def generate_data_for_problem(problem):
"""Generate data for a problem in _SUPPORTED_PROBLEM_GENERATORS."""
training_gen, dev_gen, test_gen = _SUPPORTED_PROBLEM_GENERATORS[problem]
num_train_shards = FLAGS.num_shards or 10
tf.logging.info("Generating training data for %s.", problem)
train_output_files = generator_utils.train_data_filenames(
problem + generator_utils.UNSHUFFLED_SUFFIX, FLAGS.data_dir,
num_train_shards)
generator_utils.generate_files(training_gen(), train_output_files,
FLAGS.max_cases)
num_dev_shards = int(num_train_shards * 0.1)
tf.logging.info("Generating development data for %s.", problem)
dev_output_files = generator_utils.dev_data_filenames(
problem + generator_utils.UNSHUFFLED_SUFFIX, FLAGS.data_dir,
num_dev_shards)
generator_utils.generate_files(dev_gen(), dev_output_files)
num_test_shards = int(num_train_shards * 0.1)
test_output_files = []
test_gen_data = test_gen()
if test_gen_data is not None:
tf.logging.info("Generating test data for %s.", problem)
test_output_files = generator_utils.test_data_filenames(
problem + generator_utils.UNSHUFFLED_SUFFIX, FLAGS.data_dir,
num_test_shards)
generator_utils.generate_files(test_gen_data, test_output_files)
all_output_files = train_output_files + dev_output_files + test_output_files
generator_utils.shuffle_dataset(all_output_files)
def testGenerateFiles(self):
tmp_dir = self.get_temp_dir()
(_, tmp_file_path) = tempfile.mkstemp(dir=tmp_dir)
tmp_file_name = os.path.basename(tmp_file_path)
# Generate a trivial file and assert the file exists.
def test_generator():
yield {"inputs": [1], "target": [1]}
filenames = generator_utils.train_data_filenames(tmp_file_name, tmp_dir, 1)
generator_utils.generate_files(test_generator(), filenames)
self.assertTrue(tf.gfile.Exists(tmp_file_path + "-train-00000-of-00001"))
# Clean up.
os.remove(tmp_file_path + "-train-00000-of-00001")
os.remove(tmp_file_path)
def training_filepaths(self, data_dir, num_shards, shuffled):
file_basename = self.dataset_filename()
if not shuffled:
file_basename += generator_utils.UNSHUFFLED_SUFFIX
return generator_utils.train_data_filenames(file_basename, data_dir,
num_shards)
def _testBatchExamples(self):
tf.set_random_seed(1)
tmp_dir = self.get_temp_dir()
(_, tmp_file_path) = tempfile.mkstemp(dir=tmp_dir)
tmp_file_name = os.path.basename(tmp_file_path)
# Generate a file with 100 examples, n-th example of length n + 1.
def test_generator():
for i in xrange(100):
yield {
"inputs": [i + 1 for _ in xrange(i + 1)],
"targets": [i + 1]
}
filenames = generator_utils.train_data_filenames(
tmp_file_name, tmp_dir, 1)
generator_utils.generate_files(test_generator(), filenames)
self.assertTrue(
tf.gfile.Exists(tmp_file_path + "-train-00000-of-00001"))
examples_train = data_reader.examples_reader(
[tmp_file_path + "*"], {
"inputs": tf.VarLenFeature(tf.int64),
"targets": tf.VarLenFeature(tf.int64)
}, True)
batch_train = data_reader.batch_examples(examples_train, 4)
examples_eval = data_reader.examples_reader(
[tmp_file_path + "*"], {
"inputs": tf.VarLenFeature(tf.int64),
"targets": tf.VarLenFeature(tf.int64)
}, False)
batch_eval = data_reader.batch_examples(examples_eval, 2)
session, coord = tf.Session(), tf.train.Coordinator()
with session.as_default():
tf.train.start_queue_runners(coord=coord)
# Evaluation data comes in the same order as in the file.
# The first batch will be inputs=[[1, 0], [2, 2]], targets=[[1], [2]].
examples = session.run(batch_eval)
self.assertAllClose(examples["inputs"], np.array([[1, 0], [2, 2]]))
self.assertAllClose(examples["targets"], np.array([[1], [2]]))
# Check the second batch too.
examples = session.run(batch_eval)
self.assertAllClose(examples["inputs"],
np.array([[3, 3, 3, 0], [4, 4, 4, 4]]))
self.assertAllClose(examples["targets"], np.array([[3], [4]]))
# Training data is shuffled but shouldn't have too many pads.
for _ in xrange(10):
examples = session.run(batch_train)
inputs = examples["inputs"]
# Only 3 out of 4 examples in a batch have padding zeros at all.
pad_per_example = (inputs.size - np.count_nonzero(inputs)) // 3
# Default bucketing is in steps of 8 until 64 and 32 later.
if int(max(examples["targets"])) < 64:
self.assertLess(pad_per_example, 8)
else:
self.assertLess(pad_per_example, 32)
# Clean up.
coord.request_stop()
coord.join()
os.remove(tmp_file_path + "-train-00000-of-00001")
os.remove(tmp_file_path)
def training_filepaths(self, data_dir, num_shards, shuffled):
file_basename = self.dataset_filename()
if not shuffled:
file_basename += generator_utils.UNSHUFFLED_SUFFIX
return generator_utils.train_data_filenames(file_basename, data_dir,
num_shards)
def generate_tf_records(out_path="/home/abhishek/tmp/tf-records",input_path="/home/abhishek/tmp/LJSpeech-1.1", num_shards=100):
train_paths = generator_utils.train_data_filenames("lj_speech", out_path, num_shards)
char2idx, _ = data_load.load_vocab()
generator_utils.generate_files(_generator(input_path, char2idx), train_paths)
