def report_partitioning_statistics(new_reduced_joint):
# compute partitioning statistics
import vtool as vt
vals, idxs = vt.group_indices(new_reduced_joint.values.ravel())
#groupsize = list(map(len, idxs))
#groupassigns = ut.unflat_vecmap(new_reduced_joint.assignment, idxs)
all_states = new_reduced_joint._row_labels(asindex=True)
clusterstats = [tuple(sorted(list(ut.dict_hist(a).values())))
for a in all_states]
grouped_vals = ut.group_items(new_reduced_joint.values.ravel(),
clusterstats)
#probs_assigned_to_clustertype = [(
# sorted(np.unique(np.array(b).round(decimals=5)).tolist())[::-1], a)
# for a, b in grouped_vals.items()]
probs_assigned_to_clustertype = [(
ut.dict_hist(np.array(b).round(decimals=5)), a)
for a, b in grouped_vals.items()]
sortx = ut.argsort([max(c[0].keys())
for c in probs_assigned_to_clustertype])
probs_assigned_to_clustertype = ut.take(probs_assigned_to_clustertype, sortx)
# This list of 2-tuples with the first item being the unique
# probabilies that are assigned to a cluster type along with the number
# of times they were assigned. A cluster type is the second item. Every
# number represents how many annotations were assigned to a specific
# label. The length of that list is the number of total labels. For
# all low scores you will see [[{somenum: 1}, {0: 800}], [1, 1, 1, ... 1]]
# indicating that that the assignment of everyone to a different label happend once
# where the probability was somenum and a 800 times where the probability was 0.
#print(sorted([(b, a) for a, b in ut.map_dict_vals(sum, x)]).items())
#z = sorted([(b, a) for a, b in ut.map_dict_vals(sum, grouped_vals).items()])
print(ut.repr2(probs_assigned_to_clustertype, nl=2, precision=2, sorted_=True))
def annot_to_class_feats2(aid, aid2_nid, top=None):
pair_list = []
score_list = []
nexemplar_list = []
for nid in unique_nids:
label = (aid2_nid[aid] == nid)
num_exemplars = nid2_nexemp.get(nid, 0)
if num_exemplars == 0:
continue
params = toy_params[label]
mu, sigma = ut.dict_take(params, ['mu', 'sigma'])
score_ = rng.normal(mu, sigma, size=num_exemplars).max()
score = np.clip(score_, 0, np.inf)
pair_list.append((aid, nid))
score_list.append(score)
nexemplar_list.append(num_exemplars)
rank_list = ut.argsort(score_list, reverse=True)
feat_list = np.array([score_list, rank_list, nexemplar_list]).T
sortx = np.argsort(rank_list)
feat_list = feat_list.take(sortx, axis=0)
pair_list = np.array(pair_list).take(sortx, axis=0)
if top is not None:
feat_list = feat_list[:top]
pair_list = pair_list[0:top]
return pair_list, feat_list
def fix_splits_interaction(ibs):
"""
python -m wbia fix_splits_interaction --show
Example:
>>> # DISABLE_DOCTEST GGR
>>> from wbia.other.dbinfo import * # NOQA
>>> import wbia
>>> dbdir = '/media/danger/GGR/GGR-IBEIS'
>>> dbdir = dbdir if ut.checkpath(dbdir) else ut.truepath('~/lev/media/danger/GGR/GGR-IBEIS')
>>> ibs = wbia.opendb(dbdir=dbdir, allow_newdir=False)
>>> import wbia.guitool as gt
>>> gt.ensure_qtapp()
>>> win = fix_splits_interaction(ibs)
>>> ut.quit_if_noshow()
>>> import wbia.plottool as pt
>>> gt.qtapp_loop(qwin=win)
"""
split_props = {'splitcase', 'photobomb'}
all_annot_groups = ibs._annot_groups(
ibs.group_annots_by_name(ibs.get_valid_aids())[0])
all_has_split = [
len(split_props.intersection(ut.flatten(tags))) > 0
for tags in all_annot_groups.match_tags
]
tosplit_annots = ut.compress(all_annot_groups.annots_list, all_has_split)
tosplit_annots = ut.take(tosplit_annots,
ut.argsort(ut.lmap(len, tosplit_annots)))[::-1]
if ut.get_argflag('--reverse'):
tosplit_annots = tosplit_annots[::-1]
logger.info('len(tosplit_annots) = %r' % (len(tosplit_annots), ))
aids_list = [a.aids for a in tosplit_annots]
from wbia.algo.graph import graph_iden
from wbia.viz import viz_graph2
import wbia.guitool as gt
import wbia.plottool as pt
pt.qt4ensure()
gt.ensure_qtapp()
for aids in ut.InteractiveIter(aids_list):
infr = graph_iden.AnnotInference(ibs, aids)
infr.initialize_graph()
win = viz_graph2.AnnotGraphWidget(infr=infr,
use_image=False,
init_mode='rereview')
win.populate_edge_model()
win.show()
return win
def compute_order(rmi):
"""
Returns order of computation from this input node to the sink
"""
# graph, source, target = rmi.exi_graph, rmi.node, rmi.sink
node_order_ = list(
ut.nx_all_nodes_between(rmi.exi_graph, rmi.node, rmi.sink))
node_rank = ut.nx_dag_node_rank(rmi.exi_graph.reverse(), node_order_)
node_names = list(map(str, node_order_))
# lexsort via names to break ties for consistent ordering
sortx = ut.argsort(node_rank, node_names)[::-1]
# sortx = ut.argsort(node_rank)[::-1]
node_order = ut.take(node_order_, sortx)
return node_order
def test_sharpness():
import ibeis
defaltdb = 'seaturtles'
a = ['default']
ibs = ibeis.opendb(defaultdb=defaltdb)
ibs, qaids, daids = ibeis.testdata_expanded_aids(ibs=ibs, a=a)
from vtool import quality_classifier
contrast_list = [quality_classifier.compute_average_contrast(chip) for chip in ibs.get_annot_chips(qaids)]
sortx = ut.argsort(contrast_list)[::-1]
sharpest_qaids = ut.take(qaids, sortx)
aid = sharpest_qaids[0]
ut.ensure_pylab_qt4()
from ibeis import viz
import plottool as pt
for aid in ut.InteractiveIter(sharpest_qaids):
viz.show_chip(ibs, aid, annot=False, nokpts=True)
pt.update()
def flat_compute_order(inputs):
"""
This is basically the scheduler
TODO:
We need to verify the correctness of this logic. It seems to
not be deterministic between versions of python.
CommandLine:
python -m dtool.input_helpers flat_compute_order
Example:
>>> # xdoctest: +REQUIRES(--fixme)
>>> from wbia.dtool.input_helpers import * # NOQA
>>> from wbia.dtool.example_depcache2 import * # NOQA
>>> depc = testdata_depc4()
>>> inputs = depc['feat'].rootmost_inputs.total_expand()
>>> flat_compute_order = inputs.flat_compute_order()
>>> result = ut.repr2(flat_compute_order)
...
>>> print(result)
[chip[t, t:1, 1:1], probchip[t, t:1, 1:1], feat[t, t:1]]
"""
# Compute the order in which all noes must be evaluated
import networkx as nx # NOQA
ordered_compute_nodes = [
rmi.compute_order() for rmi in inputs.rmi_list
]
flat_node_order_ = ut.unique(ut.flatten(ordered_compute_nodes))
rgraph = inputs.exi_graph.reverse()
toprank = ut.nx_topsort_rank(rgraph, flat_node_order_)
sortx = ut.argsort(toprank)[::-1]
flat_compute_order = ut.take(flat_node_order_, sortx)
# Inputs are pre-computed.
for rmi in inputs.rmi_list:
try:
flat_compute_order.remove(rmi.node)
except ValueError as ex:
ut.printex(ex, 'something is wrong', keys=['rmi.node'])
raise
return flat_compute_order
def report_partitioning_statistics(new_reduced_joint):
# compute partitioning statistics
import vtool as vt
vals, idxs = vt.group_indices(new_reduced_joint.values.ravel())
# groupsize = list(map(len, idxs))
# groupassigns = ut.unflat_vecmap(new_reduced_joint.assignment, idxs)
all_states = new_reduced_joint._row_labels(asindex=True)
clusterstats = [
tuple(sorted(list(ut.dict_hist(a).values()))) for a in all_states
]
grouped_vals = ut.group_items(new_reduced_joint.values.ravel(),
clusterstats)
# probs_assigned_to_clustertype = [(
# sorted(np.unique(np.array(b).round(decimals=5)).tolist())[::-1], a)
# for a, b in grouped_vals.items()]
probs_assigned_to_clustertype = [
(ut.dict_hist(np.array(b).round(decimals=5)), a)
for a, b in grouped_vals.items()
]
sortx = ut.argsort(
[max(c[0].keys()) for c in probs_assigned_to_clustertype])
probs_assigned_to_clustertype = ut.take(probs_assigned_to_clustertype,
sortx)
# This list of 2-tuples with the first item being the unique
# probabilies that are assigned to a cluster type along with the number
# of times they were assigned. A cluster type is the second item. Every
# number represents how many annotations were assigned to a specific
# label. The length of that list is the number of total labels. For
# all low scores you will see [[{somenum: 1}, {0: 800}], [1, 1, 1, ... 1]]
# indicating that that the assignment of everyone to a different label happend once
# where the probability was somenum and a 800 times where the probability was 0.
# logger.info(sorted([(b, a) for a, b in ut.map_dict_vals(sum, x)]).items())
# z = sorted([(b, a) for a, b in ut.map_dict_vals(sum, grouped_vals).items()])
logger.info(
ut.repr2(probs_assigned_to_clustertype,
nl=2,
precision=2,
sorted_=True))
def test_visualize_vocab_interact():
"""
python -m ibeis.new_annots --exec-test_visualize_vocab_interact --show
Example:
>>> from ibeis.new_annots import * # NOQA
>>> test_visualize_vocab_interact()
>>> ut.show_if_requested()
"""
import plottool as pt
pt.qt4ensure()
ibs, aid_list, vocab = testdata_vocab()
#aid_list = aid_list[0:1]
fstack = StackedFeatures(ibs, aid_list)
nAssign = 2
invassign = fstack.inverted_assignment(vocab, nAssign)
sortx = ut.argsort(invassign.num_list)[::-1]
wx_list = ut.take(invassign.wx_list, sortx)
wx = wx_list[0]
fnum = 1
for wx in ut.InteractiveIter(wx_list):
visualize_vocab_word(ibs, invassign, wx, fnum)
def test_visualize_vocab_interact():
"""
python -m ibeis.new_annots --exec-test_visualize_vocab_interact --show
Example:
>>> from ibeis.new_annots import * # NOQA
>>> test_visualize_vocab_interact()
>>> ut.show_if_requested()
"""
import plottool as pt
pt.qt4ensure()
ibs, aid_list, vocab = testdata_vocab()
#aid_list = aid_list[0:1]
fstack = StackedFeatures(ibs, aid_list)
nAssign = 2
invassign = fstack.inverted_assignment(vocab, nAssign)
sortx = ut.argsort(invassign.num_list)[::-1]
wx_list = ut.take(invassign.wx_list, sortx)
wx = wx_list[0]
fnum = 1
for wx in ut.InteractiveIter(wx_list):
visualize_vocab_word(ibs, invassign, wx, fnum)
def test_sharpness():
import ibeis
defaltdb = 'seaturtles'
a = ['default']
ibs = ibeis.opendb(defaultdb=defaltdb)
ibs, qaids, daids = ibeis.testdata_expanded_aids(ibs=ibs, a=a)
from vtool import quality_classifier
contrast_list = [
quality_classifier.compute_average_contrast(chip)
for chip in ibs.get_annot_chips(qaids)
]
sortx = ut.argsort(contrast_list)[::-1]
sharpest_qaids = ut.take(qaids, sortx)
aid = sharpest_qaids[0]
ut.ensure_pylab_qt4()
from ibeis import viz
import plottool as pt
for aid in ut.InteractiveIter(sharpest_qaids):
viz.show_chip(ibs, aid, annot=False, nokpts=True)
pt.update()
def make_inference(infr):
cm_list = infr.cm_list
unique_nids, prob_names = infr.make_prob_names()
cluster_tuples = infr.make_clusters()
# Make pair list for output
if infr.user_feedback is not None:
keys = list(
zip(infr.user_feedback['aid1'], infr.user_feedback['aid2']))
feedback_lookup = ut.make_index_lookup(keys)
user_feedback = infr.user_feedback
p_bg = 0
user_feedback = ut.map_dict_vals(np.array, infr.user_feedback)
part1 = user_feedback['p_match'] * (1 - user_feedback['p_notcomp'])
part2 = p_bg * user_feedback['p_notcomp']
p_same_list = part1 + part2
else:
feedback_lookup = {}
infr.user_feedback
needs_review_list = []
num_top = 4
for cm, row in zip(cm_list, prob_names):
# Find top scoring names for this chip match in the posterior distribution
idxs = row.argsort()[::-1]
top_idxs = idxs[:num_top]
nids = ut.take(unique_nids, top_idxs)
# Find the matched annotations in the pairwise prior distributions
nidxs = ut.dict_take(cm.nid2_nidx, nids, None)
name_groupxs = ut.take(cm.name_groupxs, ut.filter_Nones(nidxs))
daids_list = ut.take(cm.daid_list, name_groupxs)
for daids in daids_list:
ut.take(cm.score_list, ut.take(cm.daid2_idx, daids))
scores_all = cm.annot_score_list / cm.annot_score_list.sum()
idxs = ut.take(cm.daid2_idx, daids)
scores = scores_all.take(idxs)
raw_scores = cm.score_list.take(idxs)
scorex = scores.argmax()
raw_score = raw_scores[scorex]
daid = daids[scorex]
import scipy.special
# SUPER HACK: these are not probabilities
# TODO: set a and b based on dbsize and param configuration
# python -m plottool.draw_func2 --exec-plot_func --show --range=0,3 --func="lambda x: scipy.special.expit(2 * x - 2)"
#a = 2.0
a = 1.5
b = 2
p_same = scipy.special.expit(b * raw_score - a)
#confidence = scores[scorex]
#p_diff = 1 - p_same
#decision = 'same' if confidence > thresh else 'diff'
#confidence = p_same if confidence > thresh else p_diff
#tup = (cm.qaid, daid, decision, confidence, raw_score)
confidence = (2 * np.abs(0.5 - p_same))**2
#if infr.user_feedback is not None:
# import utool
# utool.embed(
key = (cm.qaid, daid)
fb_idx = feedback_lookup.get(key)
if fb_idx is not None:
confidence = p_same_list[fb_idx]
tup = (cm.qaid, daid, p_same, confidence, raw_score)
needs_review_list.append(tup)
# Sort resulting list by confidence
sortx = ut.argsort(ut.take_column(needs_review_list, 3))
needs_review_list = ut.take(needs_review_list, sortx)
infr.needs_review_list = needs_review_list
infr.cluster_tuples = cluster_tuples
def initialize_graph_and_model(infr):
""" Unused in internal split stuff
pt.qt4ensure()
layout_info = pt.show_nx(graph, as_directed=False, fnum=1,
layoutkw=dict(prog='neato'), use_image=True,
verbose=0)
ax = pt.gca()
pt.zoom_factory()
pt.interactions.PanEvents()
"""
#import networkx as nx
#import itertools
cm_list = infr.cm_list
hack = True
hack = False
if hack:
cm_list = cm_list[:10]
qaid_list = [cm.qaid for cm in cm_list]
daids_list = [cm.daid_list for cm in cm_list]
unique_aids = sorted(ut.list_union(*daids_list + [qaid_list]))
if hack:
unique_aids = sorted(ut.isect(unique_aids, qaid_list))
aid2_aidx = ut.make_index_lookup(unique_aids)
# Construct K-broken graph
edges = []
edge_weights = []
#top = (infr.qreq_.qparams.K + 1) * 2
#top = (infr.qreq_.qparams.K) * 2
top = (infr.qreq_.qparams.K + 2)
for count, cm in enumerate(cm_list):
qidx = aid2_aidx[cm.qaid]
score_list = cm.annot_score_list
sortx = ut.argsort(score_list)[::-1]
score_list = ut.take(score_list, sortx)[:top]
daid_list = ut.take(cm.daid_list, sortx)[:top]
for score, daid in zip(score_list, daid_list):
if daid not in qaid_list:
continue
didx = aid2_aidx[daid]
edge_weights.append(score)
edges.append((qidx, didx))
# make symmetric
directed_edges = dict(zip(edges, edge_weights))
# Find edges that point in both directions
undirected_edges = {}
for (u, v), w in directed_edges.items():
if (v, u) in undirected_edges:
undirected_edges[(v, u)] += w
undirected_edges[(v, u)] /= 2
else:
undirected_edges[(u, v)] = w
edges = list(undirected_edges.keys())
edge_weights = list(undirected_edges.values())
nodes = list(range(len(unique_aids)))
nid_labeling = infr.qreq_.ibs.get_annot_nids(unique_aids)
labeling = ut.rebase_labels(nid_labeling)
import networkx as nx
from ibeis.viz import viz_graph
set_node_attrs = nx.set_node_attributes
set_edge_attrs = nx.set_edge_attributes
# Create match-based graph structure
graph = nx.DiGraph()
graph.add_nodes_from(nodes)
graph.add_edges_from(edges)
# Important properties
nid_list = infr.qreq_.ibs.get_annot_nids(unique_aids)
labeling = ut.rebase_labels(nid_list)
set_node_attrs(graph, 'name_label', dict(zip(nodes, labeling)))
set_edge_attrs(graph, 'weight', dict(zip(edges, edge_weights)))
# Visualization properties
import plottool as pt
ax2_aid = ut.invert_dict(aid2_aidx)
set_node_attrs(graph, 'aid', ax2_aid)
viz_graph.ensure_node_images(infr.qreq_.ibs, graph)
set_node_attrs(graph, 'framewidth', dict(zip(nodes,
[3.0] * len(nodes))))
set_node_attrs(graph, 'framecolor',
dict(zip(nodes, [pt.DARK_BLUE] * len(nodes))))
ut.color_nodes(graph, labelattr='name_label')
edge_colors = pt.scores_to_color(np.array(edge_weights),
cmap_='viridis')
#import utool
#utool.embed()
#edge_colors = [pt.color_funcs.ensure_base255(color) for color in edge_colors]
#print('edge_colors = %r' % (edge_colors,))
set_edge_attrs(graph, 'color', dict(zip(edges, edge_colors)))
# Build inference model
from ibeis.algo.hots import graph_iden
#graph_iden.rrr()
model = graph_iden.InfrModel(graph)
#model = graph_iden.InfrModel(len(nodes), edges, edge_weights, labeling=labeling)
infr.model = model
def make_inference(infr):
cm_list = infr.cm_list
unique_nids, prob_names = infr.make_prob_names()
cluster_tuples = infr.make_clusters()
# Make pair list for output
if infr.user_feedback is not None:
keys = list(zip(infr.user_feedback['aid1'], infr.user_feedback['aid2']))
feedback_lookup = ut.make_index_lookup(keys)
user_feedback = infr.user_feedback
p_bg = 0
user_feedback = ut.map_dict_vals(np.array, infr.user_feedback)
part1 = user_feedback['p_match'] * (1 - user_feedback['p_notcomp'])
part2 = p_bg * user_feedback['p_notcomp']
p_same_list = part1 + part2
else:
feedback_lookup = {}
infr.user_feedback
needs_review_list = []
num_top = 4
for cm, row in zip(cm_list, prob_names):
# Find top scoring names for this chip match in the posterior distribution
idxs = row.argsort()[::-1]
top_idxs = idxs[:num_top]
nids = ut.take(unique_nids, top_idxs)
# Find the matched annotations in the pairwise prior distributions
nidxs = ut.dict_take(cm.nid2_nidx, nids, None)
name_groupxs = ut.take(cm.name_groupxs, ut.filter_Nones(nidxs))
daids_list = ut.take(cm.daid_list, name_groupxs)
for daids in daids_list:
ut.take(cm.score_list, ut.take(cm.daid2_idx, daids))
scores_all = cm.annot_score_list / cm.annot_score_list.sum()
idxs = ut.take(cm.daid2_idx, daids)
scores = scores_all.take(idxs)
raw_scores = cm.score_list.take(idxs)
scorex = scores.argmax()
raw_score = raw_scores[scorex]
daid = daids[scorex]
import scipy.special
# SUPER HACK: these are not probabilities
# TODO: set a and b based on dbsize and param configuration
# python -m plottool.draw_func2 --exec-plot_func --show --range=0,3 --func="lambda x: scipy.special.expit(2 * x - 2)"
#a = 2.0
a = 1.5
b = 2
p_same = scipy.special.expit(b * raw_score - a)
#confidence = scores[scorex]
#p_diff = 1 - p_same
#decision = 'same' if confidence > thresh else 'diff'
#confidence = p_same if confidence > thresh else p_diff
#tup = (cm.qaid, daid, decision, confidence, raw_score)
confidence = (2 * np.abs(0.5 - p_same)) ** 2
#if infr.user_feedback is not None:
# import utool
# utool.embed(
key = (cm.qaid, daid)
fb_idx = feedback_lookup.get(key)
if fb_idx is not None:
confidence = p_same_list[fb_idx]
tup = (cm.qaid, daid, p_same, confidence, raw_score)
needs_review_list.append(tup)
# Sort resulting list by confidence
sortx = ut.argsort(ut.take_column(needs_review_list, 3))
needs_review_list = ut.take(needs_review_list, sortx)
infr.needs_review_list = needs_review_list
infr.cluster_tuples = cluster_tuples
def initialize_graph_and_model(infr):
""" Unused in internal split stuff
pt.qt4ensure()
layout_info = pt.show_nx(graph, as_directed=False, fnum=1,
layoutkw=dict(prog='neato'), use_image=True,
verbose=0)
ax = pt.gca()
pt.zoom_factory()
pt.interactions.PanEvents()
"""
#import networkx as nx
#import itertools
cm_list = infr.cm_list
hack = True
hack = False
if hack:
cm_list = cm_list[:10]
qaid_list = [cm.qaid for cm in cm_list]
daids_list = [cm.daid_list for cm in cm_list]
unique_aids = sorted(ut.list_union(*daids_list + [qaid_list]))
if hack:
unique_aids = sorted(ut.isect(unique_aids, qaid_list))
aid2_aidx = ut.make_index_lookup(unique_aids)
# Construct K-broken graph
edges = []
edge_weights = []
#top = (infr.qreq_.qparams.K + 1) * 2
#top = (infr.qreq_.qparams.K) * 2
top = (infr.qreq_.qparams.K + 2)
for count, cm in enumerate(cm_list):
qidx = aid2_aidx[cm.qaid]
score_list = cm.annot_score_list
sortx = ut.argsort(score_list)[::-1]
score_list = ut.take(score_list, sortx)[:top]
daid_list = ut.take(cm.daid_list, sortx)[:top]
for score, daid in zip(score_list, daid_list):
if daid not in qaid_list:
continue
didx = aid2_aidx[daid]
edge_weights.append(score)
edges.append((qidx, didx))
# make symmetric
directed_edges = dict(zip(edges, edge_weights))
# Find edges that point in both directions
undirected_edges = {}
for (u, v), w in directed_edges.items():
if (v, u) in undirected_edges:
undirected_edges[(v, u)] += w
undirected_edges[(v, u)] /= 2
else:
undirected_edges[(u, v)] = w
edges = list(undirected_edges.keys())
edge_weights = list(undirected_edges.values())
nodes = list(range(len(unique_aids)))
nid_labeling = infr.qreq_.ibs.get_annot_nids(unique_aids)
labeling = ut.rebase_labels(nid_labeling)
import networkx as nx
from ibeis.viz import viz_graph
set_node_attrs = nx.set_node_attributes
set_edge_attrs = nx.set_edge_attributes
# Create match-based graph structure
graph = nx.DiGraph()
graph.add_nodes_from(nodes)
graph.add_edges_from(edges)
# Important properties
nid_list = infr.qreq_.ibs.get_annot_nids(unique_aids)
labeling = ut.rebase_labels(nid_list)
set_node_attrs(graph, 'name_label', dict(zip(nodes, labeling)))
set_edge_attrs(graph, 'weight', dict(zip(edges, edge_weights)))
# Visualization properties
import plottool as pt
ax2_aid = ut.invert_dict(aid2_aidx)
set_node_attrs(graph, 'aid', ax2_aid)
viz_graph.ensure_node_images(infr.qreq_.ibs, graph)
set_node_attrs(graph, 'framewidth', dict(zip(nodes, [3.0] * len(nodes))))
set_node_attrs(graph, 'framecolor', dict(zip(nodes, [pt.DARK_BLUE] * len(nodes))))
ut.color_nodes(graph, labelattr='name_label')
edge_colors = pt.scores_to_color(np.array(edge_weights), cmap_='viridis')
#import utool
#utool.embed()
#edge_colors = [pt.color_funcs.ensure_base255(color) for color in edge_colors]
#print('edge_colors = %r' % (edge_colors,))
set_edge_attrs(graph, 'color', dict(zip(edges, edge_colors)))
# Build inference model
from ibeis.algo.hots import graph_iden
#graph_iden.rrr()
model = graph_iden.InfrModel(graph)
#model = graph_iden.InfrModel(len(nodes), edges, edge_weights, labeling=labeling)
infr.model = model
