def Eval(sess):
logging.info('***************%s', FLAGS.arg_prefix)
"""Builds and evaluates a network."""
task_context = FLAGS.task_context
task_context = RewriteContext(task_context)
logging.info(task_context)
feature_sizes, domain_sizes, embedding_dims, num_actions = sess.run(
gen_parser_ops.feature_size(task_context=task_context[0],
arg_prefix=FLAGS.arg_prefix))
t = time.time()
hidden_layer_sizes = map(int, FLAGS.hidden_layer_sizes.split(','))
logging.info('Building training network with parameters: feature_sizes: %s '
'domain_sizes: %s', feature_sizes, domain_sizes)
if FLAGS.graph_builder == 'greedy':
parser = graph_builder.GreedyParser(num_actions,
feature_sizes,
domain_sizes,
embedding_dims,
hidden_layer_sizes,
gate_gradients=True,
arg_prefix=FLAGS.arg_prefix)
else:
parser = structured_graph_builder.StructuredGraphBuilder(
num_actions,
feature_sizes,
domain_sizes,
embedding_dims,
hidden_layer_sizes,
gate_gradients=True,
arg_prefix=FLAGS.arg_prefix,
beam_size=FLAGS.beam_size,
max_steps=FLAGS.max_steps)
for c in task_context:
parser.AddEvaluation(c,
FLAGS.batch_size,
corpus_name=FLAGS.input,
evaluation_max_steps=FLAGS.max_steps)
parser.AddSaver(FLAGS.slim_model)
sess.run(parser.inits.values())
parser.saver.restore(sess, FLAGS.model_path)
sink_documents = tf.placeholder(tf.string)
sink = gen_parser_ops.document_sink(sink_documents,
task_context=c,
corpus_name=FLAGS.output)
run_parser(sess, parser, sink, sink_documents)
def Eval(sess, parser, task_context):
parser.AddEvaluation(task_context,
FLAGS.batch_size,
corpus_name=FLAGS.input,
evaluation_max_steps=FLAGS.max_steps)
parser.AddSaver(FLAGS.slim_model)
sess.run(parser.inits.values())
parser.saver.restore(sess, FLAGS.model_path)
sink_documents = tf.placeholder(tf.string)
sink = gen_parser_ops.document_sink(sink_documents,
task_context=task_context,
corpus_name=FLAGS.output)
t = time.time()
num_epochs = None
num_tokens = 0
num_correct = 0
num_documents = 0
while True:
tf_eval_epochs, tf_eval_metrics, tf_documents = sess.run([
parser.evaluation['epochs'],
parser.evaluation['eval_metrics'],
parser.evaluation['documents'],
])
if len(tf_documents):
logging.info('Processed %d documents', len(tf_documents))
num_documents += len(tf_documents)
sess.run(sink, feed_dict={sink_documents: tf_documents})
num_tokens += tf_eval_metrics[0]
num_correct += tf_eval_metrics[1]
if num_epochs is None:
num_epochs = tf_eval_epochs
elif num_epochs < tf_eval_epochs:
break
logging.info('Total processed documents: %d', num_documents)
if num_tokens > 0:
eval_metric = 100.0 * num_correct / num_tokens
logging.info('num correct tokens: %d', num_correct)
logging.info('total tokens: %d', num_tokens)
logging.info(
'Seconds elapsed in evaluation: %.2f, '
'eval metric: %.2f%%',
time.time() - t, eval_metric)
return num_documents
def Eval(sess, parser, task_context):
parser.AddEvaluation(task_context,
FLAGS.batch_size,
corpus_name=FLAGS.input,
evaluation_max_steps=FLAGS.max_steps)
parser.AddSaver(FLAGS.slim_model)
sess.run(parser.inits.values())
parser.saver.restore(sess, FLAGS.model_path)
sink_documents = tf.placeholder(tf.string)
sink = gen_parser_ops.document_sink(sink_documents,
task_context=FLAGS.task_context,
corpus_name=FLAGS.output)
t = time.time()
num_epochs = None
num_tokens = 0
num_correct = 0
num_documents = 0
while True:
tf_eval_epochs, tf_eval_metrics, tf_documents = sess.run([
parser.evaluation['epochs'],
parser.evaluation['eval_metrics'],
parser.evaluation['documents'],
])
if len(tf_documents):
logging.info('Processed %d documents', len(tf_documents))
num_documents += len(tf_documents)
sess.run(sink, feed_dict={sink_documents: tf_documents})
num_tokens += tf_eval_metrics[0]
num_correct += tf_eval_metrics[1]
if num_epochs is None:
num_epochs = tf_eval_epochs
elif num_epochs < tf_eval_epochs:
break
logging.info('Total processed documents: %d', num_documents)
if num_tokens > 0:
eval_metric = 100.0 * num_correct / num_tokens
logging.info('num correct tokens: %d', num_correct)
logging.info('total tokens: %d', num_tokens)
logging.info('Seconds elapsed in evaluation: %.2f, '
'eval metric: %.2f%%', time.time() - t, eval_metric)
return num_documents
def _parse_impl(self):
with tf.variable_scope(self._pg.variable_scope):
tf_eval_epochs, tf_eval_metrics, tf_documents = self._sess.run([
self._parser.evaluation['epochs'],
self._parser.evaluation['eval_metrics'],
self._parser.evaluation['documents'],
])
sink_documents = tf.placeholder(tf.string)
sink = gen_parser_ops.document_sink(sink_documents,
task_context=self.task_context,
corpus_name='stdout-conll')
self._sess.run(sink, feed_dict={sink_documents: tf_documents})
sys.stdout.write('\n')
sys.stdout.flush()
def _eval(self):
with tf.variable_scope(self._variable_scope):
sink_documents = tf.placeholder(tf.string)
sink = gen_parser_ops.document_sink(
sink_documents,
task_context=self._task_context,
corpus_name=self._output)
t = time.time()
num_epochs = None
num_tokens = 0
num_correct = 0
num_documents = 0
while True:
tf_eval_epochs, tf_eval_metrics, tf_documents = self._sess.run(
[
self._parser.evaluation['epochs'],
self._parser.evaluation['eval_metrics'],
self._parser.evaluation['documents'],
])
if len(tf_documents):
logging.info('Processed %d documents', len(tf_documents))
num_documents += len(tf_documents)
self._sess.run(sink,
feed_dict={sink_documents: tf_documents})
num_tokens += tf_eval_metrics[0]
num_correct += tf_eval_metrics[1]
if num_epochs is None:
num_epochs = tf_eval_epochs
elif num_epochs < tf_eval_epochs:
break
logging.info('Total processed documents: %d', num_documents)
if num_tokens > 0:
eval_metric = 100.0 * num_correct / num_tokens
logging.info('num correct tokens: %d', num_correct)
logging.info('total tokens: %d', num_tokens)
logging.info(
'Seconds elapsed in evaluation: %.2f, '
'eval metric: %.2f%%',
time.time() - t, eval_metric)
def main(unused_argv):
logging.set_verbosity(logging.INFO)
if not gfile.IsDirectory(OutputPath('')):
gfile.MakeDirs(OutputPath(''))
# Rewrite context.
RewriteContext()
# Creates necessary term maps.
if FLAGS.compute_lexicon:
logging.info('Computing lexicon...')
with tf.Session(FLAGS.tf_master) as sess:
gen_parser_ops.lexicon_builder(task_context=OutputPath('context'),
corpus_name=FLAGS.training_corpus).run()
with tf.Session(FLAGS.tf_master) as sess:
feature_sizes, domain_sizes, embedding_dims, num_actions = sess.run(
gen_parser_ops.feature_size(task_context=OutputPath('context'),
arg_prefix=FLAGS.arg_prefix))
# Well formed and projectivize.
if FLAGS.projectivize_training_set:
logging.info('Preprocessing...')
with tf.Session(FLAGS.tf_master) as sess:
source, last = gen_parser_ops.document_source(
task_context=OutputPath('context'),
batch_size=FLAGS.batch_size,
corpus_name=FLAGS.training_corpus)
sink = gen_parser_ops.document_sink(
task_context=OutputPath('context'),
corpus_name='projectivized-training-corpus',
documents=gen_parser_ops.projectivize_filter(
gen_parser_ops.well_formed_filter(source,
task_context=OutputPath(
'context')),
task_context=OutputPath('context')))
while True:
tf_last, _ = sess.run([last, sink])
if tf_last:
break
logging.info('Training...')
with tf.Session(FLAGS.tf_master) as sess:
Train(sess, num_actions, feature_sizes, domain_sizes, embedding_dims)
def main(unused_argv):
logging.set_verbosity(logging.INFO)
if not gfile.IsDirectory(OutputPath('')):
gfile.MakeDirs(OutputPath(''))
# Rewrite context.
RewriteContext()
# Creates necessary term maps.
if FLAGS.compute_lexicon:
logging.info('Computing lexicon...')
with tf.Session(FLAGS.tf_master) as sess:
gen_parser_ops.lexicon_builder(
task_context=OutputPath('context'),
corpus_name=FLAGS.training_corpus).run()
with tf.Session(FLAGS.tf_master) as sess:
feature_sizes, domain_sizes, embedding_dims, num_actions = sess.run(
gen_parser_ops.feature_size(task_context=OutputPath('context'),
arg_prefix=FLAGS.arg_prefix))
# Well formed and projectivize.
if FLAGS.projectivize_training_set:
logging.info('Preprocessing...')
with tf.Session(FLAGS.tf_master) as sess:
source, last = gen_parser_ops.document_source(
task_context=OutputPath('context'),
batch_size=FLAGS.batch_size,
corpus_name=FLAGS.training_corpus)
sink = gen_parser_ops.document_sink(
task_context=OutputPath('context'),
corpus_name='projectivized-training-corpus',
documents=gen_parser_ops.projectivize_filter(
gen_parser_ops.well_formed_filter(
source, task_context=OutputPath('context')),
task_context=OutputPath('context')))
while True:
tf_last, _ = sess.run([last, sink])
if tf_last:
break
logging.info('Training...')
with tf.Session(FLAGS.tf_master) as sess:
Train(sess, num_actions, feature_sizes, domain_sizes, embedding_dims)
gate_gradients=True,
arg_prefix=tagger_arg_prefix,
beam_size=beam_size,
max_steps=max_steps)
tagger.AddEvaluation(task_context,
batch_size,
corpus_name=input_style,
evaluation_max_steps=max_steps)
tagger.AddSaver(slim_model)
sess.run(tagger.inits.values())
tagger.saver.restore(sess, tagger_model_path)
sink_documents = tf.placeholder(tf.string)
sink = gen_parser_ops.document_sink(sink_documents,
task_context=task_context,
corpus_name='stdout-conll')
def stdin_handler(signum, frame):
tf_eval_epochs, tf_eval_metrics, tf_documents = sess.run([
tagger.evaluation['epochs'],
tagger.evaluation['eval_metrics'],
tagger.evaluation['documents'],
])
sys.stdout.write('\n## result start\n')
sys.stdout.flush()
if len(tf_documents):
sess.run(sink, feed_dict={sink_documents: tf_documents})
def Eval(sess):
"""Builds and evaluates a network."""
task_context = FLAGS.task_context
if FLAGS.resource_dir:
task_context = RewriteContext(task_context)
feature_sizes, domain_sizes, embedding_dims, num_actions = sess.run(
gen_parser_ops.feature_size(task_context=task_context,
arg_prefix=FLAGS.arg_prefix))
t = time.time()
hidden_layer_sizes = map(int, FLAGS.hidden_layer_sizes.split(','))
LOGGING.info(
'Building training network with parameters: feature_sizes: %s '
'domain_sizes: %s', feature_sizes, domain_sizes)
if FLAGS.graph_builder == 'greedy':
parser = graph_builder.GreedyParser(num_actions,
feature_sizes,
domain_sizes,
embedding_dims,
hidden_layer_sizes,
gate_gradients=True,
arg_prefix=FLAGS.arg_prefix)
else:
parser = structured_graph_builder.StructuredGraphBuilder(
num_actions,
feature_sizes,
domain_sizes,
embedding_dims,
hidden_layer_sizes,
gate_gradients=True,
arg_prefix=FLAGS.arg_prefix,
beam_size=FLAGS.beam_size,
max_steps=FLAGS.max_steps)
parser.AddEvaluation(task_context,
FLAGS.batch_size,
corpus_name=FLAGS.input,
evaluation_max_steps=FLAGS.max_steps)
parser.AddSaver(FLAGS.slim_model)
sess.run(parser.inits.values())
parser.saver.restore(sess, FLAGS.model_path)
sink_documents = tf.placeholder(tf.string)
sink = gen_parser_ops.document_sink(sink_documents,
task_context=task_context,
corpus_name=FLAGS.output)
t = time.time()
num_epochs = None
num_tokens = 0
num_correct = 0
num_documents = 0
while True:
tf_eval_epochs, tf_eval_metrics, tf_documents = sess.run([
parser.evaluation['epochs'],
parser.evaluation['eval_metrics'],
parser.evaluation['documents'],
])
if len(tf_documents):
LOGGING.info('Processed %d documents', len(tf_documents))
num_documents += len(tf_documents)
sess.run(sink, feed_dict={sink_documents: tf_documents})
num_tokens += tf_eval_metrics[0]
num_correct += tf_eval_metrics[1]
if num_epochs is None:
num_epochs = tf_eval_epochs
elif num_epochs < tf_eval_epochs:
break
LOGGING.info('Total processed documents: %d', num_documents)
if num_tokens > 0:
eval_metric = 100.0 * num_correct / num_tokens
LOGGING.info('num correct tokens: %d', num_correct)
LOGGING.info('total tokens: %d', num_tokens)
LOGGING.info(
'Seconds elapsed in evaluation: %.2f, '
'eval metric: %.2f%%',
time.time() - t, eval_metric)
def main(unused_argv):
logging.set_verbosity(logging.INFO)
model_dir = FLAGS.model_dir
task_context = "%s/context.pbtxt" % model_dir
common_params = {
"task_context": task_context,
"beam_size": 8,
"max_steps": 1000,
"graph_builder": "structured",
"batch_size": 1024,
"slim_model": True,
}
model = {
"brain_parser": {
"arg_prefix": "brain_parser",
"hidden_layer_sizes": "512,512",
# input is taken from input tensor, not from corpus
"input": None,
"model_path": "%s/parser-params" % model_dir,
},
}
for prefix in ["brain_parser"]:
model[prefix].update(common_params)
feature_sizes, domain_sizes, embedding_dims, num_actions = GetFeatureSize(
task_context, prefix)
model[prefix].update({
'feature_sizes': feature_sizes,
'domain_sizes': domain_sizes,
'embedding_dims': embedding_dims,
'num_actions': num_actions
})
with tf.Session() as sess:
if FLAGS.export_path is not None:
text_input = tf.placeholder(tf.string, [None])
else:
text_input = tf.constant(["parsey is the greatest"], tf.string)
# corpus_name must be specified and valid because it indirectly informs
# the document format ("english-text" vs "conll-sentence") used to parse
# the input text
document_source = gen_parser_ops.document_source(
text=text_input,
task_context=task_context,
corpus_name="stdin-conll",
batch_size=common_params['batch_size'],
documents_from_input=True)
for prefix in ["brain_parser"]:
with tf.variable_scope(prefix):
if True or prefix == "brain_tagger":
#source = document_source.documents if prefix == "brain_tagger" else model["brain_tagger"]["documents"]
source = document_source.documents
model[prefix]["documents"] = Build(sess, source,
model[prefix])
if FLAGS.export_path is None:
sink = gen_parser_ops.document_sink(
model["brain_parser"]["documents"],
task_context=task_context,
corpus_name="stdout-conll")
sess.run(sink)
else:
assets = []
for model_file in os.listdir(model_dir):
path = os.path.join(model_dir, model_file)
if not os.path.isdir(path):
assets.append(tf.constant(path))
ExportModel(sess, FLAGS.export_path, text_input,
model["brain_parser"]["documents"], assets)
def Eval(sess, num_actions, feature_sizes, domain_sizes, embedding_dims):
"""Builds and evaluates a network.
Args:
sess: tensorflow session to use
num_actions: number of possible golden actions
feature_sizes: size of each feature vector
domain_sizes: number of possible feature ids in each feature vector
embedding_dims: embedding dimension for each feature group
"""
t = time.time()
hidden_layer_sizes = map(int, FLAGS.hidden_layer_sizes.split(','))
logging.info('Building training network with parameters: feature_sizes: %s '
'domain_sizes: %s', feature_sizes, domain_sizes)
if FLAGS.graph_builder == 'greedy':
parser = graph_builder.GreedyParser(num_actions,
feature_sizes,
domain_sizes,
embedding_dims,
hidden_layer_sizes,
gate_gradients=True,
arg_prefix=FLAGS.arg_prefix)
else:
parser = structured_graph_builder.StructuredGraphBuilder(
num_actions,
feature_sizes,
domain_sizes,
embedding_dims,
hidden_layer_sizes,
gate_gradients=True,
arg_prefix=FLAGS.arg_prefix,
beam_size=FLAGS.beam_size,
max_steps=FLAGS.max_steps)
task_context = FLAGS.task_context
parser.AddEvaluation(task_context,
FLAGS.batch_size,
corpus_name=FLAGS.input,
evaluation_max_steps=FLAGS.max_steps)
parser.AddSaver(FLAGS.slim_model)
sess.run(parser.inits.values())
parser.saver.restore(sess, FLAGS.model_path)
sink_documents = tf.placeholder(tf.string)
sink = gen_parser_ops.document_sink(sink_documents,
task_context=FLAGS.task_context,
corpus_name=FLAGS.output)
t = time.time()
num_epochs = None
num_tokens = 0
num_correct = 0
num_documents = 0
while True:
tf_eval_epochs, tf_eval_metrics, tf_documents = sess.run([
parser.evaluation['epochs'],
parser.evaluation['eval_metrics'],
parser.evaluation['documents'],
])
if len(tf_documents):
logging.info('Processed %d documents', len(tf_documents))
num_documents += len(tf_documents)
sess.run(sink, feed_dict={sink_documents: tf_documents})
num_tokens += tf_eval_metrics[0]
num_correct += tf_eval_metrics[1]
if num_epochs is None:
num_epochs = tf_eval_epochs
elif num_epochs < tf_eval_epochs:
break
logging.info('Total processed documents: %d', num_documents)
if num_tokens > 0:
eval_metric = 100.0 * num_correct / num_tokens
logging.info('num correct tokens: %d', num_correct)
logging.info('total tokens: %d', num_tokens)
logging.info('Seconds elapsed in evaluation: %.2f, '
'eval metric: %.2f%%', time.time() - t, eval_metric)
def _perform_action(action=None):
arg_prefix = action
task_context = task_context_path
if action == "brain_tagger":
hidden_layer_sizes = [64]
model_path = tagger_params_path
output = 'output-to-file'
input = 'input-from-file'
elif action == "brain_parser":
hidden_layer_sizes = [512, 512]
model_path = parser_params_path
output = 'output-to-file-conll'
input = 'input-from-file-conll'
else:
raise Exception("Do not recognize action %s" % action)
with tf.Session() as sess:
feature_sizes, domain_sizes, embedding_dims, num_actions = sess.run(
gen_parser_ops.feature_size(task_context=task_context,
arg_prefix=arg_prefix))
beam_size = 8
max_steps = 1000
batch_size = 1024
slim_model = True
parser = structured_graph_builder.StructuredGraphBuilder(
num_actions,
feature_sizes,
domain_sizes,
embedding_dims,
hidden_layer_sizes,
gate_gradients=True,
arg_prefix=arg_prefix,
beam_size=beam_size,
max_steps=max_steps)
parser.AddEvaluation(task_context,
batch_size,
corpus_name=input,
evaluation_max_steps=max_steps)
with tf.Session() as sess:
parser.AddSaver(slim_model)
sess.run(parser.inits.values())
parser.saver.restore(sess, model_path)
sink_documents = tf.placeholder(tf.string)
sink = gen_parser_ops.document_sink(sink_documents,
task_context=task_context,
corpus_name=output)
t = time.time()
num_epochs = None
num_tokens = 0
num_correct = 0
num_documents = 0
while True:
tf_eval_epochs, tf_eval_metrics, tf_documents = sess.run([
parser.evaluation['epochs'],
parser.evaluation['eval_metrics'],
parser.evaluation['documents'],
])
if len(tf_documents):
logging.info('Processed %d documents', len(tf_documents))
num_documents += len(tf_documents)
sess.run(sink, feed_dict={sink_documents: tf_documents})
num_tokens += tf_eval_metrics[0]
num_correct += tf_eval_metrics[1]
if num_epochs is None:
num_epochs = tf_eval_epochs
elif num_epochs < tf_eval_epochs:
break
logging.info('Total processed documents: %d', num_documents)
if num_tokens > 0:
eval_metric = 100.0 * num_correct / num_tokens
logging.info('num correct tokens: %d', num_correct)
logging.info('total tokens: %d', num_tokens)
logging.info(
'Seconds elapsed in evaluation: %.2f, '
'eval metric: %.2f%%',
time.time() - t, eval_metric)
feature_sizes, domain_sizes, embedding_dims, num_actions = sess.run(
gen_parser_ops.feature_size(task_context=task_context, arg_prefix=tokenizer_arg_prefix))
hidden_layer_sizes = map(int, tokenizer_hidden_layer_sizes.split(','))
tokenizer = structured_graph_builder.StructuredGraphBuilder(
num_actions, feature_sizes, domain_sizes, embedding_dims,
hidden_layer_sizes, gate_gradients=True, arg_prefix=tokenizer_arg_prefix,
beam_size=beam_size, max_steps=max_steps)
tokenizer.AddEvaluation(task_context, batch_size, corpus_name='stdin-untoken',
evaluation_max_steps=max_steps)
tokenizer.AddSaver(slim_model)
sess.run(tokenizer.inits.values())
tokenizer.saver.restore(sess, tokenizer_model_path)
sink_documents = tf.placeholder(tf.string)
sink = gen_parser_ops.document_sink(sink_documents, task_context=task_context,
corpus_name='stdin-untoken')
def stdin_handler(signum, frame):
tf_eval_epochs, tf_eval_metrics, tf_documents = sess.run([
tokenizer.evaluation['epochs'],
tokenizer.evaluation['eval_metrics'],
tokenizer.evaluation['documents'],
])
sys.stdout.write('\n## result start\n')
sys.stdout.flush()
if len(tf_documents):
sess.run(sink, feed_dict={sink_documents: tf_documents})