Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

remove hard coding of network dimensions based on specific label_count #25

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
+12 −7
Open

remove hard coding of network dimensions based on specific label_count #25

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
362bbef
remove hard coding of network dimentions based on specific label_count
Jan 3, 2019
9567a7a
ignore extra folders
Jan 5, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
checkpoint/
bert/
venv/
16 changes: 9 additions & 7 deletions BERT_NER.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -369,7 +369,7 @@ def create_model(bert_config, is_training, input_ids, input_mask,
output_layer = tf.reshape(output_layer, [-1, hidden_size])
logits = tf.matmul(output_layer, output_weight, transpose_b=True)
logits = tf.nn.bias_add(logits, output_bias)
logits = tf.reshape(logits, [-1, FLAGS.max_seq_length, 13])
logits = tf.reshape(logits, [-1, FLAGS.max_seq_length, num_labels])
# mask = tf.cast(input_mask,tf.float32)
# loss = tf.contrib.seq2seq.sequence_loss(logits,labels,mask)
# return (loss, logits, predict)
Expand All @@ -382,7 +382,7 @@ def create_model(bert_config, is_training, input_ids, input_mask,
predict = tf.argmax(probabilities,axis=-1)
return (loss, per_example_loss, logits,predict)
##########################################################################

def model_fn_builder(bert_config, num_labels, init_checkpoint, learning_rate,
num_train_steps, num_warmup_steps, use_tpu,
use_one_hot_embeddings):
Expand Down Expand Up @@ -430,13 +430,14 @@ def tpu_scaffold():
train_op=train_op,
scaffold_fn=scaffold_fn)
elif mode == tf.estimator.ModeKeys.EVAL:

def metric_fn(per_example_loss, label_ids, logits):
# def metric_fn(label_ids, logits):
predictions = tf.argmax(logits, axis=-1, output_type=tf.int32)
precision = tf_metrics.precision(label_ids,predictions,13,[1,2,4,5,6,7,8,9],average="macro")
recall = tf_metrics.recall(label_ids,predictions,13,[1,2,4,5,6,7,8,9],average="macro")
f = tf_metrics.f1(label_ids,predictions,13,[1,2,4,5,6,7,8,9],average="macro")
pos_indices = list(range(1,(num_labels-3)))
precision = tf_metrics.precision(label_ids,predictions,num_labels, pos_indices, average="macro")
recall = tf_metrics.recall(label_ids,predictions,num_labels, pos_indices, average="macro")
f = tf_metrics.f1(label_ids,predictions,num_labels, pos_indices, average="macro")
#
return {
"eval_precision":precision,
Expand Down Expand Up @@ -581,7 +582,7 @@ def main(_):
filed_based_convert_examples_to_features(predict_examples, label_list,
FLAGS.max_seq_length, tokenizer,
predict_file,mode="test")

tf.logging.info("***** Running prediction*****")
tf.logging.info(" Num examples = %d", len(predict_examples))
tf.logging.info(" Batch size = %d", FLAGS.predict_batch_size)
Expand All @@ -603,6 +604,7 @@ def main(_):
output_line = "\n".join(id2label[id] for id in prediction if id!=0) + "\n"
writer.write(output_line)


if __name__ == "__main__":
flags.mark_flag_as_required("data_dir")
flags.mark_flag_as_required("task_name")
Expand Down