def group_correspondences(all_matches, all_scores, all_daids, daid2_sccw):
daid_keys, groupxs = clustertool.group_indices(all_daids)
fs_list = clustertool.apply_grouping(all_scores, groupxs)
fm_list = clustertool.apply_grouping(all_matches, groupxs)
daid2_fm = {daid: fm for daid, fm in zip(daid_keys, fm_list)}
daid2_fs = {daid: fs * daid2_sccw[daid] for daid, fs in zip(daid_keys, fs_list)}
# FIXME: generalize to when nAssign > 1
daid2_fk = {daid: np.ones(fs.size, dtype=hstypes.FK_DTYPE) for daid, fs in zip(daid_keys, fs_list)}
daid2_chipmatch = (daid2_fm, daid2_fs, daid2_fk)
return daid2_chipmatch
def group_correspondences(all_matches, all_scores, all_daids, daid2_sccw):
daid_keys, groupxs = clustertool.group_indices(all_daids)
fs_list = clustertool.apply_grouping(all_scores, groupxs)
fm_list = clustertool.apply_grouping(all_matches, groupxs)
daid2_fm = {daid: fm for daid, fm in zip(daid_keys, fm_list)}
daid2_fs = {
daid: fs * daid2_sccw[daid]
for daid, fs in zip(daid_keys, fs_list)
}
# FIXME: generalize to when nAssign > 1
daid2_fk = {
daid: np.ones(fs.size, dtype=hstypes.FK_DTYPE)
for daid, fs in zip(daid_keys, fs_list)
}
daid2_chipmatch = (daid2_fm, daid2_fs, daid2_fk)
return daid2_chipmatch
def build_daid2_chipmatch2(invindex, common_wxs, wx2_qaids, wx2_qfxs,
scores_list, daids_list, query_sccw):
"""
Builds explicit chipmatches that the rest of the pipeline plays nice with
Notation:
An explicit cmtup_old is a tuple (fm, fs, fk) feature_matches,
feature_scores, and feature_ranks.
Let N be the number of matches
A feature match, fm{shape=(N, 2), dtype=int32}, is an array where the first
column corresponds to query_feature_indexes (qfx) and the second column
corresponds to database_feature_indexes (dfx).
A feature score, fs{shape=(N,), dtype=float64} is an array of scores
A feature rank, fk{shape=(N,), dtype=int16} is an array of ranks
Returns:
daid2_chipmatch (dict) : (daid2_fm, daid2_fs, daid2_fk)
Return Format::
daid2_fm (dict): {daid: fm, ...}
daid2_fs (dict): {daid: fs, ...}
daid2_fk (dict): {daid: fk, ...}
Example:
>>> from ibeis.algo.hots.smk.smk_core import * # NOQA
>>> from ibeis.algo.hots.smk import smk_debug
>>> ibs, invindex, qindex, qparams = smk_debug.testdata_match_kernel_L2()
>>> wx2_qrvecs, wx2_qmaws, wx2_qaids, wx2_qfxs, query_sccw = qindex
>>> smk_alpha = ibs.cfg.query_cfg.smk_cfg.smk_alpha
>>> smk_thresh = ibs.cfg.query_cfg.smk_cfg.smk_thresh
>>> withinfo = True # takes an 11s vs 2s
>>> args = (wx2_qrvecs, wx2_qmaws, wx2_qaids, wx2_qfxs, query_sccw, invindex, withinfo, smk_alpha, smk_thresh)
>>> retL1 = match_kernel_L1(*args)
>>> (daid2_totalscore, common_wxs, scores_list, daids_list, idf_list, daid_agg_keys,) = retL1
>>> daid2_chipmatch_old = build_daid2_chipmatch2(invindex, common_wxs, wx2_qaids, wx2_qfxs, scores_list, daids_list, query_sccw)
>>> daid2_chipmatch_new = build_daid2_chipmatch3(invindex, common_wxs, wx2_qaids, wx2_qfxs, scores_list, daids_list, query_sccw)
>>> print(utool.is_dicteq(daid2_chipmatch_old[0], daid2_chipmatch_new[0]))
>>> print(utool.is_dicteq(daid2_chipmatch_old[2], daid2_chipmatch_new[2]))
>>> print(utool.is_dicteq(daid2_chipmatch_old[1], daid2_chipmatch_new[1]))
%timeit build_daid2_chipmatch2(invindex, common_wxs, wx2_qaids, wx2_qfxs, scores_list, daids_list, query_sccw)
%timeit build_daid2_chipmatch3(invindex, common_wxs, wx2_qaids, wx2_qfxs, scores_list, daids_list, query_sccw)
"""
# FIXME: move groupby to vtool
if utool.VERBOSE:
print('[smk_core] build cmtup_old')
wx2_dfxs = invindex.wx2_fxs
daid2_sccw = invindex.daid2_sccw
qfxs_list = [wx2_qfxs[wx] for wx in common_wxs]
dfxs_list = [wx2_dfxs[wx] for wx in common_wxs]
shapes_list = [scores.shape for scores in scores_list] # 51us
shape_ranges = [(mem_arange(w), mem_arange(h))
for (w, h) in shapes_list] # 230us
ijs_list = [
mem_meshgrid(wrange, hrange) for (wrange, hrange) in shape_ranges
] # 278us
# Normalize scores for words, nMatches, and query sccw (still need daid sccw)
nscores_iter = (scores * query_sccw for scores in scores_list)
# FIXME: Preflatten all of these lists
out_ijs = [list(zip(_is.flat, _js.flat)) for (_is, _js) in ijs_list]
out_qfxs = [[qfxs[ix] for (ix, jx) in ijs]
for (qfxs, ijs) in zip(qfxs_list, out_ijs)]
out_dfxs = [[dfxs[jx] for (ix, jx) in ijs]
for (dfxs, ijs) in zip(dfxs_list, out_ijs)]
out_daids = ([daids[jx] for (ix, jx) in ijs]
for (daids, ijs) in zip(daids_list, out_ijs))
out_scores = ([nscores[ijx] for ijx in ijs]
for (nscores, ijs) in zip(nscores_iter, out_ijs))
nested_fm_iter = [[
tuple(product(qfxs_, dfxs_)) for qfxs_, dfxs_ in zip(qfxs, dfxs)
] for qfxs, dfxs in zip(out_qfxs, out_dfxs)]
all_fms = np.array(list(utool.iflatten(utool.iflatten(nested_fm_iter))),
dtype=hstypes.FM_DTYPE)
nested_nmatch_list = [[len(fm) for fm in fms] for fms in nested_fm_iter]
nested_daid_iter = ([
[daid] * nMatch for nMatch, daid in zip(nMatch_list, daids)
] for nMatch_list, daids in zip(nested_nmatch_list, out_daids))
nested_score_iter = ([
[score / nMatch] * nMatch
for nMatch, score in zip(nMatch_list, scores)
] for nMatch_list, scores in zip(nested_nmatch_list, out_scores))
all_daids_ = np.array(list(utool.iflatten(
utool.iflatten(nested_daid_iter))),
dtype=hstypes.INDEX_TYPE)
all_fss = np.array(list(utool.iflatten(utool.iflatten(nested_score_iter))),
dtype=hstypes.FS_DTYPE)
# Filter out 0 scores
keep_xs = np.where(all_fss > 0)[0]
all_fss = all_fss.take(keep_xs)
all_fms = all_fms.take(keep_xs, axis=0)
all_daids_ = all_daids_.take(keep_xs)
daid_keys, groupxs = clustertool.group_indices(all_daids_)
fs_list = clustertool.apply_grouping(all_fss, groupxs)
fm_list = clustertool.apply_grouping(all_fms, groupxs)
daid2_fm = {daid: fm for daid, fm in zip(daid_keys, fm_list)}
daid2_fs = {
daid: fs * daid2_sccw[daid]
for daid, fs in zip(daid_keys, fs_list)
}
# FIXME: generalize to when nAssign > 1
daid2_fk = {
daid: np.ones(fs.size, dtype=hstypes.FK_DTYPE)
for daid, fs in zip(daid_keys, fs_list)
}
daid2_chipmatch = (daid2_fm, daid2_fs, daid2_fk)
return daid2_chipmatch
def build_daid2_chipmatch2(invindex, common_wxs, wx2_qaids, wx2_qfxs,
scores_list, daids_list, query_sccw):
"""
Builds explicit chipmatches that the rest of the pipeline plays nice with
Notation:
An explicit cmtup_old is a tuple (fm, fs, fk) feature_matches,
feature_scores, and feature_ranks.
Let N be the number of matches
A feature match, fm{shape=(N, 2), dtype=int32}, is an array where the first
column corresponds to query_feature_indexes (qfx) and the second column
corresponds to database_feature_indexes (dfx).
A feature score, fs{shape=(N,), dtype=float64} is an array of scores
A feature rank, fk{shape=(N,), dtype=int16} is an array of ranks
Returns:
daid2_chipmatch (dict) : (daid2_fm, daid2_fs, daid2_fk)
Return Format::
daid2_fm (dict): {daid: fm, ...}
daid2_fs (dict): {daid: fs, ...}
daid2_fk (dict): {daid: fk, ...}
Example:
>>> from ibeis.algo.hots.smk.smk_core import * # NOQA
>>> from ibeis.algo.hots.smk import smk_debug
>>> ibs, invindex, qindex, qparams = smk_debug.testdata_match_kernel_L2()
>>> wx2_qrvecs, wx2_qmaws, wx2_qaids, wx2_qfxs, query_sccw = qindex
>>> smk_alpha = ibs.cfg.query_cfg.smk_cfg.smk_alpha
>>> smk_thresh = ibs.cfg.query_cfg.smk_cfg.smk_thresh
>>> withinfo = True # takes an 11s vs 2s
>>> args = (wx2_qrvecs, wx2_qmaws, wx2_qaids, wx2_qfxs, query_sccw, invindex, withinfo, smk_alpha, smk_thresh)
>>> retL1 = match_kernel_L1(*args)
>>> (daid2_totalscore, common_wxs, scores_list, daids_list, idf_list, daid_agg_keys,) = retL1
>>> daid2_chipmatch_old = build_daid2_chipmatch2(invindex, common_wxs, wx2_qaids, wx2_qfxs, scores_list, daids_list, query_sccw)
>>> daid2_chipmatch_new = build_daid2_chipmatch3(invindex, common_wxs, wx2_qaids, wx2_qfxs, scores_list, daids_list, query_sccw)
>>> print(utool.is_dicteq(daid2_chipmatch_old[0], daid2_chipmatch_new[0]))
>>> print(utool.is_dicteq(daid2_chipmatch_old[2], daid2_chipmatch_new[2]))
>>> print(utool.is_dicteq(daid2_chipmatch_old[1], daid2_chipmatch_new[1]))
%timeit build_daid2_chipmatch2(invindex, common_wxs, wx2_qaids, wx2_qfxs, scores_list, daids_list, query_sccw)
%timeit build_daid2_chipmatch3(invindex, common_wxs, wx2_qaids, wx2_qfxs, scores_list, daids_list, query_sccw)
"""
# FIXME: move groupby to vtool
if utool.VERBOSE:
print('[smk_core] build cmtup_old')
wx2_dfxs = invindex.wx2_fxs
daid2_sccw = invindex.daid2_sccw
qfxs_list = [wx2_qfxs[wx] for wx in common_wxs]
dfxs_list = [wx2_dfxs[wx] for wx in common_wxs]
shapes_list = [scores.shape for scores in scores_list] # 51us
shape_ranges = [(mem_arange(w), mem_arange(h)) for (w, h) in shapes_list] # 230us
ijs_list = [mem_meshgrid(wrange, hrange) for (wrange, hrange) in shape_ranges] # 278us
# Normalize scores for words, nMatches, and query sccw (still need daid sccw)
nscores_iter = (scores * query_sccw for scores in scores_list)
# FIXME: Preflatten all of these lists
out_ijs = [
list(zip(_is.flat, _js.flat))
for (_is, _js) in ijs_list
]
out_qfxs = [
[qfxs[ix] for (ix, jx) in ijs]
for (qfxs, ijs) in zip(qfxs_list, out_ijs)
]
out_dfxs = [
[dfxs[jx] for (ix, jx) in ijs]
for (dfxs, ijs) in zip(dfxs_list, out_ijs)
]
out_daids = (
[daids[jx] for (ix, jx) in ijs]
for (daids, ijs) in zip(daids_list, out_ijs)
)
out_scores = (
[nscores[ijx] for ijx in ijs]
for (nscores, ijs) in zip(nscores_iter, out_ijs)
)
nested_fm_iter = [
[
tuple(product(qfxs_, dfxs_))
for qfxs_, dfxs_ in zip(qfxs, dfxs)
]
for qfxs, dfxs in zip(out_qfxs, out_dfxs)
]
all_fms = np.array(list(utool.iflatten(utool.iflatten(nested_fm_iter))), dtype=hstypes.FM_DTYPE)
nested_nmatch_list = [[len(fm) for fm in fms] for fms in nested_fm_iter]
nested_daid_iter = (
[
[daid] * nMatch
for nMatch, daid in zip(nMatch_list, daids)
]
for nMatch_list, daids in zip(nested_nmatch_list, out_daids)
)
nested_score_iter = (
[
[score / nMatch] * nMatch
for nMatch, score in zip(nMatch_list, scores)
]
for nMatch_list, scores in zip(nested_nmatch_list, out_scores)
)
all_daids_ = np.array(list(utool.iflatten(utool.iflatten(nested_daid_iter))), dtype=hstypes.INDEX_TYPE)
all_fss = np.array(list(utool.iflatten(utool.iflatten(nested_score_iter))), dtype=hstypes.FS_DTYPE)
# Filter out 0 scores
keep_xs = np.where(all_fss > 0)[0]
all_fss = all_fss.take(keep_xs)
all_fms = all_fms.take(keep_xs, axis=0)
all_daids_ = all_daids_.take(keep_xs)
daid_keys, groupxs = clustertool.group_indices(all_daids_)
fs_list = clustertool.apply_grouping(all_fss, groupxs)
fm_list = clustertool.apply_grouping(all_fms, groupxs)
daid2_fm = {daid: fm for daid, fm in zip(daid_keys, fm_list)}
daid2_fs = {daid: fs * daid2_sccw[daid] for daid, fs in zip(daid_keys, fs_list)}
# FIXME: generalize to when nAssign > 1
daid2_fk = {daid: np.ones(fs.size, dtype=hstypes.FK_DTYPE) for daid, fs in zip(daid_keys, fs_list)}
daid2_chipmatch = (daid2_fm, daid2_fs, daid2_fk)
return daid2_chipmatch
def compute_data_sccw_(idx2_daid, wx2_drvecs, wx2_dflags, wx2_aids, wx2_idf,
wx2_dmaws, smk_alpha, smk_thresh, verbose=False):
"""
Computes sccw normalization scalar for the database annotations.
This is gamma from the SMK paper.
sccw is a self consistency critiron weight --- a scalar which ensures
the score of K(X, X) = 1
Args:
idx2_daid ():
wx2_drvecs ():
wx2_aids ():
wx2_idf ():
wx2_dmaws ():
smk_alpha ():
smk_thresh ():
Returns:
daid2_sccw
Example:
>>> # SLOW_DOCTEST
>>> from ibeis.algo.hots.smk.smk_index import * # NOQA
>>> from ibeis.algo.hots.smk import smk_index
>>> from ibeis.algo.hots.smk import smk_debug
>>> #tup = smk_debug.testdata_compute_data_sccw(db='testdb1')
>>> tup = smk_debug.testdata_compute_data_sccw(db='PZ_MTEST')
>>> ibs, annots_df, invindex, wx2_idxs, wx2_idf, wx2_drvecs, wx2_aids, qparams = tup
>>> wx2_dflags = invindex.wx2_dflags
>>> ws2_idxs = invindex.wx2_idxs
>>> wx2_dmaws = invindex.wx2_dmaws
>>> idx2_daid = invindex.idx2_daid
>>> daids = invindex.daids
>>> smk_alpha = qparams.smk_alpha
>>> smk_thresh = qparams.smk_thresh
>>> wx2_idf = wx2_idf
>>> verbose = True
>>> invindex.invindex_dbgstr()
>>> invindex.report_memory()
>>> invindex.report_memsize()
>>> daid2_sccw = smk_index.compute_data_sccw_(idx2_daid, wx2_drvecs, wx2_dflags, wx2_aids, wx2_idf, wx2_dmaws, smk_alpha, smk_thresh, verbose)
"""
#for wx in wx_sublist:
# print(len(wx2_dmaws
verbose_ = ut.VERBOSE or verbose
if ut.DEBUG2:
from ibeis.algo.hots.smk import smk_debug
smk_debug.check_wx2(wx2_rvecs=wx2_drvecs, wx2_aids=wx2_aids)
if not ut.QUIET:
print('\n[smk_index.sccw] +--- Start Compute Data Self Consistency Weight')
if verbose_:
print('[smk_index.sccw] Compute SCCW smk_alpha=%r, smk_thresh=%r: ' % (smk_alpha, smk_thresh))
mark1, end1_ = ut.log_progress(
'[smk_index.sccw] SCCW group (by present words): ', len(wx2_drvecs),
freq=100, with_time=WITH_TOTALTIME)
# Group by daids first and then by word index
# Get list of aids and rvecs w.r.t. words (ie one item per word)
wx_sublist = np.array(list(wx2_drvecs.keys()))
aids_perword = [wx2_aids[wx] for wx in wx_sublist]
# wx_list1: Lays out word indexes for each annotation
# tx_list1: Temporary within annotation subindex + wx uniquely identifies
# item in wx2_drvecs, wx2_dflags, and wx2_dmaws
# Flatten out indexes to perform grouping
flat_aids = np.hstack(aids_perword)
count = len(flat_aids)
txs_perword = [np.arange(aids.size) for aids in aids_perword]
flat_txs = np.hstack(txs_perword)
# fromiter is faster for flat_wxs because is not a list of numpy arrays
wxs_perword = ([wx] * len(aids) for wx, aids in zip(wx_sublist, aids_perword))
flat_wxs = np.fromiter(ut.iflatten(wxs_perword), hstypes.INDEX_TYPE, count)
# Group flat indexes by annotation id
unique_aids, annot_groupxs = clustertool.group_indices(flat_aids)
# Wxs and Txs grouped by annotation id
wxs_perannot = clustertool.apply_grouping_iter(flat_wxs, annot_groupxs)
txs_perannot = clustertool.apply_grouping_iter(flat_txs, annot_groupxs)
# Group by word inside each annotation group
wxsubgrouping_perannot = [clustertool.group_indices(wxs)
for wxs in wxs_perannot]
word_groupxs_perannot = (groupxs for wxs, groupxs in wxsubgrouping_perannot)
txs_perword_perannot = [clustertool.apply_grouping(txs, groupxs)
for txs, groupxs in
zip(txs_perannot, word_groupxs_perannot)]
wxs_perword_perannot = [wxs for wxs, groupxs in wxsubgrouping_perannot]
# Group relavent data for sccw measure by word for each annotation grouping
def _vector_subgroup_by_wx(wx2_arr, wxs_perword_perannot, txs_perword_perannot):
return [[wx2_arr[wx].take(txs, axis=0)
for wx, txs in zip(wx_perword_, txs_perword_)]
for wx_perword_, txs_perword_ in
zip(wxs_perword_perannot, txs_perword_perannot)]
def _scalar_subgroup_by_wx(wx2_scalar, wxs_perword_perannot):
return [[wx2_scalar[wx] for wx in wxs] for wxs in wxs_perword_perannot]
subgrouped_drvecs = _vector_subgroup_by_wx(wx2_drvecs, wxs_perword_perannot, txs_perword_perannot)
subgrouped_dmaws = _vector_subgroup_by_wx(wx2_dmaws, wxs_perword_perannot, txs_perword_perannot)
# If we aren't using dmaws replace it with an infinite None iterator
#subgrouped_dmaws = iter(lambda: None, 1)
subgrouped_dflags = _vector_subgroup_by_wx(wx2_dflags, wxs_perword_perannot, txs_perword_perannot)
#subgrouped_dflags = iter(lambda: None, 1)
subgrouped_idfs = _scalar_subgroup_by_wx(wx2_idf, wxs_perword_perannot)
if verbose_:
end1_()
mark2, end2_ = ut.log_progress(lbl='[smk_index.sccw] SCCW Sum (over daid): ',
total=len(unique_aids), freq=100, with_time=WITH_TOTALTIME)
progiter = ut.ProgressIter(lbl='[smk_index.sccw] SCCW Sum (over daid): ',
total=len(unique_aids), freq=10, with_time=WITH_TOTALTIME)
else:
progiter = ut.identity
if ut.DEBUG2:
from ibeis.algo.hots.smk import smk_debug
smk_debug.check_data_smksumm(subgrouped_idfs, subgrouped_drvecs)
sccw_list = [
smk_scoring.sccw_summation(rvecs_list, flags_list, idf_list, maws_list, smk_alpha, smk_thresh)
for rvecs_list, flags_list, maws_list, idf_list in
progiter(zip(subgrouped_drvecs, subgrouped_dflags, subgrouped_dmaws, subgrouped_idfs))
]
daid2_sccw = dict(zip(unique_aids, sccw_list))
if verbose_:
end2_()
print('[smk_index.sccw] L___ End Compute Data SCCW\n')
return daid2_sccw
def compute_data_sccw_(idx2_daid, wx2_drvecs, wx2_dflags, wx2_aids, wx2_idf,
wx2_dmaws, smk_alpha, smk_thresh, verbose=False):
"""
Computes sccw normalization scalar for the database annotations.
This is gamma from the SMK paper.
sccw is a self consistency critiron weight --- a scalar which ensures
the score of K(X, X) = 1
Args:
idx2_daid ():
wx2_drvecs ():
wx2_aids ():
wx2_idf ():
wx2_dmaws ():
smk_alpha ():
smk_thresh ():
Returns:
daid2_sccw
Example:
>>> # SLOW_DOCTEST
>>> from ibeis.algo.hots.smk.smk_index import * # NOQA
>>> from ibeis.algo.hots.smk import smk_index
>>> from ibeis.algo.hots.smk import smk_debug
>>> #tup = smk_debug.testdata_compute_data_sccw(db='testdb1')
>>> tup = smk_debug.testdata_compute_data_sccw(db='PZ_MTEST')
>>> ibs, annots_df, invindex, wx2_idxs, wx2_idf, wx2_drvecs, wx2_aids, qparams = tup
>>> wx2_dflags = invindex.wx2_dflags
>>> ws2_idxs = invindex.wx2_idxs
>>> wx2_dmaws = invindex.wx2_dmaws
>>> idx2_daid = invindex.idx2_daid
>>> daids = invindex.daids
>>> smk_alpha = qparams.smk_alpha
>>> smk_thresh = qparams.smk_thresh
>>> wx2_idf = wx2_idf
>>> verbose = True
>>> invindex.invindex_dbgstr()
>>> invindex.report_memory()
>>> invindex.report_memsize()
>>> daid2_sccw = smk_index.compute_data_sccw_(idx2_daid, wx2_drvecs, wx2_dflags, wx2_aids, wx2_idf, wx2_dmaws, smk_alpha, smk_thresh, verbose)
"""
#for wx in wx_sublist:
# print(len(wx2_dmaws
verbose_ = ut.VERBOSE or verbose
if ut.DEBUG2:
from ibeis.algo.hots.smk import smk_debug
smk_debug.check_wx2(wx2_rvecs=wx2_drvecs, wx2_aids=wx2_aids)
if not ut.QUIET:
print('\n[smk_index.sccw] +--- Start Compute Data Self Consistency Weight')
if verbose_:
print('[smk_index.sccw] Compute SCCW smk_alpha=%r, smk_thresh=%r: ' % (smk_alpha, smk_thresh))
# Group by daids first and then by word index
# Get list of aids and rvecs w.r.t. words (ie one item per word)
wx_sublist = np.array(list(wx2_drvecs.keys()))
aids_perword = [wx2_aids[wx] for wx in wx_sublist]
# wx_list1: Lays out word indexes for each annotation
# tx_list1: Temporary within annotation subindex + wx uniquely identifies
# item in wx2_drvecs, wx2_dflags, and wx2_dmaws
# Flatten out indexes to perform grouping
flat_aids = np.hstack(aids_perword)
count = len(flat_aids)
txs_perword = [np.arange(aids.size) for aids in aids_perword]
flat_txs = np.hstack(txs_perword)
# fromiter is faster for flat_wxs because is not a list of numpy arrays
wxs_perword = ([wx] * len(aids) for wx, aids in zip(wx_sublist, aids_perword))
flat_wxs = np.fromiter(ut.iflatten(wxs_perword), hstypes.INDEX_TYPE, count)
# Group flat indexes by annotation id
unique_aids, annot_groupxs = clustertool.group_indices(flat_aids)
# Wxs and Txs grouped by annotation id
wxs_perannot = clustertool.apply_grouping_iter(flat_wxs, annot_groupxs)
txs_perannot = clustertool.apply_grouping_iter(flat_txs, annot_groupxs)
# Group by word inside each annotation group
wxsubgrouping_perannot = [clustertool.group_indices(wxs)
for wxs in wxs_perannot]
word_groupxs_perannot = (groupxs for wxs, groupxs in wxsubgrouping_perannot)
txs_perword_perannot = [clustertool.apply_grouping(txs, groupxs)
for txs, groupxs in
zip(txs_perannot, word_groupxs_perannot)]
wxs_perword_perannot = [wxs for wxs, groupxs in wxsubgrouping_perannot]
# Group relavent data for sccw measure by word for each annotation grouping
def _vector_subgroup_by_wx(wx2_arr, wxs_perword_perannot, txs_perword_perannot):
return [[wx2_arr[wx].take(txs, axis=0)
for wx, txs in zip(wx_perword_, txs_perword_)]
for wx_perword_, txs_perword_ in
zip(wxs_perword_perannot, txs_perword_perannot)]
def _scalar_subgroup_by_wx(wx2_scalar, wxs_perword_perannot):
return [[wx2_scalar[wx] for wx in wxs] for wxs in wxs_perword_perannot]
subgrouped_drvecs = _vector_subgroup_by_wx(wx2_drvecs, wxs_perword_perannot, txs_perword_perannot)
subgrouped_dmaws = _vector_subgroup_by_wx(wx2_dmaws, wxs_perword_perannot, txs_perword_perannot)
# If we aren't using dmaws replace it with an infinite None iterator
#subgrouped_dmaws = iter(lambda: None, 1)
subgrouped_dflags = _vector_subgroup_by_wx(wx2_dflags, wxs_perword_perannot, txs_perword_perannot)
#subgrouped_dflags = iter(lambda: None, 1)
subgrouped_idfs = _scalar_subgroup_by_wx(wx2_idf, wxs_perword_perannot)
if verbose_:
progiter = ut.ProgressIter(lbl='[smk_index.sccw] SCCW Sum (over daid): ',
total=len(unique_aids), freq=10, with_time=WITH_TOTALTIME)
else:
progiter = ut.identity
if ut.DEBUG2:
from ibeis.algo.hots.smk import smk_debug
smk_debug.check_data_smksumm(subgrouped_idfs, subgrouped_drvecs)
sccw_list = [
smk_scoring.sccw_summation(rvecs_list, flags_list, idf_list, maws_list, smk_alpha, smk_thresh)
for rvecs_list, flags_list, maws_list, idf_list in
progiter(zip(subgrouped_drvecs, subgrouped_dflags, subgrouped_dmaws, subgrouped_idfs))
]
daid2_sccw = dict(zip(unique_aids, sccw_list))
if verbose_:
print('[smk_index.sccw] L___ End Compute Data SCCW\n')
return daid2_sccw
def compute_data_gamma_(idx2_daid, wx2_rvecs, wx2_aids, wx2_idf,
alpha=3, thresh=0):
"""
Computes gamma normalization scalar for the database annotations
Internals step4
>>> 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_idf = wx2_idf
>>> daids = invindex.daids
>>> use_cache = USE_CACHE_GAMMA and False
>>> daid2_gamma = compute_data_gamma_(idx2_daid, wx2_rvecs, wx2_aids, wx2_idf, daids, use_cache=use_cache)
"""
if utool.DEBUG2:
from ibeis.model.hots.smk import smk_debug
smk_debug.rrr()
smk_debug.check_wx2(wx2_rvecs=wx2_rvecs, wx2_aids=wx2_aids)
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 (by word): ', len(wx_sublist),
flushfreq=100, writefreq=50, with_totaltime=True)
# Get list of aids and rvecs w.r.t. words
aids_list = pdh.ensure_values_subset(wx2_aids, wx_sublist)
rvecs_list1 = pdh.ensure_values_subset(wx2_rvecs, wx_sublist)
# Group by daids first and then by word index
daid2_wx2_drvecs = utool.ddict(lambda: utool.ddict(list))
for wx, aids, rvecs in zip(wx_sublist, aids_list, rvecs_list1):
group_aids, groupxs = clustertool.group_indicies(aids)
rvecs_group = clustertool.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 (over daid): ', len(daid2_wx2_drvecs),
flushfreq=100, writefreq=25, with_totaltime=True)
# Get lists w.r.t daids
aid_list = list(daid2_wx2_drvecs.keys())
# list of mappings from words to rvecs foreach daid
# [wx2_aidrvecs_1, ..., wx2_aidrvecs_nDaids,]
_wx2_aidrvecs_list = list(daid2_wx2_drvecs.values())
_aidwxs_iter = (list(wx2_aidrvecs.keys()) for wx2_aidrvecs in _wx2_aidrvecs_list)
aidrvecs_list = [list(wx2_aidrvecs.values()) for wx2_aidrvecs in _wx2_aidrvecs_list]
aididf_list = [[wx2_idf[wx] for wx in aidwxs] for aidwxs in _aidwxs_iter]
#gamma_list = []
if utool.DEBUG2:
try:
for count, (idf_list, rvecs_list) in enumerate(zip(aididf_list, aidrvecs_list)):
assert len(idf_list) == len(rvecs_list), 'one list for each word'
#gamma = smk_core.gamma_summation2(rvecs_list, idf_list, alpha, thresh)
except Exception as ex:
utool.printex(ex)
utool.embed()
raise
gamma_list = [smk_core.gamma_summation2(rvecs_list, idf_list, alpha, thresh)
for idf_list, rvecs_list in zip(aididf_list, aidrvecs_list)]
if WITH_PANDAS:
daid2_gamma = pdh.IntSeries(gamma_list, index=aid_list, name='gamma')
else:
daid2_gamma = dict(zip(aid_list, gamma_list))
if utool.VERBOSE:
end2_()
return daid2_gamma
def compute_data_gamma_(idx2_daid,
wx2_rvecs,
wx2_aids,
wx2_idf,
alpha=3,
thresh=0):
"""
Computes gamma normalization scalar for the database annotations
Internals step4
>>> 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_idf = wx2_idf
>>> daids = invindex.daids
>>> use_cache = USE_CACHE_GAMMA and False
>>> daid2_gamma = compute_data_gamma_(idx2_daid, wx2_rvecs, wx2_aids, wx2_idf, daids, use_cache=use_cache)
"""
if utool.DEBUG2:
from ibeis.model.hots.smk import smk_debug
smk_debug.rrr()
smk_debug.check_wx2(wx2_rvecs=wx2_rvecs, wx2_aids=wx2_aids)
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 (by word): ',
len(wx_sublist),
flushfreq=100,
writefreq=50,
with_totaltime=True)
# Get list of aids and rvecs w.r.t. words
aids_list = pdh.ensure_values_subset(wx2_aids, wx_sublist)
rvecs_list1 = pdh.ensure_values_subset(wx2_rvecs, wx_sublist)
# Group by daids first and then by word index
daid2_wx2_drvecs = utool.ddict(lambda: utool.ddict(list))
for wx, aids, rvecs in zip(wx_sublist, aids_list, rvecs_list1):
group_aids, groupxs = clustertool.group_indicies(aids)
rvecs_group = clustertool.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 (over daid): ',
len(daid2_wx2_drvecs),
flushfreq=100,
writefreq=25,
with_totaltime=True)
# Get lists w.r.t daids
aid_list = list(daid2_wx2_drvecs.keys())
# list of mappings from words to rvecs foreach daid
# [wx2_aidrvecs_1, ..., wx2_aidrvecs_nDaids,]
_wx2_aidrvecs_list = list(daid2_wx2_drvecs.values())
_aidwxs_iter = (list(wx2_aidrvecs.keys())
for wx2_aidrvecs in _wx2_aidrvecs_list)
aidrvecs_list = [
list(wx2_aidrvecs.values()) for wx2_aidrvecs in _wx2_aidrvecs_list
]
aididf_list = [[wx2_idf[wx] for wx in aidwxs] for aidwxs in _aidwxs_iter]
#gamma_list = []
if utool.DEBUG2:
try:
for count, (idf_list, rvecs_list) in enumerate(
zip(aididf_list, aidrvecs_list)):
assert len(idf_list) == len(
rvecs_list), 'one list for each word'
#gamma = smk_core.gamma_summation2(rvecs_list, idf_list, alpha, thresh)
except Exception as ex:
utool.printex(ex)
utool.embed()
raise
gamma_list = [
smk_core.gamma_summation2(rvecs_list, idf_list, alpha, thresh)
for idf_list, rvecs_list in zip(aididf_list, aidrvecs_list)
]
if WITH_PANDAS:
daid2_gamma = pdh.IntSeries(gamma_list, index=aid_list, name='gamma')
else:
daid2_gamma = dict(zip(aid_list, gamma_list))
if utool.VERBOSE:
end2_()
return daid2_gamma