Delete main/src/sequence_array.py with huggingface_hub
Browse files- main/src/sequence_array.py +0 -217
main/src/sequence_array.py
DELETED
|
@@ -1,217 +0,0 @@
|
|
| 1 |
-
import sequence
|
| 2 |
-
import sampler as sampler_src
|
| 3 |
-
import numpy as np
|
| 4 |
-
import collections
|
| 5 |
-
import copy
|
| 6 |
-
import torch
|
| 7 |
-
|
| 8 |
-
# this the name used for the sample UID
|
| 9 |
-
sample_uid_name = 'sample_uid'
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
def get_batch_n(split, nb_samples, indices, transforms, use_advanced_indexing):
|
| 13 |
-
"""
|
| 14 |
-
Collect the split indices given and apply a series of transformations
|
| 15 |
-
|
| 16 |
-
Args:
|
| 17 |
-
nb_samples: the total number of samples of split
|
| 18 |
-
split: a mapping of `np.ndarray` or `torch.Tensor`
|
| 19 |
-
indices: a list of indices as numpy array
|
| 20 |
-
transforms: a transformation or list of transformations or None
|
| 21 |
-
use_advanced_indexing: if True, use the advanced indexing mechanism else
|
| 22 |
-
use a simple list (original data is referenced)
|
| 23 |
-
advanced indexing is typically faster for small objects, however for large objects (e.g., 3D data)
|
| 24 |
-
the advanced indexing makes a copy of the data making it very slow.
|
| 25 |
-
|
| 26 |
-
Returns:
|
| 27 |
-
a split with the indices provided
|
| 28 |
-
"""
|
| 29 |
-
data = {}
|
| 30 |
-
for split_name, split_data in split.items():
|
| 31 |
-
if isinstance(split_data, (torch.Tensor, np.ndarray)) and len(split_data) == nb_samples:
|
| 32 |
-
# here we prefer [split_data[i] for i in indices] over split_data[indices]
|
| 33 |
-
# this is because split_data[indices] will make a deep copy of the data which may be time consuming
|
| 34 |
-
# for large data
|
| 35 |
-
if use_advanced_indexing:
|
| 36 |
-
split_data = split_data[indices]
|
| 37 |
-
else:
|
| 38 |
-
split_data = [[split_data[i]] for i in indices]
|
| 39 |
-
if isinstance(split_data, list) and len(split_data) == nb_samples:
|
| 40 |
-
split_data = [split_data[i] for i in indices]
|
| 41 |
-
|
| 42 |
-
data[split_name] = split_data
|
| 43 |
-
|
| 44 |
-
if transforms is None:
|
| 45 |
-
# do nothing: there is no transform
|
| 46 |
-
pass
|
| 47 |
-
elif isinstance(transforms, collections.Sequence):
|
| 48 |
-
# we have a list of transforms, apply each one of them
|
| 49 |
-
for transform in transforms:
|
| 50 |
-
data = transform(data)
|
| 51 |
-
else:
|
| 52 |
-
# anything else should be a functor
|
| 53 |
-
data = transforms(data)
|
| 54 |
-
|
| 55 |
-
return data
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
def len_batch(batch):
|
| 59 |
-
"""
|
| 60 |
-
|
| 61 |
-
Args:
|
| 62 |
-
batch: a data split or a `collections.Sequence`
|
| 63 |
-
|
| 64 |
-
Returns:
|
| 65 |
-
the number of elements within a data split
|
| 66 |
-
"""
|
| 67 |
-
if isinstance(batch, (collections.Sequence, torch.Tensor)):
|
| 68 |
-
return len(batch)
|
| 69 |
-
|
| 70 |
-
assert isinstance(batch, collections.Mapping), 'Must be a dict-like structure! got={}'.format(type(batch))
|
| 71 |
-
|
| 72 |
-
for name, values in batch.items():
|
| 73 |
-
if isinstance(values, (list, tuple)):
|
| 74 |
-
return len(values)
|
| 75 |
-
if isinstance(values, torch.Tensor) and len(values.shape) != 0:
|
| 76 |
-
return values.shape[0]
|
| 77 |
-
if isinstance(values, np.ndarray) and len(values.shape) != 0:
|
| 78 |
-
return values.shape[0]
|
| 79 |
-
return 0
|
| 80 |
-
|
| 81 |
-
class SequenceArray(sequence.Sequence):
|
| 82 |
-
"""
|
| 83 |
-
Create a sequence of batches from numpy arrays, lists and :class:`torch.Tensor`
|
| 84 |
-
"""
|
| 85 |
-
def __init__(
|
| 86 |
-
self,
|
| 87 |
-
split,
|
| 88 |
-
sampler=sampler_src.SamplerRandom(),
|
| 89 |
-
transforms=None,
|
| 90 |
-
use_advanced_indexing=True,
|
| 91 |
-
sample_uid_name=sample_uid_name):
|
| 92 |
-
"""
|
| 93 |
-
|
| 94 |
-
Args:
|
| 95 |
-
split: a dictionary of tensors. Tensors may be `numpy.ndarray`, `torch.Tensor`, numeric
|
| 96 |
-
sampler: the sampler to be used to iterate through the sequence
|
| 97 |
-
transforms: a transform or list of transforms to be applied on each batch of data
|
| 98 |
-
use_advanced_indexing:
|
| 99 |
-
sample_uid_name: if not `None`, create a unique UID per sample so that it is easy to track
|
| 100 |
-
particular samples (e.g., during data augmentation)
|
| 101 |
-
"""
|
| 102 |
-
super().__init__(None) # there is no source sequence for this as we get our input from a numpy split
|
| 103 |
-
self.split = split
|
| 104 |
-
self.nb_samples = None
|
| 105 |
-
self.sampler = sampler
|
| 106 |
-
self.sampler_iterator = None
|
| 107 |
-
self.transforms = transforms
|
| 108 |
-
self.use_advanced_indexing = use_advanced_indexing
|
| 109 |
-
|
| 110 |
-
# create a unique UID
|
| 111 |
-
if sample_uid_name is not None and sample_uid_name not in split:
|
| 112 |
-
split[sample_uid_name] = np.asarray(np.arange(len_batch(split)))
|
| 113 |
-
|
| 114 |
-
def subsample(self, nb_samples):
|
| 115 |
-
# get random indices
|
| 116 |
-
subsample_sample = sampler_src.SamplerRandom(batch_size=nb_samples)
|
| 117 |
-
subsample_sample.initializer(self.split)
|
| 118 |
-
|
| 119 |
-
# extract the indices
|
| 120 |
-
indices = next(iter(subsample_sample))
|
| 121 |
-
subsampled_split = get_batch_n(
|
| 122 |
-
self.split,
|
| 123 |
-
len_batch(self.split),
|
| 124 |
-
indices,
|
| 125 |
-
self.transforms,
|
| 126 |
-
# use `use_advanced_indexing` so that we keep the types as close as possible to original
|
| 127 |
-
use_advanced_indexing=True
|
| 128 |
-
)
|
| 129 |
-
return SequenceArray(
|
| 130 |
-
subsampled_split,
|
| 131 |
-
copy.deepcopy(self.sampler),
|
| 132 |
-
transforms=self.transforms,
|
| 133 |
-
use_advanced_indexing=self.use_advanced_indexing
|
| 134 |
-
)
|
| 135 |
-
|
| 136 |
-
def subsample_uids(self, uids, uids_name, new_sampler=None):
|
| 137 |
-
uid_values = self.split.get(uids_name)
|
| 138 |
-
assert uid_values is not None, 'no UIDs with name={}'.format(uids_name)
|
| 139 |
-
|
| 140 |
-
# find the samples that are in `uids`
|
| 141 |
-
indices_to_keep = []
|
| 142 |
-
uids_set = set(uids)
|
| 143 |
-
for index, uid in enumerate(uid_values):
|
| 144 |
-
if uid in uids_set:
|
| 145 |
-
indices_to_keep.append(index)
|
| 146 |
-
|
| 147 |
-
# reorder the `indices_to_keep` following the `uids` ordering
|
| 148 |
-
uids_ordering = {uid: index for index, uid in enumerate(uids)}
|
| 149 |
-
kvp_index_ordering = []
|
| 150 |
-
for index in indices_to_keep:
|
| 151 |
-
uid = uid_values[index]
|
| 152 |
-
ordering = uids_ordering[uid]
|
| 153 |
-
kvp_index_ordering.append((index, ordering))
|
| 154 |
-
kvp_uids_ordering = sorted(kvp_index_ordering, key=lambda value: value[1])
|
| 155 |
-
indices_to_keep = [index for index, ordering in kvp_uids_ordering]
|
| 156 |
-
|
| 157 |
-
# extract the samples
|
| 158 |
-
subsampled_split = get_batch_n(
|
| 159 |
-
self.split,
|
| 160 |
-
len_batch(self.split),
|
| 161 |
-
indices_to_keep,
|
| 162 |
-
self.transforms,
|
| 163 |
-
# use `use_advanced_indexing` so that we keep the types as close as possible to original
|
| 164 |
-
use_advanced_indexing=True
|
| 165 |
-
)
|
| 166 |
-
|
| 167 |
-
if new_sampler is None:
|
| 168 |
-
new_sampler = copy.deepcopy(self.sampler)
|
| 169 |
-
else:
|
| 170 |
-
new_sampler = copy.deepcopy(new_sampler)
|
| 171 |
-
|
| 172 |
-
return SequenceArray(
|
| 173 |
-
subsampled_split,
|
| 174 |
-
new_sampler,
|
| 175 |
-
transforms=self.transforms,
|
| 176 |
-
use_advanced_indexing=self.use_advanced_indexing
|
| 177 |
-
)
|
| 178 |
-
|
| 179 |
-
def __iter__(self):
|
| 180 |
-
# make sure the sampler is copied so that we can have multiple iterators of the
|
| 181 |
-
# same sequence
|
| 182 |
-
return SequenceIteratorArray(self, copy.deepcopy(self.sampler))
|
| 183 |
-
|
| 184 |
-
def close(self):
|
| 185 |
-
pass
|
| 186 |
-
|
| 187 |
-
|
| 188 |
-
class SequenceIteratorArray(sequence.SequenceIterator):
|
| 189 |
-
"""
|
| 190 |
-
Iterate the elements of an :class:`SequenceArray` sequence
|
| 191 |
-
|
| 192 |
-
Assumptions:
|
| 193 |
-
- underlying `base_sequence` doesn't change sizes while iterating
|
| 194 |
-
"""
|
| 195 |
-
def __init__(self, base_sequence, sampler):
|
| 196 |
-
super().__init__()
|
| 197 |
-
self.base_sequence = base_sequence
|
| 198 |
-
self.nb_samples = len_batch(self.base_sequence.split)
|
| 199 |
-
|
| 200 |
-
self.sampler = sampler
|
| 201 |
-
self.sampler.initializer(self.base_sequence.split)
|
| 202 |
-
self.sampler_iterator = iter(self.sampler)
|
| 203 |
-
|
| 204 |
-
def __next__(self):
|
| 205 |
-
indices = self.sampler_iterator.__next__()
|
| 206 |
-
if not isinstance(indices, (np.ndarray, collections.Sequence)):
|
| 207 |
-
indices = [indices]
|
| 208 |
-
|
| 209 |
-
return get_batch_n(
|
| 210 |
-
self.base_sequence.split,
|
| 211 |
-
self.nb_samples,
|
| 212 |
-
indices,
|
| 213 |
-
self.base_sequence.transforms,
|
| 214 |
-
self.base_sequence.use_advanced_indexing)
|
| 215 |
-
|
| 216 |
-
def close(self):
|
| 217 |
-
pass
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|