Я ранее разместил этот вопрос . Я хотел получить встраивание, подобное этому видео на YouTube , время 33 минуты вперед.
1) Я не думаю, что вложение, которое я получаю с токена CLS, похоже на то, что показано в видео YouTube. Я попытался выполнить сходство semanti c и получил ужасные результаты. Может ли кто-нибудь подтвердить, похожи ли вложения, которые я получаю, на вложение, упомянутое на отметке 35.27 видео?
2) Если ответ на поставленный выше вопрос «не похож», то как я могу получить вложение, которое я получаю? ищу код, который я написал?
3) Если ответ на первый вопрос «они похожи», то почему я получаю ужасные результаты? мне нужно выполнить точную настройку, используя больше данных?
update 1
Код, который я использовал для точной настройки, приведен ниже. Отсюда страница . Несколько изменений было внесено в этот код для возврата CLS встраивания. Эти изменения были основаны на ответах на мой вопрос
train_InputExamples = train2.apply(lambda x: run_classifier.InputExample(guid=None, # Globally unique ID for bookkeeping, unused in this example
text_a = x[DATA_COLUMN],
text_b = None,
label = x[LABEL_COLUMN]), axis = 1)
"""
test_InputExamples = test2.apply(lambda x: run_classifier.InputExample(guid=None,
text_a = x[DATA_COLUMN],
text_b = None,
label = x[LABEL_COLUMN]), axis = 1)
"""
# In[17]:
# This is a path to an uncased (all lowercase) version of BERT
BERT_MODEL_HUB = "https://tfhub.dev/google/bert_uncased_L-12_H-768_A-12/1"
# In[18]:
#Create tokenizer function using local albert model hub
def create_tokenizer_from_hub_module():
"""Get the vocab file and casing info from the Hub module."""
with tf.Graph().as_default():
bert_module = hub.Module(BERT_MODEL_HUB)
tokenization_info = bert_module(signature="tokenization_info", as_dict=True)
with tf.Session() as sess:
vocab_file, do_lower_case = sess.run([tokenization_info["vocab_file"],
tokenization_info["do_lower_case"]])
return tokenization.FullTokenizer(
vocab_file=vocab_file, do_lower_case=do_lower_case, spm_model_file=vocab_file)
tokenizer = create_tokenizer_from_hub_module()
#Test tokenizer on a sample sentence
tokenizer.tokenize("This here's an example of using the ALBERT tokenizer")
# In[19]:
# We'll set sequences to be at most 128 tokens long.
MAX_SEQ_LENGTH = 512
# Convert our train and test features to InputFeatures that BERT understands.
train_features = run_classifier.convert_examples_to_features(train_InputExamples, label_list, MAX_SEQ_LENGTH, tokenizer)
"""
test_features = run_classifier.convert_examples_to_features(test_InputExamples, label_list, MAX_SEQ_LENGTH, tokenizer)
"""
# In[20]:
# `create_model` builds a model. First, it loads the BERT tf hub module again (this time to extract the computation graph).
#Next, it creates a single new layer that will be trained to adapt BERT to our task
#(i.e. classifying text). This strategy of using a mostly trained model is called [fine-tuning](http://wiki.fast.ai/index.php/Fine_tuning).
def create_model(is_predicting, input_ids, input_mask, segment_ids, labels,
num_labels):
"""Creates a classification model."""
bert_module = hub.Module(
BERT_MODEL_HUB,
trainable=True)
bert_inputs = dict(
input_ids=input_ids,
input_mask=input_mask,
segment_ids=segment_ids)
bert_outputs = bert_module(
inputs=bert_inputs,
signature="tokens",
as_dict=True)
# Use "pooled_output" for classification tasks on an entire sentence.
# Use "sequence_outputs" for token-level output.
output_layer = bert_outputs["pooled_output"]
pooled_output = output_layer#added 25March
hidden_size = output_layer.shape[-1].value
# Create our own layer to tune for politeness data.
output_weights = tf.get_variable(
"output_weights", [num_labels, hidden_size],
initializer=tf.truncated_normal_initializer(stddev=0.02))
output_bias = tf.get_variable(
"output_bias", [num_labels], initializer=tf.zeros_initializer())
with tf.variable_scope("loss"):
# Dropout helps prevent overfitting
output_layer = tf.nn.dropout(output_layer, keep_prob=0.9)
logits = tf.matmul(output_layer, output_weights, transpose_b=True)
logits = tf.nn.bias_add(logits, output_bias)
log_probs = tf.nn.log_softmax(logits, axis=-1)
probs = tf.nn.softmax(logits, axis=-1)#added 25March
# Convert labels into one-hot encoding
one_hot_labels = tf.one_hot(labels, depth=num_labels, dtype=tf.float32)
predicted_labels = tf.squeeze(tf.argmax(log_probs, axis=-1, output_type=tf.int32))
# If we're predicting, we want predicted labels and the probabiltiies.
if is_predicting:
return (predicted_labels, log_probs, probs, pooled_output)
# If we're train/eval, compute loss between predicted and actual label
per_example_loss = -tf.reduce_sum(one_hot_labels * log_probs, axis=-1)
loss = tf.reduce_mean(per_example_loss)
#return (loss, predicted_labels, log_probs)
return (loss, predicted_labels, log_probs, probs, pooled_output)#added 25March
# In[ ]:
# In[21]:
# Next we'll wrap our model function in a `model_fn_builder` function that adapts our model to work for training, evaluation, and prediction.
# In[14]:
# model_fn_builder actually creates our model function
# using the passed parameters for num_labels, learning_rate, etc.
def model_fn_builder(num_labels, learning_rate, num_train_steps,
num_warmup_steps):
"""Returns `model_fn` closure for TPUEstimator."""
def model_fn(features, labels, mode, params): # pylint: disable=unused-argument
"""The `model_fn` for TPUEstimator."""
input_ids = features["input_ids"]
input_mask = features["input_mask"]
segment_ids = features["segment_ids"]
label_ids = features["label_ids"]
is_predicting = (mode == tf.estimator.ModeKeys.PREDICT)
# TRAIN and EVAL
if not is_predicting:
"""
(loss, predicted_labels, log_probs) = create_model(
is_predicting, input_ids, input_mask, segment_ids, label_ids, num_labels)
"""
# this should be changed in both places
(loss, predicted_labels, log_probs, probs, pooled_output) = create_model(
is_predicting, input_ids, input_mask, segment_ids, label_ids, num_labels)
train_op = optimization.create_optimizer(
loss, learning_rate, num_train_steps, num_warmup_steps, use_tpu=False)
# Calculate evaluation metrics.
def metric_fn(label_ids, predicted_labels):
accuracy = tf.metrics.accuracy(label_ids, predicted_labels)
f1_score = tf.contrib.metrics.f1_score(
label_ids,
predicted_labels)
auc = tf.metrics.auc(
label_ids,
predicted_labels)
recall = tf.metrics.recall(
label_ids,
predicted_labels)
precision = tf.metrics.precision(
label_ids,
predicted_labels)
true_pos = tf.metrics.true_positives(
label_ids,
predicted_labels)
true_neg = tf.metrics.true_negatives(
label_ids,
predicted_labels)
false_pos = tf.metrics.false_positives(
label_ids,
predicted_labels)
false_neg = tf.metrics.false_negatives(
label_ids,
predicted_labels)
return {
"eval_accuracy": accuracy,
"f1_score": f1_score,
"auc": auc,
"precision": precision,
"recall": recall,
"true_positives": true_pos,
"true_negatives": true_neg,
"false_positives": false_pos,
"false_negatives": false_neg
}
eval_metrics = metric_fn(label_ids, predicted_labels)
if mode == tf.estimator.ModeKeys.TRAIN:
return tf.estimator.EstimatorSpec(mode=mode,
loss=loss,
train_op=train_op)
else:
return tf.estimator.EstimatorSpec(mode=mode,
loss=loss,
eval_metric_ops=eval_metrics)
else:
#(predicted_labels, log_probs) = create_model(is_predicting, input_ids, input_mask, segment_ids, label_ids, num_labels)
(predicted_labels, log_probs, probs, pooled_output)=create_model(is_predicting, input_ids, input_mask, segment_ids, label_ids, num_labels)
# return dictionary of all the values you wanted
predictions = {'log_probabilities': log_probs,'probabilities': probs,'labels': predicted_labels,'pooled_output': pooled_output}
"""
predictions = {
'probabilities': log_probs,
'labels': predicted_labels
}
"""
return tf.estimator.EstimatorSpec(mode, predictions=predictions)
# Return the actual model function in the closure
return model_fn
# In[22]:
# In[15]:
# Compute train and warmup steps from batch size
# These hyperparameters are copied from this colab notebook (https://colab.sandbox.google.com/github/tensorflow/tpu/blob/master/tools/colab/bert_finetuning_with_cloud_tpus.ipynb)
BATCH_SIZE = 32
LEARNING_RATE = 2e-5
NUM_TRAIN_EPOCHS = 2.0
# Warmup is a period of time where hte learning rate
# is small and gradually increases--usually helps training.
WARMUP_PROPORTION = 0.1
# Model configs
SAVE_CHECKPOINTS_STEPS = 500
SAVE_SUMMARY_STEPS = 100
# In[23]:
# In[16]:
# Compute # train and warmup steps from batch size
num_train_steps = int((len(train_features) / BATCH_SIZE) * NUM_TRAIN_EPOCHS)
num_warmup_steps = int(num_train_steps * WARMUP_PROPORTION)
#epochs = steps * batch_size * worker_gpu / training_subwords
#effecive batch size is batch_size * worker_gpu
# In[17]:
# Specify outpit directory and number of checkpoint steps to save
run_config = tf.estimator.RunConfig(
model_dir=OUTPUT_DIR,
save_summary_steps=SAVE_SUMMARY_STEPS,
save_checkpoints_steps=SAVE_CHECKPOINTS_STEPS)
# In[18]:
model_fn = model_fn_builder(
num_labels=len(label_list),
learning_rate=LEARNING_RATE,
num_train_steps=num_train_steps,
num_warmup_steps=num_warmup_steps)
estimator = tf.estimator.Estimator(
model_fn=model_fn,
config=run_config,
params={"batch_size": BATCH_SIZE})
# Next we create an input builder function that takes our training feature set (`train_features`) and produces a generator. This is a pretty standard design pattern for working with Tensorflow [Estimators](https://www.tensorflow.org/guide/estimators).
# In[24]:
# In[19]:
# Create an input function for training. drop_remainder = True for using TPUs.
train_input_fn = run_classifier.input_fn_builder(
features=train_features,
seq_length=MAX_SEQ_LENGTH,
is_training=True,
drop_remainder=False)
# ### Model Training
# In[46]:
print(f'Beginning Training!')
current_time = datetime.now()
estimator.train(input_fn=train_input_fn, max_steps=num_train_steps)
print("Training took time ", datetime.now() - current_time)
"""
# ### Model Testing
# In[47]:
test_input_fn = run_classifier.input_fn_builder(
features=test_features,
seq_length=MAX_SEQ_LENGTH,
is_training=False,
drop_remainder=False)
# In[48]:
estimator.evaluate(input_fn=test_input_fn, steps=None)
"""
# In[25]:
# ### Prediction
# In[24]:
def getPrediction(in_sentences):
labels = ["Negative", "Positive"]
input_examples = [run_classifier.InputExample(guid="", text_a = x, text_b = None, label = 0) for x in in_sentences] # here, "" is just a dummy label
input_features = run_classifier.convert_examples_to_features(input_examples, label_list, MAX_SEQ_LENGTH, tokenizer)
predict_input_fn = run_classifier.input_fn_builder(features=input_features, seq_length=MAX_SEQ_LENGTH, is_training=False, drop_remainder=False)
predictions = estimator.predict(predict_input_fn)
#return predictions
return [(sentence, prediction['log_probabilities'],prediction['probabilities'], labels[prediction['labels']],prediction['pooled_output']) for sentence, prediction in zip(in_sentences, predictions)]
# In[25]:
pred_sentences = [
"They sold me something I didn't want",
]
Код в видео, который получает CLS встраивание, как показано ниже
# Put the model in evaluation mode--the dropout layers behave differently
# during evaluation.
model.eval()
with torch.no_grad():
# Forward pass, return hidden states and predictions.
# This will return the logits rather than the loss because we have
# not provided labels.
logits, encoded_layers = model(
input_ids = input_ids,
token_type_ids = None,
attention_mask = attn_mask)
# Retrieve our sentence embedding--take the `[CLS]` embedding from the final
# layer.
layer_i = 12 # The last BERT layer before the classifier.
batch_i = 0 # Only one input in the batch.
token_i = 0 # The first token, corresponding to [CLS]
# Grab the embedding.
vec = encoded_layers[layer_i][batch_i][token_i]