def iterate_seqs(self,
chunk_size=None,
chunk_step=None,
used_data_keys=None):
"""
Takes chunking into consideration.
:param int chunk_size:
:param int chunk_step:
:param set(str)|None used_data_keys:
:return: generator which yields tuples (seq index, seq start, seq end)
:rtype: list[(int,NumbersDict,NumbersDict)]
"""
if chunk_size is None:
chunk_size = self.chunk_size
if chunk_step is None:
chunk_step = self.chunk_step
s = 0
while self.is_less_than_num_seqs(s):
length = self.get_seq_length(s)
if chunk_size == 0:
yield (s, length.constant_like(0), length)
else:
if used_data_keys is not None:
length = NumbersDict(
{k: length[k]
for k in used_data_keys})
t = length.constant_like(0)
default_key = "data"
# There are usually the 'data' (input) and 'classes' (targets) data-keys in `length` but there can be others.
# We expect them all of the same length so that we can do chunking.
# In case that some length is 0 or 1,
# we treat it special and always return the full seq repeated for every chunk.
keys_with_full_seqs = []
for key in length.keys():
if length[key] == length[default_key]:
continue # ok
if length[key] <= 1:
keys_with_full_seqs.append(key)
continue
raise Exception(
"Chunking with multiple data-keys of different length: %r"
% length)
while length[default_key] > t[default_key]:
chunk_start = NumbersDict(t)
chunk_end = NumbersDict.min([t + chunk_size, length])
for key in keys_with_full_seqs:
chunk_start[key] = 0
chunk_end[key] = length[key]
if length.value is None:
chunk_start.value = None
chunk_end.value = None
yield (s, chunk_start, chunk_end)
t += chunk_step
if length[default_key] - t[
default_key] <= self.min_chunk_size:
break
s += 1
def iterate_seqs(self,
chunk_size=None,
chunk_step=None,
used_data_keys=None):
"""
Takes chunking into consideration.
:param int|NumbersDict chunk_size:
:param int|NumbersDict chunk_step:
:param set(str)|None used_data_keys:
:return: generator which yields tuples (seq index, seq start, seq end)
:rtype: list[(int,NumbersDict,NumbersDict)]
"""
if chunk_size is None:
chunk_size = self.chunk_size
if chunk_step is None:
chunk_step = self.chunk_step
chunk_size = NumbersDict(chunk_size)
chunk_step = NumbersDict(chunk_step)
s = 0
while self.is_less_than_num_seqs(s):
length = self.get_seq_length(s)
if chunk_size == 0:
yield (s, NumbersDict.constant_like(0, numbers_dict=length),
length)
else:
default_key = "data"
if used_data_keys is not None:
length = NumbersDict(
{k: length[k]
for k in used_data_keys})
if default_key not in used_data_keys:
default_key = sorted(used_data_keys)[0]
if chunk_step[
default_key] == 0: # allow some keys with zero chunk-step
assert chunk_step.max_value() > 0
default_key = [
key for key in sorted(used_data_keys)
if chunk_step[key] > 0
][0]
assert chunk_step[default_key] > 0
t = NumbersDict.constant_like(0, numbers_dict=length)
# There are usually the 'data' (input) and 'classes' (targets) data-keys in `length` but there can be others.
# We expect them all of the same length so that we can do chunking.
# In case that some length is 0 or 1,
# we treat it special and always return the full seq repeated for every chunk.
keys_with_full_seqs = []
for key in length.keys():
if chunk_step[key] == chunk_step[default_key]:
if length[key] == length[default_key]:
continue # ok
if length[key] <= 1: # special case as explained above
keys_with_full_seqs.append(key)
continue
if chunk_step[key] == chunk_step[default_key]:
raise Exception(
"Chunking with multiple data-keys of different length: %r"
% length)
else:
nr_of_full_chunks_key = (length[key] - chunk_size[key]
) // chunk_step[key] + 1
nr_of_full_chunks_default_key = (
length[default_key] - chunk_size[default_key]
) // chunk_step[default_key] + 1
assert nr_of_full_chunks_key == nr_of_full_chunks_default_key
while length[default_key] > t[default_key]:
chunk_start = NumbersDict(t)
chunk_end = NumbersDict.min([t + chunk_size, length])
for key in keys_with_full_seqs:
chunk_start[key] = 0
chunk_end[key] = length[key]
if length.value is None:
chunk_start.value = None
chunk_end.value = None
yield (s, chunk_start, chunk_end)
t += chunk_step
if length[default_key] - t[
default_key] <= self.min_chunk_size:
break
s += 1
def iterate_seqs(self, chunk_size=None, chunk_step=None, used_data_keys=None):
"""
Takes chunking into consideration.
:param int|NumbersDict chunk_size:
:param int|NumbersDict chunk_step:
:param set(str)|None used_data_keys:
:return: generator which yields tuples (seq index, seq start, seq end)
:rtype: list[(int,NumbersDict,NumbersDict)]
"""
if chunk_size is None:
chunk_size = self.chunk_size
if chunk_step is None:
chunk_step = self.chunk_step
chunk_size = NumbersDict(chunk_size)
chunk_step = NumbersDict(chunk_step)
s = 0
while self.is_less_than_num_seqs(s):
length = self.get_seq_length(s)
if chunk_size == 0:
yield (s, NumbersDict.constant_like(0, numbers_dict=length), length)
else:
default_key = "data"
if used_data_keys is not None:
length = NumbersDict({k: length[k] for k in used_data_keys})
if default_key not in used_data_keys:
default_key = sorted(used_data_keys)[0]
if chunk_step[default_key] == 0: # allow some keys with zero chunk-step
assert chunk_step.max_value() > 0
default_key = [key for key in sorted(used_data_keys) if chunk_step[key] > 0][0]
assert chunk_step[default_key] > 0
t = NumbersDict.constant_like(0, numbers_dict=length)
# There are usually the 'data' (input) and 'classes' (targets) data-keys in `length` but there can be others.
# We expect them all of the same length so that we can do chunking.
# In case that some length is 0 or 1,
# we treat it special and always return the full seq repeated for every chunk.
keys_with_full_seqs = []
for key in length.keys():
if chunk_step[key] == chunk_step[default_key]:
if length[key] == length[default_key]:
continue # ok
if length[key] <= 1: # special case as explained above
keys_with_full_seqs.append(key)
continue
if chunk_step[key] == chunk_step[default_key]:
raise Exception("Chunking with multiple data-keys of different length: %r" % length)
else:
nr_of_full_chunks_key = (length[key] - chunk_size[key]) // chunk_step[key] + 1
nr_of_full_chunks_default_key = (
(length[default_key] - chunk_size[default_key]) // chunk_step[default_key] + 1)
assert nr_of_full_chunks_key == nr_of_full_chunks_default_key
while length[default_key] > t[default_key]:
chunk_start = NumbersDict(t)
chunk_end = NumbersDict.min([t + chunk_size, length])
for key in keys_with_full_seqs:
chunk_start[key] = 0
chunk_end[key] = length[key]
if length.value is None:
chunk_start.value = None
chunk_end.value = None
yield (s, chunk_start, chunk_end)
t += chunk_step
if length[default_key] - t[default_key] <= self.min_chunk_size:
break
s += 1
