def test_multiprocess_read_with_qiterable(self):
reader = MultiprocessDatasetReader(base_reader=self.base_reader, num_workers=4)
all_instances = []
qiterable = reader.read(self.identical_files_glob)
assert isinstance(qiterable, QIterable)
# Essentially QIterable.__iter__. Broken out here as we intend it to be
# a public interface.
qiterable.start()
while qiterable.num_active_workers.value > 0 or qiterable.num_inflight_items.value > 0:
while True:
try:
all_instances.append(qiterable.output_queue.get(block=False, timeout=1.0))
with qiterable.num_inflight_items.get_lock():
qiterable.num_inflight_items.value -= 1
except Empty:
break
qiterable.join()
# 100 files * 4 sentences / file
assert len(all_instances) == 100 * 4
counts = Counter(fingerprint(instance) for instance in all_instances)
# should have the exact same data 100 times
assert len(counts) == 4
assert counts[("cats", "are", "animals", ".", "N", "V", "N", "N")] == 100
assert counts[("dogs", "are", "animals", ".", "N", "V", "N", "N")] == 100
assert counts[("snakes", "are", "animals", ".", "N", "V", "N", "N")] == 100
assert counts[("birds", "are", "animals", ".", "N", "V", "N", "N")] == 100
def test_multiple_epochs(self):
reader = MultiprocessDatasetReader(base_reader=self.base_reader,
num_workers=2,
epochs_per_read=3)
all_instances = []
for instance in reader.read(self.glob):
all_instances.append(instance)
# 100 files * 4 sentences per file * 3 epochs
assert len(all_instances) == 100 * 4 * 3
counts = Counter(fingerprint(instance) for instance in all_instances)
# should have the exact same data 100 * 3 times
assert len(counts) == 4
assert counts[("cats", "are", "animals", ".", "N", "V", "N",
"N")] == 300
assert counts[("dogs", "are", "animals", ".", "N", "V", "N",
"N")] == 300
assert counts[("snakes", "are", "animals", ".", "N", "V", "N",
"N")] == 300
assert counts[("birds", "are", "animals", ".", "N", "V", "N",
"N")] == 300
def test_with_iterator(self):
reader = MultiprocessDatasetReader(base_reader=self.base_reader, num_workers=2)
instances = reader.read(self.identical_files_glob)
iterator = BasicIterator(batch_size=32)
iterator.index_with(self.vocab)
batches = [batch for batch in iterator(instances, num_epochs=1)]
# 400 instances / batch_size 32 = 12 full batches + 1 batch of 16
sizes = sorted([len(batch['tags']) for batch in batches])
assert sizes == [16] + 12 * [32]
def test_with_iterator(self):
reader = MultiprocessDatasetReader(base_reader=self.base_reader, num_workers=2)
instances = reader.read(self.glob)
iterator = BasicIterator(batch_size=32)
iterator.index_with(self.vocab)
batches = [batch for batch in iterator(instances, num_epochs=1)]
# 400 instances / batch_size 32 = 12 full batches + 1 batch of 16
sizes = sorted([len(batch['tags']) for batch in batches])
assert sizes == [16] + 12 * [32]
def test_multiprocess_reader_with_multiprocess_iterator(self):
# use SequenceTaggingDatasetReader as the base reader
reader = MultiprocessDatasetReader(base_reader=self.base_reader, num_workers=2)
base_iterator = BasicIterator(batch_size=32, max_instances_in_memory=1024)
iterator = MultiprocessIterator(base_iterator, num_workers=2)
iterator.index_with(self.vocab)
instances = reader.read(self.glob)
tensor_dicts = iterator(instances, num_epochs=1)
sizes = [len(tensor_dict['tags']) for tensor_dict in tensor_dicts]
assert sum(sizes) == 400
def test_multiprocess_reader_with_multiprocess_iterator(self):
# use SequenceTaggingDatasetReader as the base reader
reader = MultiprocessDatasetReader(base_reader=self.base_reader, num_workers=2)
base_iterator = BasicIterator(batch_size=32, max_instances_in_memory=1024)
iterator = MultiprocessIterator(base_iterator, num_workers=2)
iterator.index_with(self.vocab)
instances = reader.read(self.glob)
tensor_dicts = iterator(instances, num_epochs=1)
sizes = [len(tensor_dict["tags"]) for tensor_dict in tensor_dicts]
assert sum(sizes) == 400
def test_multiprocess_read(self):
reader = MultiprocessDatasetReader(base_reader=self.base_reader, num_workers=4)
all_instances = []
for instance in reader.read(self.identical_files_glob):
all_instances.append(instance)
# 100 files * 4 sentences / file
assert len(all_instances) == 100 * 4
counts = Counter(fingerprint(instance) for instance in all_instances)
# should have the exact same data 100 times
assert len(counts) == 4
assert counts[("cats", "are", "animals", ".", "N", "V", "N", "N")] == 100
assert counts[("dogs", "are", "animals", ".", "N", "V", "N", "N")] == 100
assert counts[("snakes", "are", "animals", ".", "N", "V", "N", "N")] == 100
assert counts[("birds", "are", "animals", ".", "N", "V", "N", "N")] == 100
def test_multiprocess_read(self):
reader = MultiprocessDatasetReader(base_reader=self.base_reader, num_workers=4)
all_instances = []
for instance in reader.read(self.glob):
all_instances.append(instance)
# 100 files * 4 sentences / file
assert len(all_instances) == 100 * 4
counts = Counter(fingerprint(instance) for instance in all_instances)
# should have the exact same data 100 times
assert len(counts) == 4
assert counts[("cats", "are", "animals", ".", "N", "V", "N", "N")] == 100
assert counts[("dogs", "are", "animals", ".", "N", "V", "N", "N")] == 100
assert counts[("snakes", "are", "animals", ".", "N", "V", "N", "N")] == 100
assert counts[("birds", "are", "animals", ".", "N", "V", "N", "N")] == 100
def test_multiprocess_read_partial_does_not_hang(self):
# Use a small queue size such that the processes generating the data will block.
reader = MultiprocessDatasetReader(base_reader=self.base_reader, num_workers=4, output_queue_size=10)
all_instances = []
# Half of 100 files * 4 sentences / file
i = 0
for instance in reader.read(self.identical_files_glob):
# Stop early such that the processes generating the data remain
# active (given the small queue size).
if i == 200:
break
i += 1
all_instances.append(instance)
# This should be trivially true. The real test here is that we exit
# normally and don't hang due to the still active processes.
assert len(all_instances) == 200