def main(argv):
if len(argv) > 1:
raise app.UsageError("Too many command-line arguments.")
tf.logging.set_verbosity(tf.logging.INFO)
if not FLAGS.output_dir:
FLAGS.output_dir = os.path.dirname(FLAGS.generation_file)
tf.io.gfile.makedirs(FLAGS.output_dir)
# Load generations.
vocab = text_utils.Vocab.load(FLAGS.vocab_path)
captions = load_synthetic_captions(FLAGS.generation_file, vocab)
images = []
for image_id, captions in captions.items():
metadata = image_utils.ImageMetadata(image_id=image_id,
captions=captions,
objects=FLAGS.features)
images.append(metadata)
# Dump to sharded TFRecords.
io_utils.convert_to_tfrecords(dataset=images,
num_shards=FLAGS.num_shards,
basename=os.path.join(
FLAGS.output_dir, "train"),
example_fn=io_utils.caption_example)
def main(argv):
if len(argv) > 1:
raise app.UsageError("Too many command-line arguments.")
tf.logging.set_verbosity(tf.logging.INFO)
tf.io.gfile.makedirs(FLAGS.output_dir)
pattern = "%s/%s-*" % (FLAGS.sqa_path, FLAGS.split)
questions = load_synthetic_questions(pattern)
# Convert to ImageMetadata.
images = []
for image_id, data in questions.items():
metadata = image_utils.ImageMetadata(
image_id=image_id,
question_ids=data["question_ids"],
questions=data["questions"],
answers=data["answers"],
captions=data["captions"],
objects="%s/%s_features.hdf5" % (FLAGS.coco_path, FLAGS.split))
images.append(metadata)
# Dump to sharded TFRecords.
io_utils.convert_to_tfrecords(
dataset=images,
num_shards=FLAGS.num_shards,
basename=os.path.join(FLAGS.output_dir, FLAGS.split),
example_fn=io_utils.vqa_example)
def main(argv):
if len(argv) > 1:
raise app.UsageError("Too many command-line arguments.")
tf.logging.set_verbosity(tf.logging.INFO)
tf.io.gfile.makedirs(FLAGS.output_dir)
# Load data and re-split according to Karpathy paper.
splits = io_utils.load_karpathy_splits(FLAGS.splits)
vocab = text_utils.Vocab.load(FLAGS.vocab_path)
captions = collections.defaultdict(list)
for split in ["train", "val"]:
captions_file = ("%s/annotations/captions_%s2014.json" %
(FLAGS.coco_path, split))
for image_id, split_captions in load_captions(captions_file,
vocab).items():
captions[image_id].extend(split_captions)
for split, image_ids in splits.items():
# Convert to RCInputs.
inputs = []
for image_id, image_captions in captions.items():
if image_id not in image_ids:
continue
for input_ids, input_mask, segment_ids in image_captions:
inputs.append(
RCInputs(image_id, input_ids, input_mask, segment_ids))
# Dump to sharded TFRecords.
io_utils.convert_to_tfrecords(
dataset=inputs,
num_shards=getattr(FLAGS, "%s_shards" % split),
basename=os.path.join(FLAGS.output_dir, split),
example_fn=rc_example)
def main(argv):
if len(argv) > 1:
raise app.UsageError("Too many command-line arguments.")
tf.logging.set_verbosity(tf.logging.INFO)
tf.io.gfile.makedirs(FLAGS.output_dir)
# Load VIZWIZ data.
vocab = text_utils.Vocab.load(FLAGS.vocab_path)
vizwiz_data = collections.defaultdict(
lambda: collections.defaultdict(list))
for split in ["train", "val"]:
questions_file = "%s/Annotations/%s.json" % (FLAGS.vizwiz_path, split)
for image_id, entry in load_questions(questions_file, vocab).items():
for k, v in entry.items():
vizwiz_data[image_id][k].extend(v)
# Convert to ImageMetadata.
images = []
for image_id, data in vizwiz_data.items():
images.append(
image_utils.ImageMetadata(image_id=image_id,
question_ids=data["question_ids"],
questions=data["questions"],
answers=data["answers"],
objects="%s/features.hdf5" %
FLAGS.vizwiz_path))
# Load pre-computed random splits.
# (This is for backwards compatibility with previous experiments).
splits_file = "%s/capwap_splits.json" % FLAGS.vizwiz_path
with tf.io.gfile.GFile(splits_file, "r") as f:
split_ids = json.load(f)
splits = dict(
test=[im for im in images if im.image_id in split_ids["test"]],
val=[im for im in images if im.image_id in split_ids["val"]],
train=[im for im in images if im.image_id in split_ids["train"]])
# Make sure we have the right images.
assert len(splits["train"]) == len(split_ids["train"])
assert len(splits["val"]) == len(split_ids["val"])
assert len(splits["test"]) == len(split_ids["test"])
# Dump to sharded TFRecords and also RC format.
for split, split_images in splits.items():
io_utils.convert_to_tfrecords(
dataset=split_images,
num_shards=getattr(FLAGS, "%s_shards" % split),
basename=os.path.join(FLAGS.output_dir, split),
example_fn=io_utils.vqa_example)
output_file = os.path.join(FLAGS.output_dir, split + ".json")
io_utils.convert_to_rc(split_images, output_file)
def main(argv):
if len(argv) > 1:
raise app.UsageError("Too many command-line arguments.")
tf.logging.set_verbosity(tf.logging.INFO)
tf.io.gfile.makedirs(FLAGS.output_dir)
# Load and aggregate all VQA data.
vocab = text_utils.Vocab.load(FLAGS.vocab_path)
questions = collections.defaultdict(lambda: collections.defaultdict(list))
for split in ["train", "val"]:
questions_file = ("%s/v2_OpenEnded_mscoco_%s2014_questions.json" %
(FLAGS.vqa_path, split))
annotations_file = ("%s/v2_mscoco_%s2014_annotations.json" %
(FLAGS.vqa_path, split))
split_questions = load_questions(questions_file, annotations_file,
vocab)
for image_id, entry in split_questions.items():
for k, v in entry.items():
questions[image_id][k].extend(v)
# Re-split according to Karpathy splits.
splits = io_utils.load_karpathy_splits(FLAGS.splits)
for split, image_ids in splits.items():
# Convert to ImageMetadata.
images = []
for image_id, data in questions.items():
if image_id not in image_ids:
continue
images.append(
image_utils.ImageMetadata(image_id=image_id,
question_ids=data["question_ids"],
questions=data["questions"],
answers=data["answers"],
objects="%s/%s_features.hdf5" %
(FLAGS.coco_path, split)))
# Dump to sharded TFRecords.
io_utils.convert_to_tfrecords(
dataset=images,
num_shards=getattr(FLAGS, "%s_shards" % split),
basename=os.path.join(FLAGS.output_dir, split),
example_fn=io_utils.vqa_example)
# And to RC formatted file.
output_file = os.path.join(FLAGS.output_dir, split + ".json")
io_utils.convert_to_rc(images, output_file)
def main(argv):
if len(argv) > 1:
raise app.UsageError("Too many command-line arguments.")
tf.logging.set_verbosity(tf.logging.INFO)
tf.io.gfile.makedirs(FLAGS.output_dir)
# Create dataset splits.
metadata_file = "%s/image_data.json" % FLAGS.v7w_path
dataset_file = os.path.join(FLAGS.v7w_path, "dataset_v7w_telling.json")
karpathy_splits = io_utils.load_karpathy_splits(FLAGS.splits)
splits = make_splits(dataset_file, metadata_file, karpathy_splits)
# Load Visual7W questions.
vocab = text_utils.Vocab.load(FLAGS.vocab_path)
questions = load_questions(dataset_file, vocab)
for split, image_ids in splits.items():
# Convert to ImageMetadata.
images = []
for image_id, data in questions.items():
if image_id not in image_ids:
continue
images.append(
image_utils.ImageMetadata(image_id=image_id,
question_ids=data["question_ids"],
questions=data["questions"],
answers=data["answers"],
objects="%s/features.hdf5" %
FLAGS.v7w_path))
# Dump to sharded TFRecords.
io_utils.convert_to_tfrecords(
dataset=images,
num_shards=getattr(FLAGS, "%s_shards" % split),
basename=os.path.join(FLAGS.output_dir, split),
example_fn=io_utils.vqa_example)
# And to RC formatted file.
output_file = os.path.join(FLAGS.output_dir, split + ".json")
io_utils.convert_to_rc(images, output_file)
def main(argv):
if len(argv) > 1:
raise app.UsageError("Too many command-line arguments.")
tf.logging.set_verbosity(tf.logging.INFO)
tf.io.gfile.makedirs(FLAGS.output_dir)
# Load COCO train image ids to be sure not to use them.
coco_train = io_utils.load_karpathy_splits(FLAGS.splits)["train"]
vocab = text_utils.Vocab.load(FLAGS.vocab_path)
# Load pre-computed random splits.
# (This is for backwards compatibility with previous experiments).
splits_file = "%s/capwap_splits.json" % FLAGS.gqa_path
with tf.io.gfile.GFile(splits_file, "r") as f:
split_ids = json.load(f)
# Load GQA train.
filename = "%s/%s_balanced_questions.json" % (FLAGS.gqa_path, "train")
gqa_data = load_questions(filename, vocab)
images = []
for image_id, data in gqa_data.items():
images.append(
image_utils.ImageMetadata(image_id=image_id,
question_ids=data["question_ids"],
questions=data["questions"],
answers=data["answers"],
objects="%s/train_features.hdf5" %
FLAGS.gqa_path))
# Make sure we have the right images.
images = [im for im in images if im.image_id in split_ids["train"]]
assert len(images) == len(split_ids["train"])
# Dump.
io_utils.convert_to_tfrecords(dataset=images,
num_shards=FLAGS.train_shards,
basename=os.path.join(
FLAGS.output_dir, "train"),
example_fn=io_utils.vqa_example)
io_utils.convert_to_rc(images, os.path.join(FLAGS.output_dir,
"train.json"))
# Load GQA dev.
filename = "%s/%s_balanced_questions.json" % (FLAGS.gqa_path, "val")
gqa_data = load_questions(filename, vocab)
images = []
for image_id, data in gqa_data.items():
images.append(
image_utils.ImageMetadata(image_id=image_id,
question_ids=data["question_ids"],
questions=data["questions"],
answers=data["answers"],
objects="%s/val_features.hdf5" %
FLAGS.gqa_path))
images = [image for image in images if image.image_id not in coco_train]
# Resplit into dev and test.
splits = dict(
val=[im for im in images if im.image_id in split_ids["val"]],
test=[im for im in images if im.image_id in split_ids["test"]])
# Make sure we have the right images.
assert len(splits["val"]) == len(split_ids["val"])
assert len(splits["test"]) == len(split_ids["test"])
# Dump to sharded TFRecords and also RC format.
for split, split_images in splits.items():
io_utils.convert_to_tfrecords(
dataset=split_images,
num_shards=getattr(FLAGS, "%s_shards" % split),
basename=os.path.join(FLAGS.output_dir, split),
example_fn=io_utils.vqa_example)
output_file = os.path.join(FLAGS.output_dir, split + ".json")
io_utils.convert_to_rc(split_images, output_file)