def assign_to_words_(wordflann, words, idx2_vec, idx_name='idx', dense=True,
nAssign=1, with_pandas=WITH_PANDAS):
"""
Assigns descriptor-vectors to nearest word. Returns forward and inverted index.
>>> from ibeis.model.hots.smk.smk_index import * # NOQA
>>> from ibeis.model.hots.smk import smk_debug
>>> ibs, annots_df, daids, qaids, invindex = smk_debug.testdata_raw_internals0()
>>> words = invindex.words
>>> wordflann = invindex.wordflann
>>> idx2_vec = invindex.idx2_dvec
>>> dense = True
>>> nAssign = ibs.cfg.query_cfg.smk_cfg.nAssign
>>> idx_name, series_name = 'idx', 'wx2_idxs'
>>> _dbargs = (wordflann, words, idx2_vec, idx_name, dense, nAssign)
>>> wx2_idxs, idx2_wx = assign_to_words_(*_dbargs)
"""
idx2_vec_values = pdh.ensure_values(idx2_vec)
# Find each vectors nearest word
#TODO: multiple assignment
_idx2_wx, _idx2_wdist = wordflann.nn_index(idx2_vec_values, nAssign)
if nAssign > 1:
#((words[_idx2_wx[:,0]].astype(np.float64) - idx2_vec_values.astype(np.float64)) ** 2).sum(axis=0)
#_idx2_wdist[:,0]
#np.sqrt(((words[_idx2_wx[:,0]].astype(np.float64) - idx2_vec_values.astype(np.float64)) ** 2).sum(axis=0))
# mutli assignment filtering as in
# http://lear.inrialpes.fr/pubs/2010/JDS10a/jegou_improvingbof_preprint.pdf
alpha = 1.2
thresh = alpha * _idx2_wdist.T[0:1].T
invalid = _idx2_wdist >= thresh
# Weighting as in Lost in Quantization
sigma = 80
unnorm_weight = np.exp(np.divide(-_idx2_wdist.astype(np.float64), 2 * (sigma ** 2)))
masked_weight = np.ma.masked_array(unnorm_weight, mask=invalid)
weight = masked_weight / masked_weight.sum(axis=1)[:, np.newaxis]
masked_wxs = np.ma.masked_array(_idx2_wx, mask=invalid)
idx2_wxs = map(utool.filter_Nones, masked_wxs.tolist())
idx2_wx_weights = map(utool.filter_Nones, weight.tolist())
#masked_weight1 = np.ma.masked_array(_idx2_wdist, mask=invalid)
#weight1 = masked_weight1 / masked_weight1.sum(axis=1)[:, np.newaxis]
# multiple assignment weight: expt(-(d ** 2) / (2 * sigma ** 2))
# The distance d_0 is used to filter asignments with distance less than
# alpha * d_0 where alpha = 1.2
PANDAS_GROUP = True or with_pandas
# Compute inverted index
if PANDAS_GROUP:
# Pandas grouping seems to be faster in this instance
word_assignments = pd.DataFrame(_idx2_wx, columns=['wx']) # 141 us
word_group = word_assignments.groupby('wx') # 34.5 us
_wx2_idxs = word_group['wx'].indices # 8.6 us
else:
idx2_idx = np.arange(len(idx2_vec))
wx_list, groupxs = smk_speed.group_indicies(_idx2_wx) # 5.52 ms
idxs_list = smk_speed.apply_grouping(idx2_idx, groupxs) # 2.9 ms
_wx2_idxs = dict(zip(wx_list, idxs_list)) # 753 us
#
if with_pandas:
idx_series = pdh.ensure_index(idx2_vec)
wx_series = pdh.ensure_index(words)
wx2_idxs = pdh.pandasify_dict1d(
_wx2_idxs, wx_series, idx_name, ('wx2_' + idx_name + 's'), dense=dense) # 274 ms 97.4 %
idx2_wx = pdh.IntSeries(_idx2_wx, index=idx_series, name='wx')
else:
if dense:
wx2_idxs = {
wx: _wx2_idxs[wx].astype(INDEX_TYPE)
if wx in _wx2_idxs else
np.empty(0, dtype=INDEX_TYPE)
for wx in range(len(words))
}
#wx2_idxs = _wx2_idxs
#for wx in range(len(words)):
# if wx not in wx2_idxs:
# wx2_idxs[wx] = np.empty(0, dtype=INDEX_TYPE)
else:
wx2_idxs = _wx2_idxs
idx2_wx = _idx2_wx
return wx2_idxs, idx2_wx
def assign_to_words_(wordflann, words, idx2_vec, idx_name='idx', dense=True,
nAssign=1, massign_alpha=1.2, massign_sigma=80):
"""
Assigns descriptor-vectors to nearest word.
Returns inverted index, multi-assigned weights, and forward index
wx2_idxs - word index -> vector indexes
wx2_maws - word index -> multi-assignment weights
idf2_wxs - vector index -> assigned word indexes
>>> from ibeis.model.hots.smk.smk_index import * # NOQA
>>> from ibeis.model.hots.smk import smk_debug
>>> ibs, annots_df, daids, qaids, invindex = smk_debug.testdata_raw_internals0()
>>> words = invindex.words
>>> wordflann = invindex.wordflann
>>> idx2_vec = invindex.idx2_dvec
>>> dense = True
>>> nAssign = ibs.cfg.query_cfg.smk_cfg.nAssign
>>> _dbargs = (wordflann, words, idx2_vec, idx_name, dense, nAssign)
>>> wx2_idxs, wx2_maws, idx2_wxs = assign_to_words_(*_dbargs)
"""
idx2_vec_values = pdh.ensure_values(idx2_vec)
# Assign each vector to the nearest visual words
_idx2_wx, _idx2_wdist = wordflann.nn_index(idx2_vec_values, nAssign)
if nAssign > 1:
# MultiAssignment Filtering from Improving Bag of Features
# http://lear.inrialpes.fr/pubs/2010/JDS10a/jegou_improvingbof_preprint.pdf
thresh = np.multiply(massign_alpha, _idx2_wdist.T[0:1].T)
invalid = np.greater_equal(_idx2_wdist, thresh)
# Weighting as in Lost in Quantization
gauss_numer = -_idx2_wdist.astype(np.float64)
gauss_denom = 2 * (massign_sigma ** 2)
gauss_exp = np.divide(gauss_numer, gauss_denom)
unnorm_maw = np.exp(gauss_exp)
# Mask invalid multiassignment weights
masked_unorm_maw = np.ma.masked_array(unnorm_maw, mask=invalid)
# Normalize multiassignment weights from 0 to 1
masked_norm = masked_unorm_maw.sum(axis=1)[:, np.newaxis]
masked_maw = np.divide(masked_unorm_maw, masked_norm)
masked_wxs = np.ma.masked_array(_idx2_wx, mask=invalid)
# Remove masked weights and word indexes
idx2_wxs = list(map(utool.filter_Nones, masked_wxs.tolist()))
idx2_maws = list(map(utool.filter_Nones, masked_maw.tolist()))
else:
idx2_wxs = _idx2_wx.tolist()
idx2_maws = [1.0] * len(idx2_wxs)
# Invert mapping -- Group by word indexes
jagged_idxs = ([idx] * len(wxs) for idx, wxs in enumerate(idx2_wxs))
wx_keys, groupxs = clustertool.jagged_group(idx2_wxs)
idxs_list = clustertool.apply_jagged_grouping(jagged_idxs, groupxs)
maws_list = clustertool.apply_jagged_grouping(idx2_maws, groupxs)
wx2_idxs = dict(zip(wx_keys, idxs_list))
wx2_maws = dict(zip(wx_keys, maws_list))
if WITH_PANDAS:
idx_series = pdh.ensure_index(idx2_vec)
wx_series = pdh.ensure_index(words)
wx2_idxs = pdh.pandasify_dict1d(
wx2_idxs, wx_series, idx_name, ('wx2_' + idx_name + 's'), dense=dense)
idx2_wxs = pdh.IntSeries(idx2_wxs, index=idx_series, name='wx')
return wx2_idxs, wx2_maws, idx2_wxs
def assign_to_words_(wordflann,
words,
idx2_vec,
idx_name='idx',
dense=True,
nAssign=1,
with_pandas=WITH_PANDAS):
"""
Assigns descriptor-vectors to nearest word. Returns forward and inverted index.
>>> from ibeis.model.hots.smk.smk_index import * # NOQA
>>> from ibeis.model.hots.smk import smk_debug
>>> ibs, annots_df, daids, qaids, invindex = smk_debug.testdata_raw_internals0()
>>> words = invindex.words
>>> wordflann = invindex.wordflann
>>> idx2_vec = invindex.idx2_dvec
>>> dense = True
>>> nAssign = ibs.cfg.query_cfg.smk_cfg.nAssign
>>> idx_name, series_name = 'idx', 'wx2_idxs'
>>> _dbargs = (wordflann, words, idx2_vec, idx_name, dense, nAssign)
>>> wx2_idxs, idx2_wx = assign_to_words_(*_dbargs)
"""
idx2_vec_values = pdh.ensure_values(idx2_vec)
# Find each vectors nearest word
#TODO: multiple assignment
_idx2_wx, _idx2_wdist = wordflann.nn_index(idx2_vec_values, nAssign)
if nAssign > 1:
#((words[_idx2_wx[:,0]].astype(np.float64) - idx2_vec_values.astype(np.float64)) ** 2).sum(axis=0)
#_idx2_wdist[:,0]
#np.sqrt(((words[_idx2_wx[:,0]].astype(np.float64) - idx2_vec_values.astype(np.float64)) ** 2).sum(axis=0))
# mutli assignment filtering as in
# http://lear.inrialpes.fr/pubs/2010/JDS10a/jegou_improvingbof_preprint.pdf
alpha = 1.2
thresh = alpha * _idx2_wdist.T[0:1].T
invalid = _idx2_wdist >= thresh
# Weighting as in Lost in Quantization
sigma = 80
unnorm_weight = np.exp(
np.divide(-_idx2_wdist.astype(np.float64), 2 * (sigma**2)))
masked_weight = np.ma.masked_array(unnorm_weight, mask=invalid)
weight = masked_weight / masked_weight.sum(axis=1)[:, np.newaxis]
masked_wxs = np.ma.masked_array(_idx2_wx, mask=invalid)
idx2_wxs = map(utool.filter_Nones, masked_wxs.tolist())
idx2_wx_weights = map(utool.filter_Nones, weight.tolist())
#masked_weight1 = np.ma.masked_array(_idx2_wdist, mask=invalid)
#weight1 = masked_weight1 / masked_weight1.sum(axis=1)[:, np.newaxis]
# multiple assignment weight: expt(-(d ** 2) / (2 * sigma ** 2))
# The distance d_0 is used to filter asignments with distance less than
# alpha * d_0 where alpha = 1.2
PANDAS_GROUP = True or with_pandas
# Compute inverted index
if PANDAS_GROUP:
# Pandas grouping seems to be faster in this instance
word_assignments = pd.DataFrame(_idx2_wx, columns=['wx']) # 141 us
word_group = word_assignments.groupby('wx') # 34.5 us
_wx2_idxs = word_group['wx'].indices # 8.6 us
else:
idx2_idx = np.arange(len(idx2_vec))
wx_list, groupxs = smk_speed.group_indicies(_idx2_wx) # 5.52 ms
idxs_list = smk_speed.apply_grouping(idx2_idx, groupxs) # 2.9 ms
_wx2_idxs = dict(zip(wx_list, idxs_list)) # 753 us
#
if with_pandas:
idx_series = pdh.ensure_index(idx2_vec)
wx_series = pdh.ensure_index(words)
wx2_idxs = pdh.pandasify_dict1d(_wx2_idxs,
wx_series,
idx_name, ('wx2_' + idx_name + 's'),
dense=dense) # 274 ms 97.4 %
idx2_wx = pdh.IntSeries(_idx2_wx, index=idx_series, name='wx')
else:
if dense:
wx2_idxs = {
wx: _wx2_idxs[wx].astype(INDEX_TYPE)
if wx in _wx2_idxs else np.empty(0, dtype=INDEX_TYPE)
for wx in range(len(words))
}
#wx2_idxs = _wx2_idxs
#for wx in range(len(words)):
# if wx not in wx2_idxs:
# wx2_idxs[wx] = np.empty(0, dtype=INDEX_TYPE)
else:
wx2_idxs = _wx2_idxs
idx2_wx = _idx2_wx
return wx2_idxs, idx2_wx
def assign_to_words_(wordflann,
words,
idx2_vec,
idx_name='idx',
dense=True,
nAssign=1,
massign_alpha=1.2,
massign_sigma=80):
"""
Assigns descriptor-vectors to nearest word.
Returns inverted index, multi-assigned weights, and forward index
wx2_idxs - word index -> vector indexes
wx2_maws - word index -> multi-assignment weights
idf2_wxs - vector index -> assigned word indexes
>>> from ibeis.model.hots.smk.smk_index import * # NOQA
>>> from ibeis.model.hots.smk import smk_debug
>>> ibs, annots_df, daids, qaids, invindex = smk_debug.testdata_raw_internals0()
>>> words = invindex.words
>>> wordflann = invindex.wordflann
>>> idx2_vec = invindex.idx2_dvec
>>> dense = True
>>> nAssign = ibs.cfg.query_cfg.smk_cfg.nAssign
>>> _dbargs = (wordflann, words, idx2_vec, idx_name, dense, nAssign)
>>> wx2_idxs, wx2_maws, idx2_wxs = assign_to_words_(*_dbargs)
"""
idx2_vec_values = pdh.ensure_values(idx2_vec)
# Assign each vector to the nearest visual words
_idx2_wx, _idx2_wdist = wordflann.nn_index(idx2_vec_values, nAssign)
if nAssign > 1:
# MultiAssignment Filtering from Improving Bag of Features
# http://lear.inrialpes.fr/pubs/2010/JDS10a/jegou_improvingbof_preprint.pdf
thresh = np.multiply(massign_alpha, _idx2_wdist.T[0:1].T)
invalid = np.greater_equal(_idx2_wdist, thresh)
# Weighting as in Lost in Quantization
gauss_numer = -_idx2_wdist.astype(np.float64)
gauss_denom = 2 * (massign_sigma**2)
gauss_exp = np.divide(gauss_numer, gauss_denom)
unnorm_maw = np.exp(gauss_exp)
# Mask invalid multiassignment weights
masked_unorm_maw = np.ma.masked_array(unnorm_maw, mask=invalid)
# Normalize multiassignment weights from 0 to 1
masked_norm = masked_unorm_maw.sum(axis=1)[:, np.newaxis]
masked_maw = np.divide(masked_unorm_maw, masked_norm)
masked_wxs = np.ma.masked_array(_idx2_wx, mask=invalid)
# Remove masked weights and word indexes
idx2_wxs = list(map(utool.filter_Nones, masked_wxs.tolist()))
idx2_maws = list(map(utool.filter_Nones, masked_maw.tolist()))
else:
idx2_wxs = _idx2_wx.tolist()
idx2_maws = [1.0] * len(idx2_wxs)
# Invert mapping -- Group by word indexes
jagged_idxs = ([idx] * len(wxs) for idx, wxs in enumerate(idx2_wxs))
wx_keys, groupxs = clustertool.jagged_group(idx2_wxs)
idxs_list = clustertool.apply_jagged_grouping(jagged_idxs, groupxs)
maws_list = clustertool.apply_jagged_grouping(idx2_maws, groupxs)
wx2_idxs = dict(zip(wx_keys, idxs_list))
wx2_maws = dict(zip(wx_keys, maws_list))
if WITH_PANDAS:
idx_series = pdh.ensure_index(idx2_vec)
wx_series = pdh.ensure_index(words)
wx2_idxs = pdh.pandasify_dict1d(wx2_idxs,
wx_series,
idx_name, ('wx2_' + idx_name + 's'),
dense=dense)
idx2_wxs = pdh.IntSeries(idx2_wxs, index=idx_series, name='wx')
return wx2_idxs, wx2_maws, idx2_wxs