def assign_to_words_(wordflann, words, idx2_vec, nAssign, massign_alpha,
massign_sigma, massign_equal_weights):
"""
Assigns descriptor-vectors to nearest word.
Args:
wordflann (FLANN): nearest neighbor index over words
words (ndarray): vocabulary words
idx2_vec (ndarray): descriptors to assign
nAssign (int): number of words to assign each descriptor to
massign_alpha (float): multiple-assignment ratio threshold
massign_sigma (float): multiple-assignment gaussian variance
massign_equal_weights (bool): assign equal weight to all multiassigned words
Returns:
tuple: inverted index, multi-assigned weights, and forward index
formated as::
* wx2_idxs - word index -> vector indexes
* wx2_maws - word index -> multi-assignment weights
* idf2_wxs - vector index -> assigned word indexes
Example:
>>> # SLOW_DOCTEST
>>> from ibeis.algo.hots.smk.smk_index import * # NOQA
>>> from ibeis.algo.hots.smk import smk_debug
>>> ibs, annots_df, daids, qaids, invindex, qreq_ = smk_debug.testdata_raw_internals0()
>>> words = invindex.words
>>> wordflann = invindex.wordflann
>>> idx2_vec = invindex.idx2_dvec
>>> nAssign = qreq_.qparams.nAssign
>>> massign_alpha = qreq_.qparams.massign_alpha
>>> massign_sigma = qreq_.qparams.massign_sigma
>>> massign_equal_weights = qreq_.qparams.massign_equal_weights
>>> _dbargs = (wordflann, words, idx2_vec, nAssign, massign_alpha, massign_sigma, massign_equal_weights)
>>> wx2_idxs, wx2_maws, idx2_wxs = assign_to_words_(*_dbargs)
"""
if ut.VERBOSE:
print('[smk_index.assign] +--- Start Assign vecs to words.')
print('[smk_index.assign] * nAssign=%r' % nAssign)
if not ut.QUIET:
print('[smk_index.assign] assign_to_words_. len(idx2_vec) = %r' % len(idx2_vec))
# Assign each vector to the nearest visual words
assert nAssign > 0, 'cannot assign to 0 neighbors'
try:
_idx2_wx, _idx2_wdist = wordflann.nn_index(idx2_vec, nAssign)
except pyflann.FLANNException as ex:
ut.printex(ex, 'probably misread the cached flann_fpath=%r' % (wordflann.flann_fpath,))
raise
_idx2_wx.shape = (idx2_vec.shape[0], nAssign)
_idx2_wdist.shape = (idx2_vec.shape[0], nAssign)
if nAssign > 1:
idx2_wxs, idx2_maws = compute_multiassign_weights_(
_idx2_wx, _idx2_wdist, massign_alpha, massign_sigma, massign_equal_weights)
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 ut.VERBOSE:
print('[smk_index.assign] L___ End Assign vecs to words.')
return wx2_idxs, wx2_maws, idx2_wxs
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, nAssign, massign_alpha,
massign_sigma, massign_equal_weights):
"""
Assigns descriptor-vectors to nearest word.
Args:
wordflann (FLANN): nearest neighbor index over words
words (ndarray): vocabulary words
idx2_vec (ndarray): descriptors to assign
nAssign (int): number of words to assign each descriptor to
massign_alpha (float): multiple-assignment ratio threshold
massign_sigma (float): multiple-assignment gaussian variance
massign_equal_weights (bool): assign equal weight to all multiassigned words
Returns:
tuple: inverted index, multi-assigned weights, and forward index
formated as::
* wx2_idxs - word index -> vector indexes
* wx2_maws - word index -> multi-assignment weights
* idf2_wxs - vector index -> assigned word indexes
Example:
>>> # SLOW_DOCTEST
>>> from ibeis.algo.hots.smk.smk_index import * # NOQA
>>> from ibeis.algo.hots.smk import smk_debug
>>> ibs, annots_df, daids, qaids, invindex, qreq_ = smk_debug.testdata_raw_internals0()
>>> words = invindex.words
>>> wordflann = invindex.wordflann
>>> idx2_vec = invindex.idx2_dvec
>>> nAssign = qreq_.qparams.nAssign
>>> massign_alpha = qreq_.qparams.massign_alpha
>>> massign_sigma = qreq_.qparams.massign_sigma
>>> massign_equal_weights = qreq_.qparams.massign_equal_weights
>>> _dbargs = (wordflann, words, idx2_vec, nAssign, massign_alpha, massign_sigma, massign_equal_weights)
>>> wx2_idxs, wx2_maws, idx2_wxs = assign_to_words_(*_dbargs)
"""
if ut.VERBOSE:
print('[smk_index.assign] +--- Start Assign vecs to words.')
print('[smk_index.assign] * nAssign=%r' % nAssign)
if not ut.QUIET:
print('[smk_index.assign] assign_to_words_. len(idx2_vec) = %r' % len(idx2_vec))
# Assign each vector to the nearest visual words
assert nAssign > 0, 'cannot assign to 0 neighbors'
try:
_idx2_wx, _idx2_wdist = wordflann.nn_index(idx2_vec, nAssign)
except pyflann.FLANNException as ex:
ut.printex(ex, 'probably misread the cached flann_fpath=%r' % (wordflann.flann_fpath,))
raise
_idx2_wx.shape = (idx2_vec.shape[0], nAssign)
_idx2_wdist.shape = (idx2_vec.shape[0], nAssign)
if nAssign > 1:
idx2_wxs, idx2_maws = compute_multiassign_weights_(
_idx2_wx, _idx2_wdist, massign_alpha, massign_sigma, massign_equal_weights)
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 ut.VERBOSE:
print('[smk_index.assign] L___ End Assign vecs to words.')
return wx2_idxs, wx2_maws, idx2_wxs
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
