def compute_data_gamma_(idx2_daid, wx2_rvecs, wx2_aids, wx2_weight,
alpha=3, thresh=0):
"""
Internals step4
Computes gamma normalization scalar for the database annotations
>>> from ibeis.model.hots.smk.smk_index import * # NOQA
>>> from ibeis.model.hots.smk import smk_debug
>>> ibs, annots_df, invindex, wx2_idxs, wx2_idf, wx2_rvecs, wx2_aids = smk_debug.testdata_raw_internals2()
>>> alpha = ibs.cfg.query_cfg.smk_cfg.alpha
>>> thresh = ibs.cfg.query_cfg.smk_cfg.thresh
>>> idx2_daid = invindex.idx2_daid
>>> wx2_weight = wx2_idf
>>> daids = invindex.daids
>>> use_cache = USE_CACHE_GAMMA and False
>>> daid2_gamma = compute_data_gamma_(idx2_daid, wx2_rvecs, wx2_aids, wx2_weight, daids, use_cache=use_cache)
"""
# Gropuing by aid and words
wx_sublist = pdh.ensure_values(pdh.ensure_index(wx2_rvecs))
if utool.VERBOSE:
print('[smk_index] Compute Gamma alpha=%r, thresh=%r: ' % (alpha, thresh))
mark1, end1_ = utool.log_progress(
'[smk_index] Gamma Group: ', len(wx_sublist), flushfreq=100, writefreq=50)
rvecs_list1 = pdh.ensure_values_subset(wx2_rvecs, wx_sublist)
aids_list = pdh.ensure_values_subset(wx2_aids, wx_sublist)
daid2_wx2_drvecs = utool.ddict(lambda: utool.ddict(list))
# Group by daids first and then by word index
for wx, aids, rvecs in zip(wx_sublist, aids_list, rvecs_list1):
group_aids, groupxs = smk_speed.group_indicies(aids)
rvecs_group = smk_speed.apply_grouping(rvecs, groupxs) # 2.9 ms
for aid, rvecs_ in zip(group_aids, rvecs_group):
daid2_wx2_drvecs[aid][wx] = rvecs_
if utool.VERBOSE:
end1_()
# For every daid, compute its gamma using pregrouped rvecs
# Summation over words for each aid
if utool.VERBOSE:
mark2, end2_ = utool.log_progress(
'[smk_index] Gamma Sum: ', len(daid2_wx2_drvecs), flushfreq=100, writefreq=25)
aid_list = list(daid2_wx2_drvecs.keys())
wx2_aidrvecs_list = list(daid2_wx2_drvecs.values())
aidwxs_list = [list(wx2_aidrvecs.keys()) for wx2_aidrvecs in wx2_aidrvecs_list]
aidrvecs_list = [list(wx2_aidrvecs.values()) for wx2_aidrvecs in wx2_aidrvecs_list]
aidweight_list = [[wx2_weight[wx] for wx in aidwxs] for aidwxs in aidwxs_list]
#gamma_list = []
#for weight_list, rvecs_list in zip(aidweight_list, aidrvecs_list):
# assert len(weight_list) == len(rvecs_list), 'one list for each word'
# gamma = smk_core.gamma_summation2(rvecs_list, weight_list, alpha, thresh) # 66.8 %
# #weight_list = np.ones(weight_list.size)
# gamma_list.append(gamma)
gamma_list = [smk_core.gamma_summation2(rvecs_list, weight_list, alpha, thresh)
for weight_list, rvecs_list in zip(aidweight_list, aidrvecs_list)]
daid2_gamma = pdh.IntSeries(gamma_list, index=aid_list, name='gamma')
if utool.VERBOSE:
end2_()
return daid2_gamma
def compute_data_gamma_(idx2_daid,
wx2_rvecs,
wx2_aids,
wx2_weight,
alpha=3,
thresh=0):
"""
Internals step4
Computes gamma normalization scalar for the database annotations
>>> from ibeis.model.hots.smk.smk_index import * # NOQA
>>> from ibeis.model.hots.smk import smk_debug
>>> ibs, annots_df, invindex, wx2_idxs, wx2_idf, wx2_rvecs, wx2_aids = smk_debug.testdata_raw_internals2()
>>> alpha = ibs.cfg.query_cfg.smk_cfg.alpha
>>> thresh = ibs.cfg.query_cfg.smk_cfg.thresh
>>> idx2_daid = invindex.idx2_daid
>>> wx2_weight = wx2_idf
>>> daids = invindex.daids
>>> use_cache = USE_CACHE_GAMMA and False
>>> daid2_gamma = compute_data_gamma_(idx2_daid, wx2_rvecs, wx2_aids, wx2_weight, daids, use_cache=use_cache)
"""
# Gropuing by aid and words
wx_sublist = pdh.ensure_values(pdh.ensure_index(wx2_rvecs))
if utool.VERBOSE:
print('[smk_index] Compute Gamma alpha=%r, thresh=%r: ' %
(alpha, thresh))
mark1, end1_ = utool.log_progress('[smk_index] Gamma Group: ',
len(wx_sublist),
flushfreq=100,
writefreq=50)
rvecs_list1 = pdh.ensure_values_subset(wx2_rvecs, wx_sublist)
aids_list = pdh.ensure_values_subset(wx2_aids, wx_sublist)
daid2_wx2_drvecs = utool.ddict(lambda: utool.ddict(list))
# Group by daids first and then by word index
for wx, aids, rvecs in zip(wx_sublist, aids_list, rvecs_list1):
group_aids, groupxs = smk_speed.group_indicies(aids)
rvecs_group = smk_speed.apply_grouping(rvecs, groupxs) # 2.9 ms
for aid, rvecs_ in zip(group_aids, rvecs_group):
daid2_wx2_drvecs[aid][wx] = rvecs_
if utool.VERBOSE:
end1_()
# For every daid, compute its gamma using pregrouped rvecs
# Summation over words for each aid
if utool.VERBOSE:
mark2, end2_ = utool.log_progress('[smk_index] Gamma Sum: ',
len(daid2_wx2_drvecs),
flushfreq=100,
writefreq=25)
aid_list = list(daid2_wx2_drvecs.keys())
wx2_aidrvecs_list = list(daid2_wx2_drvecs.values())
aidwxs_list = [
list(wx2_aidrvecs.keys()) for wx2_aidrvecs in wx2_aidrvecs_list
]
aidrvecs_list = [
list(wx2_aidrvecs.values()) for wx2_aidrvecs in wx2_aidrvecs_list
]
aidweight_list = [[wx2_weight[wx] for wx in aidwxs]
for aidwxs in aidwxs_list]
#gamma_list = []
#for weight_list, rvecs_list in zip(aidweight_list, aidrvecs_list):
# assert len(weight_list) == len(rvecs_list), 'one list for each word'
# gamma = smk_core.gamma_summation2(rvecs_list, weight_list, alpha, thresh) # 66.8 %
# #weight_list = np.ones(weight_list.size)
# gamma_list.append(gamma)
gamma_list = [
smk_core.gamma_summation2(rvecs_list, weight_list, alpha, thresh)
for weight_list, rvecs_list in zip(aidweight_list, aidrvecs_list)
]
daid2_gamma = pdh.IntSeries(gamma_list, index=aid_list, name='gamma')
if utool.VERBOSE:
end2_()
return daid2_gamma
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,
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