-%d %H:%M:%S',
level=logging.INFO,
handlers=[LoggingHandler()])
#### /print debug information to stdout
# Read the dataset
train_batch_size = 16
num_epochs = 4
model_save_path = os.path.join(dirname, 'output/training_stsbenchmark_bert-'+datetime.now().strftime("%Y-%m-%d_%H-%M-%S"))
sts_reader = STSDataReader(os.path.join(dirname, 'data/sts-b'), normalize_scores=True)
# Use BERT for mapping tokens to embeddings
word_embedding_model = models.BERT('bert-base-uncased')
# Apply mean pooling to get one fixed sized sentence vector
pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimension(),
pooling_mode_mean_tokens=True,
pooling_mode_cls_token=False,
pooling_mode_max_tokens=False)
model = SentenceTransformer(modules=[word_embedding_model, pooling_model])
# Convert the dataset to a DataLoader ready for training
logging.info("Read STSbenchmark train dataset")
train_data = SentencesDataset(sts_reader.get_examples('sts-train.csv'), model)
from sentence_transformers import SentencesDataset, SentenceTransformer, losses
from sentence_transformers.evaluation import EmbeddingSimilarityEvaluator
from sentence_transformers.readers import STSDataReader
from torch.utils.data import DataLoader
# model = SentenceTransformer('bert-base-nli-mean-tokens')
sts_reader = STSDataReader('stsbenchmark_data', normalize_scores=True)
train_data = SentencesDataset(sts_reader.get_examples('sts-train.csv'), model)
train_dataloader = DataLoader(train_data,
shuffle=True,
batch_size=train_batch_size)
train_loss = losses.CosineSimilarityLoss(model=model)
print(train_data)
This examples loads a pre-trained model and evaluates it on the STSbenchmark dataset
"""
from torch.utils.data import DataLoader
from sentence_transformers import SentenceTransformer, SentencesDataset, LoggingHandler
from sentence_transformers.evaluation import EmbeddingSimilarityEvaluator
from sentence_transformers.readers import STSDataReader
import numpy as np
import logging
#### Just some code to print debug information to stdout
np.set_printoptions(threshold=100)
logging.basicConfig(format='%(asctime)s - %(message)s',
datefmt='%Y-%m-%d %H:%M:%S',
level=logging.INFO,
handlers=[LoggingHandler()])
#### /print debug information to stdout
# Load a named sentence model (based on BERT). This will download the model from our server.
# Alternatively, you can also pass a filepath to SentenceTransformer()
model = SentenceTransformer('bert-base-nli-mean-tokens')
sts_reader = STSDataReader('datasets/stsbenchmark')
test_data = SentencesDataset(examples=sts_reader.get_examples("sts-test.csv"),
model=model)
test_dataloader = DataLoader(test_data, shuffle=False, batch_size=8)
evaluator = EmbeddingSimilarityEvaluator(test_dataloader)
model.evaluate(evaluator)