def initImg2TxtWorker(listenQ, sendQ, checkpointPath, vocabularyPath):
from Demo.Img2Txt.im2txt.im2txt.inference_utils import caption_generator
from Demo.Img2Txt.im2txt.im2txt.inference_utils import vocabulary
from Demo.Img2Txt.im2txt.im2txt import inference_wrapper
from Demo.Img2Txt.im2txt.im2txt import configuration
import tensorflow as tf
print("Starting Img2Txt model...")
print("Using checkpoint:", checkpointPath)
# Build the inference graph.
g = tf.Graph()
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(configuration.ModelConfig(),
checkpointPath)
g.finalize()
vocab = vocabulary.Vocabulary(vocabularyPath) # Init the vocabulary
with tf.Session(graph=g) as sess:
restore_fn(sess) # Load the model from checkpoint.
# Prepare the caption generator. Here we are implicitly using the default
# beam search parameters. See caption_generator.py for a description of the
# available beam search parameters.
generator = caption_generator.CaptionGenerator(model, vocab)
img2TxtPredictionCycle(sess, generator, vocab, listenQ, sendQ)
def run():
"""Runs evaluation in a loop, and logs summaries to TensorBoard."""
# Create the evaluation directory if it doesn't exist.
eval_dir = FLAGS.eval_dir
if not tf.gfile.IsDirectory(eval_dir):
tf.logging.info("Creating eval directory: %s", eval_dir)
tf.gfile.MakeDirs(eval_dir)
g = tf.Graph()
with g.as_default():
# Build the model for evaluation.
model_config = configuration.ModelConfig()
model_config.input_file_pattern = FLAGS.input_file_pattern
model = show_and_tell_model.ShowAndTellModel(model_config, mode="eval")
model.build()
# Create the Saver to restore model Variables.
saver = tf.train.Saver()
# Create the summary operation and the summary writer.
summary_op = tf.summary.merge_all()
summary_writer = tf.summary.FileWriter(eval_dir)
g.finalize()
# Run a new evaluation run every eval_interval_secs.
while True:
start = time.time()
tf.logging.info(
"Starting evaluation at " +
time.strftime("%Y-%m-%d-%H:%M:%S", time.localtime()))
run_once(model, saver, summary_writer, summary_op)
time_to_next_eval = start + FLAGS.eval_interval_secs - time.time()
if time_to_next_eval > 0:
time.sleep(time_to_next_eval)
def mkPredictor():
import tensorflow as tf
from Demo.Img2Txt.im2txt.im2txt.inference_utils import caption_generator
from Demo.Img2Txt.im2txt.im2txt.inference_utils import vocabulary
from Demo.Img2Txt.im2txt.im2txt import inference_wrapper
from Demo.Img2Txt.im2txt.im2txt import configuration
# Init the vocabulary
vocab = vocabulary.Vocabulary(VOCABULARY_PATH)
# Build the graph
import tensorflow as tf
g = tf.Graph()
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(configuration.ModelConfig(),
CHECKPOINT_PATH)
g.finalize()
# Prepare a session object
sess = tf.Session(graph=g)
restore_fn(sess) # Load the model from checkpoint.
generator = caption_generator.CaptionGenerator(model, vocab)
def predict(image):
image = cv2.imencode('.jpg', image)[1].tobytes()
for caption in generator.beam_search(sess, image):
# Ignore begin and end words.
sentence = [vocab.id_to_word(w) for w in caption.sentence[1:-1]]
yield " ".join(sentence)
return predict
def main():
# Build the inference graph.
g = tf.Graph()
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(configuration.ModelConfig(),
Constants.CHECKPOINT_PATH)
g.finalize()
vocab = vocabulary.Vocabulary(Constants.VOCABULARY_PATH)
filenames = []
for file_pattern in IMAGE_FILE.split(","):
filenames.extend(tf.gfile.Glob(file_pattern))
tf.logging.info("Running caption generation on %d files matching %s",
len(filenames), IMAGE_FILE)
with tf.Session(graph=g) as sess:
# Load the model from checkpoint.
restore_fn(sess)
# Prepare the caption generator. Here we are implicitly using the default
# beam search parameters. See caption_generator.py for a description of the
# available beam search parameters.
generator = caption_generator.CaptionGenerator(model, vocab)
for filename in filenames:
f = open(filename, 'rb')
image = f.read()
captions = generator.beam_search(sess, image)
print("Captions for image %s:" % os.path.basename(filename))
for i, caption in enumerate(captions):
# Ignore begin and end words.
sentence = [
vocab.id_to_word(w) for w in caption.sentence[1:-1]
]
sentence = " ".join(sentence)
print(" %d) %s (p=%f)" %
(i, sentence, math.exp(caption.logprob)))
def setUp(self):
super(ShowAndTellModelTest, self).setUp()
self._model_config = configuration.ModelConfig()
def main(unused_argv):
assert FLAGS.input_file_pattern, "--input_file_pattern is required"
assert FLAGS.train_dir, "--train_dir is required"
model_config = configuration.ModelConfig()
model_config.input_file_pattern = FLAGS.input_file_pattern
model_config.inception_checkpoint_file = FLAGS.inception_checkpoint_file
training_config = configuration.TrainingConfig()
# Create training directory.
train_dir = FLAGS.train_dir
if not tf.gfile.IsDirectory(train_dir):
tf.logging.info("Creating training directory: %s", train_dir)
tf.gfile.MakeDirs(train_dir)
# Build the TensorFlow graph.
g = tf.Graph()
with g.as_default():
# Build the model.
model = show_and_tell_model.ShowAndTellModel(
model_config, mode="train", train_inception=FLAGS.train_inception)
model.build()
# Set up the learning rate.
learning_rate_decay_fn = None
if FLAGS.train_inception:
learning_rate = tf.constant(
training_config.train_inception_learning_rate)
else:
learning_rate = tf.constant(training_config.initial_learning_rate)
if training_config.learning_rate_decay_factor > 0:
num_batches_per_epoch = (
training_config.num_examples_per_epoch /
model_config.batch_size)
decay_steps = int(num_batches_per_epoch *
training_config.num_epochs_per_decay)
def _learning_rate_decay_fn(learning_rate, global_step):
return tf.train.exponential_decay(
learning_rate,
global_step,
decay_steps=decay_steps,
decay_rate=training_config.learning_rate_decay_factor,
staircase=True)
learning_rate_decay_fn = _learning_rate_decay_fn
# Set up the training ops.
train_op = tf.contrib.layers.optimize_loss(
loss=model.total_loss,
global_step=model.global_step,
learning_rate=learning_rate,
optimizer=training_config.optimizer,
clip_gradients=training_config.clip_gradients,
learning_rate_decay_fn=learning_rate_decay_fn)
# Set up the Saver for saving and restoring model checkpoints.
saver = tf.train.Saver(
max_to_keep=training_config.max_checkpoints_to_keep)
# Run training.
tf.contrib.slim.learning.train(train_op,
train_dir,
log_every_n_steps=FLAGS.log_every_n_steps,
graph=g,
global_step=model.global_step,
number_of_steps=FLAGS.number_of_steps,
init_fn=model.init_fn,
saver=saver)