def execute_and_save(qreq_miss):
# Iterate over vsone queries in chunks.
total_chunks = ut.get_num_chunks(len(qreq_miss.qaids), qreq_miss.chunksize)
qaid_chunk_iter = ut.ichunks(qreq_miss.qaids, qreq_miss.chunksize)
_prog = ut.ProgPartial(
length=total_chunks,
freq=1,
label='[mc5] query chunk: ',
prog_hook=qreq_miss.prog_hook,
bs=False,
)
qaid_chunk_iter = iter(_prog(qaid_chunk_iter))
qaid_to_cm = {}
for qaids in qaid_chunk_iter:
sub_qreq = qreq_miss.shallowcopy(qaids=qaids)
cm_batch = sub_qreq.execute_pipeline()
assert len(cm_batch) == len(qaids), 'bad alignment'
assert all([qaid == cm.qaid for qaid, cm in zip(qaids, cm_batch)])
# TODO: we already computed the fpaths
# should be able to pass them in
fpath_list = sub_qreq.get_chipmatch_fpaths(qaids)
_prog = ut.ProgPartial(
length=len(cm_batch),
adjust=True,
freq=1,
label='saving chip matches',
bs=True,
)
for cm, fpath in _prog(zip(cm_batch, fpath_list)):
cm.save_to_fpath(fpath, verbose=False)
qaid_to_cm.update({cm.qaid: cm for cm in cm_batch})
return qaid_to_cm
def print_priors(model, ignore_ttypes=[], title='Priors', color='blue'):
ut.colorprint('\n --- %s ---' % (title, ), color=color)
for ttype, cpds in model.ttype2_cpds.items():
if ttype not in ignore_ttypes:
for fs_ in ut.ichunks(cpds, 4):
ut.colorprint(ut.hz_str([f._cpdstr('psql') for f in fs_]),
color)
def write_dirty_aids(ibs, dirty_probchip_fpath_list, dirty_aids, config2_,
species):
if config2_ is None:
fw_detector = ibs.cfg.featweight_cfg.fw_detector
else:
fw_detector = config2_.get('fw_detector')
if fw_detector == 'rf':
(
extramargin_fpath_list,
probchip_extramargin_fpath_list,
halfoffset_cs_list,
) = compute_extramargin_detectchip(ibs,
dirty_aids,
config2_=config2_,
species=species,
FACTOR=4)
#dirty_cfpath_list = ibs.get_annot_chip_fpath(dirty_aids, ensure=True, config2_=config2_)
config = {
'scale_list': [1.0],
'output_gpath_list': probchip_extramargin_fpath_list,
'mode': 1,
}
probchip_generator = randomforest.detect_gpath_list_with_species(
ibs, extramargin_fpath_list, species, **config)
# Evalutate genrator until completion
ut.evaluate_generator(probchip_generator)
extramargin_mask_gen = (vt.imread(fpath, grayscale=True)
for fpath in probchip_extramargin_fpath_list)
# Crop the extra margin off of the new probchips
_iter = zip(dirty_probchip_fpath_list, extramargin_mask_gen,
halfoffset_cs_list)
for (probchip_fpath, extramargin_probchip, halfmargin) in _iter:
half_w, half_h = halfmargin
probchip = extramargin_probchip[half_h:-half_h, half_w:-half_w]
vt.imwrite(probchip_fpath, probchip)
elif fw_detector == 'cnn':
# dont use extrmargin here (for now)
chip_fpath_list = ibs.get_annot_chip_fpath(dirty_aids,
config2_=config2_)
mask_gen = ibs.generate_species_background_mask(
chip_fpath_list, species)
_iter = zip(dirty_probchip_fpath_list, mask_gen)
for chunk in ut.ichunks(_iter, 64):
for probchip_fpath, probchip in ut.ProgressIter(
chunk,
lbl='write probchip chunk',
adjust=True,
time_thresh=30.0):
probchip = postprocess_mask(probchip)
vt.imwrite(probchip_fpath, probchip)
else:
raise NotImplementedError('bad fw_detector=%r' % (fw_detector, ))
def print_factors(model, factor_list):
if hasattr(model, 'var2_cpd'):
semtypes = [model.var2_cpd[f.variables[0]].ttype for f in factor_list]
else:
semtypes = [0] * len(factor_list)
for type_, factors in ut.group_items(factor_list, semtypes).items():
logger.info('Result Factors (%r)' % (type_, ))
factors = ut.sortedby(factors, [f.variables[0] for f in factors])
for fs_ in ut.ichunks(factors, 4):
ut.colorprint(ut.hz_str([f._str('phi', 'psql') for f in fs_]),
'yellow')
def print_factors(model, factor_list):
if hasattr(model, 'var2_cpd'):
semtypes = [model.var2_cpd[f.variables[0]].ttype
for f in factor_list]
else:
semtypes = [0] * len(factor_list)
for type_, factors in ut.group_items(factor_list, semtypes).items():
print('Result Factors (%r)' % (type_,))
factors = ut.sortedby(factors, [f.variables[0] for f in factors])
for fs_ in ut.ichunks(factors, 4):
ut.colorprint(ut.hz_str([f._str('phi', 'psql') for f in fs_]),
'yellow')
def execute_query2(ibs, qreq_, verbose, save_qcache, batch_size=None):
"""
Breaks up query request into several subrequests
to process "more efficiently" and safer as well.
"""
qreq_.lazy_preload(verbose=verbose and ut.NOT_QUIET)
all_qaids = qreq_.qaids
print('len(missed_qaids) = %r' % (len(all_qaids), ))
qaid2_cm = {}
# vsone must have a chunksize of 1
if batch_size is None:
if HOTS_BATCH_SIZE is None:
hots_batch_size = ibs.cfg.other_cfg.hots_batch_size
else:
hots_batch_size = HOTS_BATCH_SIZE
else:
hots_batch_size = batch_size
chunksize = 1 if qreq_.qparams.vsone else hots_batch_size
# Iterate over vsone queries in chunks.
# This minimizes lost computation if a qreq_ crashes
nTotalChunks = ut.get_nTotalChunks(len(all_qaids), chunksize)
qaid_chunk_iter = ut.ichunks(all_qaids, chunksize)
_qreq_iter = (qreq_.shallowcopy(qaids=qaids) for qaids in qaid_chunk_iter)
sub_qreq_iter = ut.ProgressIter(_qreq_iter,
nTotal=nTotalChunks,
freq=1,
lbl='[mc4] query chunk: ',
prog_hook=qreq_.prog_hook)
for sub_qreq_ in sub_qreq_iter:
if ut.VERBOSE:
print('Generating vsmany chunk')
sub_cm_list = pipeline.request_ibeis_query_L0(ibs,
sub_qreq_,
verbose=verbose)
assert len(sub_qreq_.qaids) == len(sub_cm_list), 'not aligned'
assert all([
qaid == cm.qaid for qaid, cm in zip(sub_qreq_.qaids, sub_cm_list)
]), 'not corresonding'
if save_qcache:
fpath_list = qreq_.get_chipmatch_fpaths(sub_qreq_.qaids)
_iter = zip(sub_cm_list, fpath_list)
_iter = ut.ProgressIter(_iter,
nTotal=len(sub_cm_list),
lbl='saving chip matches',
adjust=True,
freq=1)
for cm, fpath in _iter:
cm.save_to_fpath(fpath, verbose=False)
else:
if ut.VERBOSE:
print('[mc4] not saving vsmany chunk')
qaid2_cm.update({cm.qaid: cm for cm in sub_cm_list})
return qaid2_cm
def execute_query2(ibs, qreq_, verbose, save_qcache, batch_size=None):
"""
Breaks up query request into several subrequests
to process "more efficiently" and safer as well.
"""
qreq_.lazy_preload(verbose=verbose and ut.NOT_QUIET)
all_qaids = qreq_.get_external_qaids()
print('len(missed_qaids) = %r' % (len(all_qaids),))
qaid2_cm = {}
# vsone must have a chunksize of 1
if batch_size is None:
if HOTS_BATCH_SIZE is None:
hots_batch_size = ibs.cfg.other_cfg.hots_batch_size
else:
hots_batch_size = HOTS_BATCH_SIZE
else:
hots_batch_size = batch_size
chunksize = 1 if qreq_.qparams.vsone else hots_batch_size
# Iterate over vsone queries in chunks. This ensures that we dont lose
# too much time if a qreq_ crashes after the 2000th nn index.
nTotalChunks = ut.get_nTotalChunks(len(all_qaids), chunksize)
qaid_chunk_iter = ut.ichunks(all_qaids, chunksize)
_qreq_iter = (
qreq_.shallowcopy(qaids=qaids)
for qaids in qaid_chunk_iter
)
sub_qreq_iter = ut.ProgressIter(
_qreq_iter, nTotal=nTotalChunks, freq=1,
lbl='[mc4] query chunk: ',
prog_hook=qreq_.prog_hook)
for sub_qreq_ in sub_qreq_iter:
if ut.VERBOSE:
print('Generating vsmany chunk')
sub_cm_list = pipeline.request_ibeis_query_L0(
ibs, sub_qreq_, verbose=verbose)
assert len(sub_qreq_.get_external_qaids()) == len(sub_cm_list)
assert all([qaid == cm.qaid for qaid, cm in zip(sub_qreq_.get_external_qaids(), sub_cm_list)])
if save_qcache:
fpath_list = qreq_.get_chipmatch_fpaths(sub_qreq_.get_external_qaids())
_iter = zip(sub_cm_list, fpath_list)
_iter = ut.ProgressIter(_iter, nTotal=len(sub_cm_list),
lbl='saving chip matches', adjust=True, freq=1)
for cm, fpath in _iter:
cm.save_to_fpath(fpath, verbose=False)
else:
if ut.VERBOSE:
print('[mc4] not saving vsmany chunk')
qaid2_cm.update({cm.qaid: cm for cm in sub_cm_list})
return qaid2_cm
def write_dirty_aids(ibs, dirty_probchip_fpath_list, dirty_aids, config2_, species):
if config2_ is None:
featweight_detector = ibs.cfg.featweight_cfg.featweight_detector
else:
featweight_detector = config2_.get('featweight_detector')
if featweight_detector == 'rf':
(extramargin_fpath_list,
probchip_extramargin_fpath_list,
halfoffset_cs_list,
) = compute_extramargin_detectchip(
ibs, dirty_aids, config2_=config2_, species=species, FACTOR=4)
#dirty_cfpath_list = ibs.get_annot_chip_fpath(dirty_aids, ensure=True, config2_=config2_)
config = {
'scale_list': [1.0],
'output_gpath_list': probchip_extramargin_fpath_list,
'mode': 1,
}
probchip_generator = randomforest.detect_gpath_list_with_species(
ibs, extramargin_fpath_list, species, **config)
# Evalutate genrator until completion
ut.evaluate_generator(probchip_generator)
extramargin_mask_gen = (
vt.imread(fpath, grayscale=True) for fpath in probchip_extramargin_fpath_list
)
# Crop the extra margin off of the new probchips
_iter = zip(dirty_probchip_fpath_list,
extramargin_mask_gen,
halfoffset_cs_list)
for (probchip_fpath, extramargin_probchip, halfmargin) in _iter:
half_w, half_h = halfmargin
probchip = extramargin_probchip[half_h:-half_h, half_w:-half_w]
vt.imwrite(probchip_fpath, probchip)
elif featweight_detector == 'cnn':
# dont use extrmargin here (for now)
chip_fpath_list = ibs.get_annot_chip_fpath(dirty_aids, config2_=config2_)
mask_gen = ibs.generate_species_background_mask(chip_fpath_list, species)
_iter = zip(dirty_probchip_fpath_list, mask_gen)
for chunk in ut.ichunks(_iter, 64):
for probchip_fpath, probchip in ut.ProgressIter(chunk, lbl='write probchip chunk', adjust=True, time_thresh=30.0):
probchip = postprocess_mask(probchip)
vt.imwrite(probchip_fpath, probchip)
else:
raise NotImplementedError('bad featweight_detector=%r' % (featweight_detector,))
def testshow_colors(rgb_list, gray=ut.get_argflag('--gray')):
"""
colors = ['r', 'b', 'purple', 'orange', 'deeppink', 'g']
colors = list(mcolors.CSS4_COLORS.keys())
CommandLine:
python -m wbia.plottool.color_funcs testshow_colors --show
Example:
>>> # ENABLE_DOCTEST
>>> from wbia.plottool.color_funcs import * # NOQA
>>> colors = ut.get_argval('--colors', type_=list, default=['k', 'r'])
>>> ut.quit_if_noshow()
>>> rgb_list = ut.emap(ensure_base01, colors)
>>> testshow_colors(rgb_list)
>>> import wbia.plottool as pt
>>> pt.show_if_requested()
"""
import wbia.plottool as pt
import vtool as vt
block = np.zeros((5, 5, 3))
block_list = [block + color[0:3] for color in rgb_list]
# print(ut.repr2(block_list))
# print(ut.repr2(rgb_list))
chunks = ut.ichunks(block_list, 10)
stacked_chunk = []
for chunk in chunks:
stacked_chunk.append(vt.stack_image_list(chunk, vert=False))
stacked_block = vt.stack_image_list(stacked_chunk, vert=True)
# convert to bgr
stacked_block = stacked_block[:, :, ::-1]
uint8_img = (255 * stacked_block).astype(np.uint8)
if gray:
import cv2
uint8_img = cv2.cvtColor(uint8_img, cv2.COLOR_RGB2GRAY)
pt.imshow(uint8_img)
def execute_query2(qreq_,
verbose,
save_qcache,
batch_size=None,
use_supercache=False):
"""
Breaks up query request into several subrequests
to process "more efficiently" and safer as well.
"""
if qreq_.prog_hook is not None:
preload_hook, query_hook = qreq_.prog_hook.subdivide(
spacing=[0, 0.15, 0.8])
preload_hook(0, lbl='preloading')
qreq_.prog_hook = query_hook
else:
preload_hook = None
# Load features / weights for all annotations
qreq_.lazy_preload(prog_hook=preload_hook,
verbose=verbose and ut.NOT_QUIET)
all_qaids = qreq_.qaids
logger.info('len(missed_qaids) = %r' % (len(all_qaids), ))
qaid2_cm = {}
# vsone must have a chunksize of 1
if batch_size is None:
if HOTS_BATCH_SIZE is None:
hots_batch_size = qreq_.ibs.cfg.other_cfg.hots_batch_size
# hots_batch_size = 256
else:
hots_batch_size = HOTS_BATCH_SIZE
else:
hots_batch_size = batch_size
chunksize = 1 if qreq_.qparams.vsone else hots_batch_size
# Iterate over vsone queries in chunks.
n_total_chunks = ut.get_num_chunks(len(all_qaids), chunksize)
qaid_chunk_iter = ut.ichunks(all_qaids, chunksize)
_qreq_iter = (qreq_.shallowcopy(qaids=qaids) for qaids in qaid_chunk_iter)
sub_qreq_iter = ut.ProgIter(
_qreq_iter,
length=n_total_chunks,
freq=1,
label='[mc4] query chunk: ',
prog_hook=qreq_.prog_hook,
)
for sub_qreq_ in sub_qreq_iter:
if ut.VERBOSE:
logger.info('Generating vsmany chunk')
sub_cm_list = pipeline.request_wbia_query_L0(qreq_.ibs,
sub_qreq_,
verbose=verbose)
assert len(sub_qreq_.qaids) == len(sub_cm_list), 'not aligned'
assert all([
qaid == cm.qaid for qaid, cm in zip(sub_qreq_.qaids, sub_cm_list)
]), 'not corresonding'
if save_qcache:
fpath_list = list(
qreq_.get_chipmatch_fpaths(sub_qreq_.qaids,
super_qres_cache=use_supercache))
_iter = zip(sub_cm_list, fpath_list)
_iter = ut.ProgIter(
_iter,
length=len(sub_cm_list),
label='saving chip matches',
adjust=True,
freq=1,
)
for cm, fpath in _iter:
cm.save_to_fpath(fpath, verbose=False)
else:
if ut.VERBOSE:
logger.info('[mc4] not saving vsmany chunk')
qaid2_cm.update({cm.qaid: cm for cm in sub_cm_list})
return qaid2_cm
def draw_twoday_count(ibs, visit_info_list_):
import copy
visit_info_list = copy.deepcopy(visit_info_list_)
aids_day1, aids_day2 = ut.take_column(visit_info_list_, 'aids')
nids_day1, nids_day2 = ut.take_column(visit_info_list_, 'unique_nids')
resight_nids = ut.isect(nids_day1, nids_day2)
if False:
# HACK REMOVE DATA TO MAKE THIS FASTER
num = 20
for info in visit_info_list:
non_resight_nids = list(set(info['unique_nids']) - set(resight_nids))
sample_nids2 = non_resight_nids[0:num] + resight_nids[:num]
info['grouped_aids'] = ut.dict_subset(info['grouped_aids'], sample_nids2)
info['unique_nids'] = sample_nids2
# Build a graph of matches
if False:
debug = False
for info in visit_info_list:
edges = []
grouped_aids = info['grouped_aids']
aids_list = list(grouped_aids.values())
ams_list = ibs.get_annotmatch_rowids_in_cliques(aids_list)
aids1_list = ibs.unflat_map(ibs.get_annotmatch_aid1, ams_list)
aids2_list = ibs.unflat_map(ibs.get_annotmatch_aid2, ams_list)
for ams, aids, aids1, aids2 in zip(ams_list, aids_list, aids1_list, aids2_list):
edge_nodes = set(aids1 + aids2)
##if len(edge_nodes) != len(set(aids)):
# #print('--')
# #print('aids = %r' % (aids,))
# #print('edge_nodes = %r' % (edge_nodes,))
bad_aids = edge_nodes - set(aids)
if len(bad_aids) > 0:
print('bad_aids = %r' % (bad_aids,))
unlinked_aids = set(aids) - edge_nodes
mst_links = list(ut.itertwo(list(unlinked_aids) + list(edge_nodes)[:1]))
bad_aids.add(None)
user_links = [(u, v) for (u, v) in zip(aids1, aids2) if u not in bad_aids and v not in bad_aids]
new_edges = mst_links + user_links
new_edges = [(int(u), int(v)) for u, v in new_edges if u not in bad_aids and v not in bad_aids]
edges += new_edges
info['edges'] = edges
# Add edges between days
grouped_aids1, grouped_aids2 = ut.take_column(visit_info_list, 'grouped_aids')
nids_day1, nids_day2 = ut.take_column(visit_info_list, 'unique_nids')
resight_nids = ut.isect(nids_day1, nids_day2)
resight_aids1 = ut.take(grouped_aids1, resight_nids)
resight_aids2 = ut.take(grouped_aids2, resight_nids)
#resight_aids3 = [list(aids1) + list(aids2) for aids1, aids2 in zip(resight_aids1, resight_aids2)]
ams_list = ibs.get_annotmatch_rowids_between_groups(resight_aids1, resight_aids2)
aids1_list = ibs.unflat_map(ibs.get_annotmatch_aid1, ams_list)
aids2_list = ibs.unflat_map(ibs.get_annotmatch_aid2, ams_list)
between_edges = []
for ams, aids1, aids2, rawaids1, rawaids2 in zip(ams_list, aids1_list, aids2_list, resight_aids1, resight_aids2):
link_aids = aids1 + aids2
rawaids3 = rawaids1 + rawaids2
badaids = ut.setdiff(link_aids, rawaids3)
assert not badaids
user_links = [(int(u), int(v)) for (u, v) in zip(aids1, aids2)
if u is not None and v is not None]
# HACK THIS OFF
user_links = []
if len(user_links) == 0:
# Hack in an edge
between_edges += [(rawaids1[0], rawaids2[0])]
else:
between_edges += user_links
assert np.all(0 == np.diff(np.array(ibs.unflat_map(ibs.get_annot_nids, between_edges)), axis=1))
import plottool_ibeis as pt
import networkx as nx
#pt.qt4ensure()
#len(list(nx.connected_components(graph1)))
#print(ut.graph_info(graph1))
# Layout graph
layoutkw = dict(
prog='neato',
draw_implicit=False, splines='line',
#splines='curved',
#splines='spline',
#sep=10 / 72,
#prog='dot', rankdir='TB',
)
def translate_graph_to_origin(graph):
x, y, w, h = ut.get_graph_bounding_box(graph)
ut.translate_graph(graph, (-x, -y))
def stack_graphs(graph_list, vert=False, pad=None):
graph_list_ = [g.copy() for g in graph_list]
for g in graph_list_:
translate_graph_to_origin(g)
bbox_list = [ut.get_graph_bounding_box(g) for g in graph_list_]
if vert:
dim1 = 3
dim2 = 2
else:
dim1 = 2
dim2 = 3
dim1_list = np.array([bbox[dim1] for bbox in bbox_list])
dim2_list = np.array([bbox[dim2] for bbox in bbox_list])
if pad is None:
pad = np.mean(dim1_list) / 2
offset1_list = ut.cumsum([0] + [d + pad for d in dim1_list[:-1]])
max_dim2 = max(dim2_list)
offset2_list = [(max_dim2 - d2) / 2 for d2 in dim2_list]
if vert:
t_xy_list = [(d2, d1) for d1, d2 in zip(offset1_list, offset2_list)]
else:
t_xy_list = [(d1, d2) for d1, d2 in zip(offset1_list, offset2_list)]
for g, t_xy in zip(graph_list_, t_xy_list):
ut.translate_graph(g, t_xy)
nx.set_node_attributes(g, name='pin', values='true')
new_graph = nx.compose_all(graph_list_)
#pt.show_nx(new_graph, layout='custom', node_labels=False, as_directed=False) # NOQA
return new_graph
# Construct graph
for count, info in enumerate(visit_info_list):
graph = nx.Graph()
edges = [(int(u), int(v)) for u, v in info['edges']
if u is not None and v is not None]
graph.add_edges_from(edges, attr_dict={'zorder': 10})
nx.set_node_attributes(graph, name='zorder', values=20)
# Layout in neato
_ = pt.nx_agraph_layout(graph, inplace=True, **layoutkw) # NOQA
# Extract components and then flatten in nid ordering
ccs = list(nx.connected_components(graph))
root_aids = []
cc_graphs = []
for cc_nodes in ccs:
cc = graph.subgraph(cc_nodes)
try:
root_aids.append(list(ut.nx_source_nodes(cc.to_directed()))[0])
except nx.NetworkXUnfeasible:
root_aids.append(list(cc.nodes())[0])
cc_graphs.append(cc)
root_nids = ibs.get_annot_nids(root_aids)
nid2_graph = dict(zip(root_nids, cc_graphs))
resight_nids_ = set(resight_nids).intersection(set(root_nids))
noresight_nids_ = set(root_nids) - resight_nids_
n_graph_list = ut.take(nid2_graph, sorted(noresight_nids_))
r_graph_list = ut.take(nid2_graph, sorted(resight_nids_))
if len(n_graph_list) > 0:
n_graph = nx.compose_all(n_graph_list)
_ = pt.nx_agraph_layout(n_graph, inplace=True, **layoutkw) # NOQA
n_graphs = [n_graph]
else:
n_graphs = []
r_graphs = [stack_graphs(chunk) for chunk in ut.ichunks(r_graph_list, 100)]
if count == 0:
new_graph = stack_graphs(n_graphs + r_graphs, vert=True)
else:
new_graph = stack_graphs(r_graphs[::-1] + n_graphs, vert=True)
#pt.show_nx(new_graph, layout='custom', node_labels=False, as_directed=False) # NOQA
info['graph'] = new_graph
graph1_, graph2_ = ut.take_column(visit_info_list, 'graph')
if False:
_ = pt.show_nx(graph1_, layout='custom', node_labels=False, as_directed=False) # NOQA
_ = pt.show_nx(graph2_, layout='custom', node_labels=False, as_directed=False) # NOQA
graph_list = [graph1_, graph2_]
twoday_graph = stack_graphs(graph_list, vert=True, pad=None)
nx.set_node_attributes(twoday_graph, name='pin', values='true')
if debug:
ut.nx_delete_None_edge_attr(twoday_graph)
ut.nx_delete_None_node_attr(twoday_graph)
print('twoday_graph(pre) info' + ut.repr3(ut.graph_info(twoday_graph), nl=2))
# Hack, no idea why there are nodes that dont exist here
between_edges_ = [edge for edge in between_edges
if twoday_graph.has_node(edge[0]) and twoday_graph.has_node(edge[1])]
twoday_graph.add_edges_from(between_edges_, attr_dict={'alpha': .2, 'zorder': 0})
ut.nx_ensure_agraph_color(twoday_graph)
layoutkw['splines'] = 'line'
layoutkw['prog'] = 'neato'
agraph = pt.nx_agraph_layout(twoday_graph, inplace=True, return_agraph=True, **layoutkw)[-1] # NOQA
if False:
fpath = ut.truepath('~/ggr_graph.png')
agraph.draw(fpath)
ut.startfile(fpath)
if debug:
print('twoday_graph(post) info' + ut.repr3(ut.graph_info(twoday_graph)))
_ = pt.show_nx(twoday_graph, layout='custom', node_labels=False, as_directed=False) # NOQA
def detect_species_bboxes(src_gpath_list, species, quick=True, use_chunks=False, **detectkw):
"""
Generates bounding boxes for each source image
For each image yeilds a list of bounding boxes
"""
nImgs = len(src_gpath_list)
print('[detect.rf] Begining %s detection' % (species,))
detect_lbl = 'detect %s ' % species
mark_prog, end_prog = utool.progress_func(nImgs, detect_lbl, flush_after=1)
detect_config = _get_detect_config(**detectkw)
detector, forest = _get_detector(species, quick=quick)
detector.set_detect_params(**detect_config)
dst_gpath_list = [splitext(gpath)[0] for gpath in src_gpath_list]
# FIXME: Doing this in a generator may cause unnecessary page-faults
# Maybe there is a better way of doing this, or generating results
# in batch. It could be a utool batch serial process
chunksize = 8
use_chunks_ = use_chunks and nImgs >= chunksize
if use_chunks_:
print('[rf] detect in chunks')
pathtup_iter = zip(src_gpath_list, dst_gpath_list)
for ic, chunk in enumerate(utool.ichunks(pathtup_iter, chunksize)):
src_gpath_list = [tup[0] for tup in chunk]
dst_gpath_list = [tup[1] for tup in chunk]
mark_prog(ic * chunksize)
results_list = detector.detect_many(forest, src_gpath_list, dst_gpath_list)
for results in results_list:
bboxes = [(minx, miny, (maxx - minx), (maxy - miny))
for (centx, centy, minx, miny, maxx, maxy, confidence, supressed)
in results if supressed == 0]
#x_arr = results[:, 2]
#y_arr = results[:, 3]
#w_arr = results[:, 4] - results[:, 2]
#h_arr = results[:, 5] - results[:, 3]
#bboxes = np.hstack((x_arr, y_arr, w_arr, h_arr))
# Unpack unsupressed bounding boxes
confidences = [confidence
for (centx, centy, minx, miny, maxx, maxy, confidence, supressed)
in results if supressed == 0]
if len(results) > 0:
image_confidence = max([float(result[6]) for result in results])
else:
image_confidence = 0.0
yield bboxes, confidences, image_confidence
else:
print('[rf] detect one image at a time')
pathtup_iter = izip(src_gpath_list, dst_gpath_list)
for ix, (src_gpath, dst_gpath) in enumerate(pathtup_iter):
mark_prog(ix)
results = detector.detect(forest, src_gpath, dst_gpath)
bboxes = [(minx, miny, (maxx - minx), (maxy - miny))
for (centx, centy, minx, miny, maxx, maxy, confidence, supressed)
in results if supressed == 0]
confidences = [confidence
for (centx, centy, minx, miny, maxx, maxy, confidence, supressed)
in results if supressed == 0]
if len(results) > 0:
image_confidence = max([float(result[6]) for result in results])
else:
image_confidence = 0.0
yield bboxes, confidences, image_confidence
end_prog()
def detect(
gpath_list,
config_filepath=None,
weight_filepath=None,
classes_filepath=None,
sensitivity=0.0,
verbose=VERBOSE_LN,
flip=False,
batch_size=192,
**kwargs,
):
"""Detect image filepaths with lightnet.
Args:
gpath_list (list of str): the list of image paths that need proposal candidates
Kwargs (optional): refer to the Lightnet documentation for configuration settings
Returns:
iter
"""
# Get correct weight if specified with shorthand
config_url = None
if config_filepath in CONFIG_URL_DICT:
config_url = CONFIG_URL_DICT[config_filepath]
config_filepath = ut.grab_file_url(config_url,
appname='lightnet',
check_hash=True)
# Get correct weights if specified with shorthand
if weight_filepath in CONFIG_URL_DICT:
if weight_filepath is None and config_url is not None:
config_url_ = config_url
else:
config_url_ = CONFIG_URL_DICT[weight_filepath]
weight_url = _parse_weights_from_cfg(config_url_)
weight_filepath = ut.grab_file_url(weight_url,
appname='lightnet',
check_hash=True)
assert exists(config_filepath)
config_filepath = ut.truepath(config_filepath)
assert exists(weight_filepath)
weight_filepath = ut.truepath(weight_filepath)
conf_thresh = sensitivity
nms_thresh = 1.0 # Turn off NMS
params = _create_network(config_filepath, weight_filepath, conf_thresh,
nms_thresh)
# Execute detector for each image
results_list_ = []
for gpath_batch_list in tqdm(list(ut.ichunks(gpath_list, batch_size))):
try:
result_list, img_sizes = _detect(params,
gpath_batch_list,
flip=flip)
except cv2.error:
result_list, img_sizes = [], []
for result, img_size in zip(result_list, img_sizes):
img_w, img_h = img_size
result_list_ = []
for output in list(result):
xtl = int(np.around(float(output.x_top_left)))
ytl = int(np.around(float(output.y_top_left)))
xbr = int(np.around(float(output.x_top_left + output.width)))
ybr = int(np.around(float(output.y_top_left + output.height)))
width = xbr - xtl
height = ybr - ytl
class_ = output.class_label
conf = float(output.confidence)
if flip:
xtl = img_w - xbr
result_dict = {
'xtl': xtl,
'ytl': ytl,
'width': width,
'height': height,
'class': class_,
'confidence': conf,
}
result_list_.append(result_dict)
results_list_.append(result_list_)
if len(results_list_) != len(gpath_list):
raise ValueError('Lightnet did not return valid data')
results_list = zip(gpath_list, results_list_)
return results_list
def ensure_pz_mtest_batchworkflow_test():
r"""
CommandLine:
python -m ibeis.init.sysres --test-ensure_pz_mtest_batchworkflow_test
python -m ibeis.init.sysres --test-ensure_pz_mtest_batchworkflow_test --reset
python -m ibeis.init.sysres --test-ensure_pz_mtest_batchworkflow_test --reset
Example:
>>> # SCRIPT
>>> from ibeis.init.sysres import * # NOQA
>>> ensure_pz_mtest_batchworkflow_test()
"""
import ibeis
ibeis.ensure_pz_mtest()
workdir = ibeis.sysres.get_workdir()
mtest_dbpath = join(workdir, 'PZ_MTEST')
source_dbdir = mtest_dbpath
dest_dbdir = join(workdir, 'PZ_BATCH_WORKFLOW_MTEST')
if ut.get_argflag('--reset'):
ut.delete(dest_dbdir)
if ut.checkpath(dest_dbdir):
return
else:
copy_ibeisdb(source_dbdir, dest_dbdir)
ibs = ibeis.opendb('PZ_BATCH_WORKFLOW_MTEST')
assert len(ibs.get_valid_aids()) == 119
assert len(ibs.get_valid_nids()) == 41
ibs.delete_all_encounters()
aid_list = ibs.get_valid_aids()
unixtime_list = ibs.get_annot_image_unixtimes(aid_list)
untimed_aids = ut.compress(aid_list, [t == -1 for t in unixtime_list])
ibs.get_annot_groundtruth(untimed_aids, aid_list)
aids_list, nid_list = ibs.group_annots_by_name(aid_list)
hourdiffs_list = ibs.get_name_hourdiffs(nid_list)
encounter_aids_list = [[] for _ in range(4)]
encounter_idx = 0
for hourdiffs, aids in zip(hourdiffs_list, aids_list):
#import scipy.spatial.distance as spdist
if len(aids) == 1:
encounter_aids_list[encounter_idx].extend(aids)
encounter_idx = (encounter_idx + 1) % len(encounter_aids_list)
else:
for chunk in list(ut.ichunks(aids, 2)):
encounter_aids_list[encounter_idx].extend(chunk)
encounter_idx = (encounter_idx + 1) % len(encounter_aids_list)
#import vtool as vt
#import networkx as netx
#nodes = list(range(len(aids)))
#edges_pairs = vt.pdist_argsort(hourdiffs)
#edge_weights = -hourdiffs[hourdiffs.argsort()]
#netx_graph = make_netx_graph(edges_pairs, nodes, edge_weights)
#cut_edges = netx.minimum_edge_cut(netx_graph)
#netx_graph.remove_edges_from(cut_edges)
#components = list(netx.connected_components(netx_graph))
#components = ut.sortedby(components, list(map(len, components)), reverse=True)
#print(components)
#encounter_aids_list[0].extend(components[0])
#for compoment in components:
# TODO do max-nway cut
#day_diffs = spdist.squareform(hourdiffs) / 24.0
#print(ut.numpy_str(day_diffs, precision=2, suppress_small=True))
#import itertools
#compare_idxs = [(r, c) for r, c in itertools.product(range(len(aids)), range(len(aids))) if (c > r)]
#print(len(aids))
#def make_netx_graph(edges_pairs, nodes=None, edge_weights=None):
# import networkx as netx
# node_lbls = [('id_', 'int')]
# edge_lbls = [('weight', 'float')]
# edges = [(pair[0], pair[1], weight) for pair, weight in zip(edges_pairs, edge_weights)]
# print('make_netx_graph')
# # Make a graph between the chips
# netx_nodes = [(ntup[0], {key[0]: val for (key, val) in zip(node_lbls, ntup[1:])})
# for ntup in iter(zip(nodes))]
# netx_edges = [(etup[0], etup[1], {key[0]: val for (key, val) in zip(edge_lbls, etup[2:])})
# for etup in iter(edges)]
# netx_graph = netx.Graph()
# netx_graph.add_nodes_from(netx_nodes)
# netx_graph.add_edges_from(netx_edges)
# return netx_graph
# Group into encounters based on old names
gids_list = ibs.unflat_map(ibs.get_annot_image_rowids, encounter_aids_list)
eid_list = ibs.new_encounters_from_images(gids_list) # NOQA
# Remove all names
ibs.delete_annot_nids(aid_list)
def temp_model(num_annots,
num_names,
score_evidence=[],
name_evidence=[],
other_evidence={},
noquery=False,
verbose=None,
**kwargs):
if verbose is None:
verbose = ut.VERBOSE
method = kwargs.pop('method', None)
model = make_name_model(num_annots, num_names, verbose=verbose, **kwargs)
if verbose:
model.print_priors(ignore_ttypes=[MATCH_TTYPE, SCORE_TTYPE])
model, evidence, soft_evidence = update_model_evidence(
model, name_evidence, score_evidence, other_evidence)
if verbose and len(soft_evidence) != 0:
model.print_priors(ignore_ttypes=[MATCH_TTYPE, SCORE_TTYPE],
title='Soft Evidence',
color='green')
# if verbose:
# ut.colorprint('\n --- Soft Evidence ---', 'white')
# for ttype, cpds in model.ttype2_cpds.items():
# if ttype != MATCH_TTYPE:
# for fs_ in ut.ichunks(cpds, 4):
# ut.colorprint(ut.hz_str([f._cpdstr('psql') for f in fs_]),
# 'green')
if verbose:
ut.colorprint('\n --- Inference ---', 'red')
if (len(evidence) > 0 or len(soft_evidence) > 0) and not noquery:
evidence = model._ensure_internal_evidence(evidence)
query_vars = []
query_vars += ut.list_getattr(model.ttype2_cpds[NAME_TTYPE],
'variable')
# query_vars += ut.list_getattr(model.ttype2_cpds[MATCH_TTYPE], 'variable')
query_vars = ut.setdiff(query_vars, evidence.keys())
# query_vars = ut.setdiff(query_vars, soft_evidence.keys())
query_results = cluster_query(model, query_vars, evidence,
soft_evidence, method)
else:
query_results = {}
factor_list = query_results['factor_list']
if verbose:
if verbose:
logger.info('+--------')
semtypes = [model.var2_cpd[f.variables[0]].ttype for f in factor_list]
for type_, factors in ut.group_items(factor_list, semtypes).items():
logger.info('Result Factors (%r)' % (type_, ))
factors = ut.sortedby(factors, [f.variables[0] for f in factors])
for fs_ in ut.ichunks(factors, 4):
ut.colorprint(ut.hz_str([f._str('phi', 'psql') for f in fs_]),
'yellow')
logger.info('MAP assignments')
top_assignments = query_results.get('top_assignments', [])
tmp = []
for lbl, val in top_assignments:
tmp.append('%s : %.4f' % (ut.repr2(lbl), val))
logger.info(ut.align('\n'.join(tmp), ' :'))
logger.info('L_____\n')
showkw = dict(evidence=evidence,
soft_evidence=soft_evidence,
**query_results)
from wbia.algo.hots import pgm_viz
pgm_viz.show_model(model, **showkw)
return (model, evidence, query_results)
def ensure_pz_mtest_batchworkflow_test():
r"""
CommandLine:
python -m ibeis.init.sysres --test-ensure_pz_mtest_batchworkflow_test
python -m ibeis.init.sysres --test-ensure_pz_mtest_batchworkflow_test --reset
python -m ibeis.init.sysres --test-ensure_pz_mtest_batchworkflow_test --reset
Example:
>>> # SCRIPT
>>> from ibeis.init.sysres import * # NOQA
>>> ensure_pz_mtest_batchworkflow_test()
"""
import ibeis
ibeis.ensure_pz_mtest()
workdir = ibeis.sysres.get_workdir()
mtest_dbpath = join(workdir, 'PZ_MTEST')
source_dbdir = mtest_dbpath
dest_dbdir = join(workdir, 'PZ_BATCH_WORKFLOW_MTEST')
if ut.get_argflag('--reset'):
ut.delete(dest_dbdir)
if ut.checkpath(dest_dbdir):
return
else:
copy_ibeisdb(source_dbdir, dest_dbdir)
ibs = ibeis.opendb('PZ_BATCH_WORKFLOW_MTEST')
assert len(ibs.get_valid_aids()) == 119
assert len(ibs.get_valid_nids()) == 41
ibs.delete_all_imagesets()
aid_list = ibs.get_valid_aids()
unixtime_list = ibs.get_annot_image_unixtimes(aid_list)
untimed_aids = ut.compress(aid_list, [t == -1 for t in unixtime_list])
ibs.get_annot_groundtruth(untimed_aids, aid_list)
aids_list, nid_list = ibs.group_annots_by_name(aid_list)
hourdiffs_list = ibs.get_name_hourdiffs(nid_list)
imageset_aids_list = [[] for _ in range(4)]
imageset_idx = 0
for hourdiffs, aids in zip(hourdiffs_list, aids_list):
#import scipy.spatial.distance as spdist
if len(aids) == 1:
imageset_aids_list[imageset_idx].extend(aids)
imageset_idx = (imageset_idx + 1) % len(imageset_aids_list)
else:
for chunk in list(ut.ichunks(aids, 2)):
imageset_aids_list[imageset_idx].extend(chunk)
imageset_idx = (imageset_idx + 1) % len(imageset_aids_list)
#import vtool as vt
#import networkx as netx
#nodes = list(range(len(aids)))
#edges_pairs = vt.pdist_argsort(hourdiffs)
#edge_weights = -hourdiffs[hourdiffs.argsort()]
#netx_graph = make_netx_graph(edges_pairs, nodes, edge_weights)
#cut_edges = netx.minimum_edge_cut(netx_graph)
#netx_graph.remove_edges_from(cut_edges)
#components = list(netx.connected_components(netx_graph))
#components = ut.sortedby(components, list(map(len, components)), reverse=True)
#print(components)
#imageset_aids_list[0].extend(components[0])
#for compoment in components:
# TODO do max-nway cut
#day_diffs = spdist.squareform(hourdiffs) / 24.0
#print(ut.numpy_str(day_diffs, precision=2, suppress_small=True))
#import itertools
#compare_idxs = [(r, c) for r, c in itertools.product(range(len(aids)), range(len(aids))) if (c > r)]
#print(len(aids))
#def make_netx_graph(edges_pairs, nodes=None, edge_weights=None):
# import networkx as netx
# node_lbls = [('id_', 'int')]
# edge_lbls = [('weight', 'float')]
# edges = [(pair[0], pair[1], weight) for pair, weight in zip(edges_pairs, edge_weights)]
# print('make_netx_graph')
# # Make a graph between the chips
# netx_nodes = [(ntup[0], {key[0]: val for (key, val) in zip(node_lbls, ntup[1:])})
# for ntup in iter(zip(nodes))]
# netx_edges = [(etup[0], etup[1], {key[0]: val for (key, val) in zip(edge_lbls, etup[2:])})
# for etup in iter(edges)]
# netx_graph = netx.Graph()
# netx_graph.add_nodes_from(netx_nodes)
# netx_graph.add_edges_from(netx_edges)
# return netx_graph
# Group into imagesets based on old names
gids_list = ibs.unflat_map(ibs.get_annot_image_rowids, imageset_aids_list)
imgsetid_list = ibs.new_imagesets_from_images(gids_list) # NOQA
# Remove all names
ibs.delete_annot_nids(aid_list)
def add_chip_feat(ibs, chip_rowid_list, config2_=None, verbose=not ut.QUIET, return_num_dirty=False):
""" chip.feat.add(chip_rowid_list)
CRITICAL FUNCTION MUST EXIST FOR ALL DEPENDANTS
Adds / ensures / computes a dependant property
Args:
chip_rowid_list
Returns:
returns feat_rowid_list of added (or already existing feats)
TemplateInfo:
python -m ibeis.templates.template_generator --key feat --funcname-filter "\<add_chip_feat\>" --modfname=manual_feat_funcs
Tadder_pl_dependant
parent = chip
leaf = feat
CommandLine:
python -m ibeis.control.manual_feat_funcs --test-add_chip_feat
Example0:
>>> # ENABLE_DOCTEST
>>> from ibeis.control.manual_feat_funcs import * # NOQA
>>> ibs, config2_ = testdata_ibs()
>>> ibs.get_annot_chip_rowids(ibs.get_valid_aids()) # Ensure chips are computed
>>> chip_rowid_list = ibs._get_all_chip_rowids()[::3]
>>> feat_rowid_list = ibs.add_chip_feat(chip_rowid_list, config2_=config2_)
>>> assert len(feat_rowid_list) == len(chip_rowid_list), 'bad length'
>>> ut.assert_all_not_None(feat_rowid_list)
Example1:
>>> # ENABLE_DOCTEST
>>> from ibeis.control.manual_feat_funcs import * # NOQA
>>> ibs, config2_ = testdata_ibs()
>>> ibs.get_annot_chip_rowids(ibs.get_valid_aids()) # Ensure chips are computed
>>> chip_rowid_list = ibs._get_all_chip_rowids()[0:10]
>>> assert len(chip_rowid_list) == 10, 'chips not computed'
>>> sub_chip_rowid_list1 = chip_rowid_list[0:6]
>>> sub_chip_rowid_list2 = chip_rowid_list[5:7]
>>> sub_chip_rowid_list3 = chip_rowid_list[0:7]
>>> sub_feat_rowid_list1 = ibs.get_chip_feat_rowid(sub_chip_rowid_list1, config2_=config2_, ensure=True)
>>> ibs.get_chip_feat_rowid(sub_chip_rowid_list1, config2_=config2_, ensure=True)
>>> sub_feat_rowid_list1, num_dirty0 = ibs.add_chip_feat(sub_chip_rowid_list1, config2_=config2_, return_num_dirty=True)
>>> assert num_dirty0 == 0, 'num_dirty0=%r' % (num_dirty0,)
>>> ut.assert_all_not_None(sub_feat_rowid_list1)
>>> ibs.delete_chip_feats(sub_chip_rowid_list2)
>>> #ibs.delete_chip_feat(sub_chip_rowid_list2)?
>>> sub_feat_rowid_list3 = ibs.get_chip_feat_rowid(sub_chip_rowid_list3, config2_=config2_, ensure=False)
>>> # Only the last two should be None
>>> ut.assert_all_not_None(sub_feat_rowid_list3[0:5], 'sub_feat_rowid_list3[0:5])')
>>> assert sub_feat_rowid_list3[5:7] == [None, None], 'sub_feat_rowid_list3=%r' % (sub_feat_rowid_list3,)
>>> sub_feat_rowid_list3_ensured, num_dirty1 = ibs.add_chip_feat(sub_chip_rowid_list3, config2_=config2_, return_num_dirty=True)
>>> assert num_dirty1 == 2, 'Only two params should have been computed here'
>>> ut.assert_all_not_None(sub_feat_rowid_list3_ensured)
"""
from ibeis.algo.preproc import preproc_feat
ut.assert_all_not_None(chip_rowid_list, ' chip_rowid_list')
# Get requested configuration id
config_rowid = ibs.get_feat_config_rowid(config2_=config2_)
# Find leaf rowids that need to be computed
initial_feat_rowid_list = get_chip_feat_rowids_(
ibs, chip_rowid_list, config2_=config2_)
# Get corresponding "dirty" parent rowids
isdirty_list = ut.flag_None_items(initial_feat_rowid_list)
dirty_chip_rowid_list = ut.compress(chip_rowid_list, isdirty_list)
num_dirty = len(dirty_chip_rowid_list)
num_total = len(chip_rowid_list)
if num_dirty > 0:
if verbose:
fmtstr = '[add_chip_feat] adding %d / %d new feat for config_rowid=%r'
print(fmtstr % (num_dirty, num_total, config_rowid))
# Dependant columns do not need true from_superkey getters.
# We can use the Tgetter_pl_dependant_rowids_ instead
get_rowid_from_superkey = functools.partial(
ibs.get_chip_feat_rowids_, config2_=config2_)
# CALL EXTERNAL PREPROCESSING / GENERATION FUNCTION
proptup_gen = preproc_feat.generate_feat_properties(
ibs, dirty_chip_rowid_list, config2_=config2_)
dirty_params_iter = (
(chip_rowid, config_rowid, feature_nFeat,
feature_kpt_arr, feature_vec_arr)
for chip_rowid, (feature_nFeat, feature_kpt_arr, feature_vec_arr,) in
zip(dirty_chip_rowid_list, proptup_gen)
)
colnames = ['chip_rowid', 'config_rowid',
'feature_num_feats', 'feature_keypoints', 'feature_vecs']
#feat_rowid_list = ibs.dbcache.add_cleanly(const.FEATURE_TABLE, colnames, dirty_params_iter, get_rowid_from_superkey)
CHUNKED_ADD = True
if CHUNKED_ADD:
chunksize = 128
print('[add_chip_feat] adding to sql in chunks with chunksize=%r' % (chunksize,))
for dirty_params_chunk in ut.ichunks(dirty_params_iter, chunksize=chunksize):
print('[add_chip_feat] adding feature chunk to sql')
nInput = len(dirty_params_chunk)
ibs.dbcache._add(
const.FEATURE_TABLE, colnames, dirty_params_chunk, nInput=nInput)
else:
nInput = num_dirty
ibs.dbcache._add(
const.FEATURE_TABLE, colnames, dirty_params_iter, nInput=nInput)
#ibs.dbcache._add(const.FEATURE_TABLE, colnames, dirty_params_iter)
# Now that the dirty params are added get the correct order of rowids
feat_rowid_list = get_rowid_from_superkey(chip_rowid_list)
else:
feat_rowid_list = initial_feat_rowid_list
if return_num_dirty:
return feat_rowid_list, num_dirty
return feat_rowid_list
def test_model(num_annots, num_names, score_evidence=[], name_evidence=[],
other_evidence={}, noquery=False, verbose=None,
**kwargs):
if verbose is None:
verbose = ut.VERBOSE
method = kwargs.pop('method', None)
model = make_name_model(num_annots, num_names, verbose=verbose, **kwargs)
if verbose:
model.print_priors(ignore_ttypes=['match', 'score'])
model, evidence, soft_evidence = update_model_evidence(
model, name_evidence, score_evidence, other_evidence)
if verbose and len(soft_evidence) != 0:
model.print_priors(ignore_ttypes=['match', 'score'],
title='Soft Evidence', color='green')
#if verbose:
# ut.colorprint('\n --- Soft Evidence ---', 'white')
# for ttype, cpds in model.ttype2_cpds.items():
# if ttype != 'match':
# for fs_ in ut.ichunks(cpds, 4):
# ut.colorprint(ut.hz_str([f._cpdstr('psql') for f in fs_]),
# 'green')
if verbose:
ut.colorprint('\n --- Inference ---', 'red')
if (len(evidence) > 0 or len(soft_evidence) > 0) and not noquery:
evidence = model._ensure_internal_evidence(evidence)
query_vars = []
query_vars += ut.list_getattr(model.ttype2_cpds['name'], 'variable')
#query_vars += ut.list_getattr(model.ttype2_cpds['match'], 'variable')
query_vars = ut.setdiff(query_vars, evidence.keys())
#query_vars = ut.setdiff(query_vars, soft_evidence.keys())
query_results = cluster_query(model, query_vars, evidence,
soft_evidence, method)
else:
query_results = {}
factor_list = query_results['factor_list']
if verbose:
if verbose:
print('+--------')
semtypes = [model.var2_cpd[f.variables[0]].ttype
for f in factor_list]
for type_, factors in ut.group_items(factor_list, semtypes).items():
print('Result Factors (%r)' % (type_,))
factors = ut.sortedby(factors, [f.variables[0] for f in factors])
for fs_ in ut.ichunks(factors, 4):
ut.colorprint(ut.hz_str([f._str('phi', 'psql') for f in fs_]),
'yellow')
print('MAP assignments')
top_assignments = query_results.get('top_assignments', [])
tmp = []
for lbl, val in top_assignments:
tmp.append('%s : %.4f' % (ut.repr2(lbl), val))
print(ut.align('\n'.join(tmp), ' :'))
print('L_____\n')
showkw = dict(evidence=evidence,
soft_evidence=soft_evidence,
**query_results)
pgm_viz.show_model(model, **showkw)
return (model, evidence, query_results)
def print_priors(model, ignore_ttypes=[], title='Priors', color='darkblue'):
ut.colorprint('\n --- %s ---' % (title,), color=color)
for ttype, cpds in model.ttype2_cpds.items():
if ttype not in ignore_ttypes:
for fs_ in ut.ichunks(cpds, 4):
ut.colorprint(ut.hz_str([f._cpdstr('psql') for f in fs_]), color)
def check_database_overlap(ibs1, ibs2):
"""
CommandLine:
python -m wbia.other.dbinfo --test-get_dbinfo:1 --db PZ_MTEST
dev.py -t listdbs
python -m wbia.dbio.export_subset check_database_overlap
--db PZ_MTEST --db2 PZ_MOTHERS
CommandLine:
python -m wbia.dbio.export_subset check_database_overlap
python -m wbia.dbio.export_subset check_database_overlap --db1=PZ_MTEST --db2=PZ_Master0 # NOQA
python -m wbia.dbio.export_subset check_database_overlap --db1=NNP_Master3 --db2=PZ_Master0 # NOQA
python -m wbia.dbio.export_subset check_database_overlap --db1=GZ_Master0 --db2=GZ_ALL
python -m wbia.dbio.export_subset check_database_overlap --db1=GZ_ALL --db2=lewa_grevys
python -m wbia.dbio.export_subset check_database_overlap --db1=PZ_FlankHack --db2=PZ_Master1
python -m wbia.dbio.export_subset check_database_overlap --db1=PZ_PB_RF_TRAIN --db2=PZ_Master1
Example:
>>> # SCRIPT
>>> from wbia.dbio.export_subset import * # NOQA
>>> import wbia
>>> import utool as ut
>>> #ibs1 = wbia.opendb(db='PZ_Master0')
>>> #ibs2 = wbia.opendb(dbdir='/raid/work2/Turk/PZ_Master')
>>> db1 = ut.get_argval('--db1', str, default='PZ_MTEST')
>>> db2 = ut.get_argval('--db2', str, default='testdb1')
>>> dbdir1 = ut.get_argval('--dbdir1', str, default=None)
>>> dbdir2 = ut.get_argval('--dbdir2', str, default=None)
>>> ibs1 = wbia.opendb(db=db1, dbdir=dbdir1)
>>> ibs2 = wbia.opendb(db=db2, dbdir=dbdir2)
>>> check_database_overlap(ibs1, ibs2)
"""
import numpy as np
def print_isect(items1, items2, lbl=''):
set1_ = set(items1)
set2_ = set(items2)
items_isect = set1_.intersection(set2_)
fmtkw1 = dict(
part=1,
lbl=lbl,
num=len(set1_),
num_isect=len(items_isect),
percent=100 * len(items_isect) / len(set1_),
)
fmtkw2 = dict(
part=2,
lbl=lbl,
num=len(set2_),
num_isect=len(items_isect),
percent=100 * len(items_isect) / len(set2_),
)
fmt_a = ' * Num {lbl} {part}: {num_isect} / {num} = {percent:.2f}%'
# fmt_b = ' * Num {lbl} isect: {num}'
logger.info('Checking {lbl} intersection'.format(lbl=lbl))
logger.info(fmt_a.format(**fmtkw1))
logger.info(fmt_a.format(**fmtkw2))
# logger.info(fmt_b.format(lbl=lbl, num=len(items_isect)))
# items = items_isect
# list_ = items1
x_list1 = ut.find_list_indexes(items1, items_isect)
x_list2 = ut.find_list_indexes(items2, items_isect)
return x_list1, x_list2
gids1 = ibs1.images()
gids2 = ibs2.images()
# Find common images
# items1, items2, lbl, = gids1.uuids, gids2.uuids, 'images'
gx_list1, gx_list2 = print_isect(gids1.uuids, gids2.uuids, 'images')
gids_isect1 = gids1.take(gx_list1)
gids_isect2 = gids2.take(gx_list2)
assert gids_isect2.uuids == gids_isect1.uuids, 'sequence must be aligned'
SHOW_ISECT_GIDS = False
if SHOW_ISECT_GIDS:
if len(gx_list1) > 0:
logger.info('gids_isect1 = %r' % (gids_isect1, ))
logger.info('gids_isect2 = %r' % (gids_isect2, ))
if False:
# Debug code
import wbia.viz
import wbia.plottool as pt
gid_pairs = list(zip(gids_isect1, gids_isect2))
pairs_iter = ut.ichunks(gid_pairs, chunksize=8)
for fnum, pairs in enumerate(pairs_iter, start=1):
pnum_ = pt.make_pnum_nextgen(nRows=len(pairs), nCols=2)
for gid1, gid2 in pairs:
wbia.viz.show_image(ibs1,
gid1,
pnum=pnum_(),
fnum=fnum)
wbia.viz.show_image(ibs2,
gid2,
pnum=pnum_(),
fnum=fnum)
# if False:
# aids1 = ibs1.get_valid_aids()
# aids2 = ibs2.get_valid_aids()
# ibs1.update_annot_visual_uuids(aids1)
# ibs2.update_annot_visual_uuids(aids2)
# ibs1.update_annot_semantic_uuids(aids1)
# ibs2.update_annot_semantic_uuids(aids2)
# Check to see which intersecting images have different annotations
image_aids_isect1 = gids_isect1.aids
image_aids_isect2 = gids_isect2.aids
image_avuuids_isect1 = np.array(
ibs1.unflat_map(ibs1.get_annot_visual_uuids, image_aids_isect1))
image_avuuids_isect2 = np.array(
ibs2.unflat_map(ibs2.get_annot_visual_uuids, image_aids_isect2))
changed_image_xs = np.nonzero(
image_avuuids_isect1 != image_avuuids_isect2)[0]
if len(changed_image_xs) > 0:
logger.info(
'There are %d images with changes in annotation visual information'
% (len(changed_image_xs), ))
changed_gids1 = ut.take(gids_isect1, changed_image_xs)
changed_gids2 = ut.take(gids_isect2, changed_image_xs)
SHOW_CHANGED_GIDS = False
if SHOW_CHANGED_GIDS:
logger.info('gids_isect1 = %r' % (changed_gids2, ))
logger.info('gids_isect2 = %r' % (changed_gids1, ))
# if False:
# # Debug code
# import wbia.viz
# import wbia.plottool as pt
# gid_pairs = list(zip(changed_gids1, changed_gids2))
# pairs_iter = ut.ichunks(gid_pairs, chunksize=8)
# for fnum, pairs in enumerate(pairs_iter, start=1):
# pnum_ = pt.make_pnum_nextgen(nRows=len(pairs), nCols=2)
# for gid1, gid2 in pairs:
# wbia.viz.show_image(
# ibs1, gid1, pnum=pnum_(), fnum=fnum)
# wbia.viz.show_image(
# ibs2, gid2, pnum=pnum_(), fnum=fnum)
# Check for overlapping annotations (visual info only) in general
aids1 = ibs1.annots()
aids2 = ibs2.annots()
# Check for overlapping annotations (visual + semantic info) in general
aux_list1, aux_list2 = print_isect(aids1.uuids, aids2.uuids, 'uuids')
avx_list1, avx_list2 = print_isect(aids1.visual_uuids, aids2.visual_uuids,
'vuuids')
asx_list1, asx_list2 = print_isect(aids1.semantic_uuids,
aids2.semantic_uuids, 'suuids')
# Check which images with the same visual uuids have different semantic
# uuids
changed_ax_list1 = ut.setdiff_ordered(avx_list1, asx_list1)
changed_ax_list2 = ut.setdiff_ordered(avx_list2, asx_list2)
assert len(changed_ax_list1) == len(changed_ax_list2)
assert ut.take(aids1.visual_uuids,
changed_ax_list1) == ut.take(aids2.visual_uuids,
changed_ax_list2)
changed_aids1 = np.array(ut.take(aids1, changed_ax_list1))
changed_aids2 = np.array(ut.take(aids2, changed_ax_list2))
changed_sinfo1 = ibs1.get_annot_semantic_uuid_info(changed_aids1)
changed_sinfo2 = ibs2.get_annot_semantic_uuid_info(changed_aids2)
sinfo1_arr = np.array(changed_sinfo1)
sinfo2_arr = np.array(changed_sinfo2)
is_semantic_diff = sinfo2_arr != sinfo1_arr
# Inspect semantic differences
if np.any(is_semantic_diff):
colxs, rowxs = np.nonzero(is_semantic_diff)
colx2_rowids = ut.group_items(rowxs, colxs)
prop2_rowids = ut.map_dict_keys(changed_sinfo1._fields.__getitem__,
colx2_rowids)
logger.info('changed_value_counts = ' +
ut.repr2(ut.map_dict_vals(len, prop2_rowids)))
yawx = changed_sinfo1._fields.index('yaw')
# Show change in viewpoints
if len(colx2_rowids[yawx]) > 0:
vp_category_diff = ibsfuncs.viewpoint_diff(
sinfo1_arr[yawx], sinfo2_arr[yawx]).astype(np.float)
# Look for category changes
# any_diff = np.floor(vp_category_diff) > 0
# _xs = np.nonzero(any_diff)[0]
# _aids1 = changed_aids1.take(_xs)
# _aids2 = changed_aids2.take(_xs)
# Look for significant changes
is_significant_diff = np.floor(vp_category_diff) > 1
significant_xs = np.nonzero(is_significant_diff)[0]
significant_aids1 = changed_aids1.take(significant_xs)
significant_aids2 = changed_aids2.take(significant_xs)
logger.info('There are %d significant viewpoint changes' %
(len(significant_aids2), ))
# vt.ori_distance(sinfo1_arr[yawx], sinfo2_arr[yawx])
# zip(ibs1.get_annot_viewpoint_code(significant_aids1),
# ibs2.get_annot_viewpoint_code(significant_aids2))
# logger.info('yawdiff = %r' % )
# if False:
# Hack: Apply fixes
# good_yaws = ibs2.get_annot_yaws(significant_aids2)
# ibs1.set_annot_yaws(significant_aids1, good_yaws)
# pass
if False:
# Debug code
import wbia.viz
import wbia.plottool as pt
# aid_pairs = list(zip(_aids1, _aids2))
aid_pairs = list(zip(significant_aids1, significant_aids2))
pairs_iter = ut.ichunks(aid_pairs, chunksize=8)
for fnum, pairs in enumerate(pairs_iter, start=1):
pnum_ = pt.make_pnum_nextgen(nRows=len(pairs), nCols=2)
for aid1, aid2 in pairs:
wbia.viz.show_chip(
ibs1,
aid1,
pnum=pnum_(),
fnum=fnum,
show_viewcode=True,
nokpts=True,
)
wbia.viz.show_chip(
ibs2,
aid2,
pnum=pnum_(),
fnum=fnum,
show_viewcode=True,
nokpts=True,
)
#
nAnnots_per_image1 = np.array(ibs1.get_image_num_annotations(gids1))
nAnnots_per_image2 = np.array(ibs2.get_image_num_annotations(gids2))
#
images_without_annots1 = sum(nAnnots_per_image1 == 0)
images_without_annots2 = sum(nAnnots_per_image2 == 0)
logger.info('images_without_annots1 = %r' % (images_without_annots1, ))
logger.info('images_without_annots2 = %r' % (images_without_annots2, ))
nAnnots_per_image1
def get_sift_collection(sift,
aff=None,
bin_color=BLACK,
arm1_color=RED,
arm2_color=BLACK,
arm_alpha=1.0,
arm1_lw=1.0,
arm2_lw=2.0,
circ_alpha=.5,
**kwargs):
"""
Creates a collection of SIFT matplotlib patches
get_sift_collection
Args:
sift (?):
aff (None):
bin_color (ndarray):
arm1_color (ndarray):
arm2_color (ndarray):
arm_alpha (float):
arm1_lw (float):
arm2_lw (float):
circ_alpha (float):
Returns:
?: coll_tup
CommandLine:
python -m plottool.mpl_sift --test-get_sift_collection
Example:
>>> from plottool.mpl_sift import * # NOQA
>>> sift = testdata_sifts()[0]
>>> aff = None
>>> bin_color = array([ 0., 0., 0., 1.])
>>> arm1_color = array([ 1., 0., 0., 1.])
>>> arm2_color = array([ 0., 0., 0., 1.])
>>> arm_alpha = 1.0
>>> arm1_lw = 0.5
>>> arm2_lw = 1.0
>>> circ_alpha = 0.5
>>> coll_tup = get_sift_collection(sift, aff, bin_color, arm1_color, arm2_color, arm_alpha, arm1_lw, arm2_lw, circ_alpha)
>>> print(coll_tup)
"""
# global offset scale adjustments
if aff is None:
aff = mpl.transforms.Affine2D()
MULTI_COLORED_ARMS = kwargs.pop('multicolored_arms', False)
_kwarm = kwargs.copy()
_kwarm.update(
dict(head_width=1e-10,
length_includes_head=False,
transform=aff,
color=[1, 1, 0]))
_kwcirc = dict(transform=aff)
arm_patches = []
DSCALE = 0.25 # Descriptor scale factor
ARMSCALE = 1.5 # Arm length scale factor
XYSCALE = 0.5 # Position scale factor
XYOFFST = -0.75 # Position offset
NORI, NX, NY = 8, 4, 4 # SIFT BIN CONSTANTS
NBINS = NX * NY
discrete_ori = (np.arange(0, NORI) * (TAU / NORI))
# Arm magnitude and orientations
arm_mag = sift / 255.0
arm_ori = np.tile(discrete_ori, (NBINS, 1)).flatten()
# Arm orientation in dxdy format
arm_dxy = np.array(list(zip(*_cirlce_rad2xy(arm_ori, arm_mag))))
# Arm locations and dxdy index
yxt_gen = iprod(range(NY), range(NX), range(NORI))
# Circle x,y locations
yx_gen = iprod(range(NY), range(NX))
# Draw 8 directional arms in each of the 4x4 grid cells
arm_args_list = []
for y, x, t in yxt_gen:
#print('y=%r, x=%r, t=%r' % (y, x, t))
index = (y * NX * NORI) + (x * NORI) + (t)
(dx, dy) = arm_dxy[index]
arm_x = (x * XYSCALE) + XYOFFST # MULTIPLY BY -1 to invert X axis
arm_y = (y * XYSCALE) + XYOFFST
arm_dy = (dy * DSCALE) * ARMSCALE
arm_dx = (dx * DSCALE) * ARMSCALE
_args = [arm_x, arm_y, arm_dx, arm_dy]
arm_args_list.append(_args)
for _args in arm_args_list:
arm_patch = mpl.patches.FancyArrow(*_args, **_kwarm)
arm_patches.append(arm_patch)
#print('len(arm_patches) = %r' % (len(arm_patches),))
# Draw circles around each of the 4x4 grid cells
circle_patches = []
for y, x in yx_gen:
circ_xy = (x * XYSCALE + XYOFFST, y * XYSCALE + XYOFFST)
circ_radius = DSCALE
circle_patches += [mpl.patches.Circle(circ_xy, circ_radius, **_kwcirc)]
circ_coll = _circl_collection(circle_patches, bin_color, circ_alpha)
arm2_coll = _arm_collection(arm_patches, arm2_color, arm_alpha, arm2_lw)
if MULTI_COLORED_ARMS:
# Hack in same colorscheme for arms as the sift bars
ori_colors = color_fns.distinct_colors(16)
coll_tup = [circ_coll, arm2_coll]
coll_tup += [
_arm_collection(_, color, arm_alpha, arm1_lw)
for _, color in zip(ut.ichunks(arm_patches, 8), ori_colors)
]
coll_tup = tuple(coll_tup)
else:
# Just use a single color for all the arms
arm1_coll = _arm_collection(arm_patches, arm1_color, arm_alpha,
arm1_lw)
coll_tup = (circ_coll, arm2_coll, arm1_coll)
return coll_tup
def test_siamese_performance(model, data, labels, flat_metadata, dataname=''):
r"""
CommandLine:
utprof.py -m ibeis_cnn --tf pz_patchmatch --db liberty --test --weights=liberty:current --arch=siaml2_128 --test
python -m ibeis_cnn --tf netrun --db liberty --arch=siaml2_128 --test --ensure
python -m ibeis_cnn --tf netrun --db liberty --arch=siaml2_128 --test --ensure --weights=new
python -m ibeis_cnn --tf netrun --db liberty --arch=siaml2_128 --train --weights=new
python -m ibeis_cnn --tf netrun --db pzmtest --weights=liberty:current --arch=siaml2_128 --test # NOQA
python -m ibeis_cnn --tf netrun --db pzmtest --weights=liberty:current --arch=siaml2_128
"""
import vtool as vt
import plottool as pt
# TODO: save in model.trainind_dpath/diagnostics/figures
ut.colorprint('\n[siam_perf] Testing Siamese Performance', 'white')
#epoch_dpath = model.get_epoch_diagnostic_dpath()
epoch_dpath = model.arch_dpath
ut.vd(epoch_dpath)
dataname += ' ' + model.get_history_hashid() + '\n'
history_text = ut.list_str(model.era_history, newlines=True)
ut.write_to(ut.unixjoin(epoch_dpath, 'era_history.txt'), history_text)
#if True:
# import matplotlib as mpl
# mpl.rcParams['agg.path.chunksize'] = 100000
#data = data[::50]
#labels = labels[::50]
#from ibeis_cnn import utils
#data, labels = utils.random_xy_sample(data, labels, 10000, model.data_per_label_input)
FULL = not ut.get_argflag('--quick')
fnum_gen = pt.make_fnum_nextgen()
ut.colorprint('[siam_perf] Show era history', 'white')
fig = model.show_era_loss(fnum=fnum_gen())
pt.save_figure(fig=fig, dpath=epoch_dpath, dpi=180)
# hack
ut.colorprint('[siam_perf] Show weights image', 'white')
fig = model.show_weights_image(fnum=fnum_gen())
pt.save_figure(fig=fig, dpath=epoch_dpath, dpi=180)
#model.draw_all_conv_layer_weights(fnum=fnum_gen())
#model.imwrite_weights(1)
#model.imwrite_weights(2)
# Compute each type of score
ut.colorprint('[siam_perf] Building Scores', 'white')
test_outputs = model.predict2(model, data)
network_output = test_outputs['network_output_determ']
# hack converting network output to distances for non-descriptor networks
if len(network_output.shape) == 2 and network_output.shape[1] == 1:
cnn_scores = network_output.T[0]
elif len(network_output.shape) == 1:
cnn_scores = network_output
elif len(network_output.shape) == 2 and network_output.shape[1] > 1:
assert model.data_per_label_output == 2
vecs1 = network_output[0::2]
vecs2 = network_output[1::2]
cnn_scores = vt.L2(vecs1, vecs2)
else:
assert False
cnn_scores = cnn_scores.astype(np.float64)
# Segfaults with the data passed in is large (AND MEMMAPPED apparently)
# Fixed in hesaff implementation
SIFT = FULL
if SIFT:
sift_scores, sift_list = test_sift_patchmatch_scores(data, labels)
sift_scores = sift_scores.astype(np.float64)
ut.colorprint('[siam_perf] Learning Encoders', 'white')
# Learn encoders
encoder_kw = {
#'monotonize': False,
'monotonize': True,
}
cnn_encoder = vt.ScoreNormalizer(**encoder_kw)
cnn_encoder.fit(cnn_scores, labels)
if SIFT:
sift_encoder = vt.ScoreNormalizer(**encoder_kw)
sift_encoder.fit(sift_scores, labels)
# Visualize
ut.colorprint('[siam_perf] Visualize Encoders', 'white')
viz_kw = dict(
with_scores=False,
with_postbayes=False,
with_prebayes=False,
target_tpr=.95,
)
inter_cnn = cnn_encoder.visualize(
figtitle=dataname + ' CNN scores. #data=' + str(len(data)),
fnum=fnum_gen(), **viz_kw)
if SIFT:
inter_sift = sift_encoder.visualize(
figtitle=dataname + ' SIFT scores. #data=' + str(len(data)),
fnum=fnum_gen(), **viz_kw)
# Save
pt.save_figure(fig=inter_cnn.fig, dpath=epoch_dpath)
if SIFT:
pt.save_figure(fig=inter_sift.fig, dpath=epoch_dpath)
# Save out examples of hard errors
#cnn_fp_label_indicies, cnn_fn_label_indicies =
#cnn_encoder.get_error_indicies(cnn_scores, labels)
#sift_fp_label_indicies, sift_fn_label_indicies =
#sift_encoder.get_error_indicies(sift_scores, labels)
with_patch_examples = FULL
if with_patch_examples:
ut.colorprint('[siam_perf] Visualize Confusion Examples', 'white')
cnn_indicies = cnn_encoder.get_confusion_indicies(cnn_scores, labels)
if SIFT:
sift_indicies = sift_encoder.get_confusion_indicies(sift_scores, labels)
warped_patch1_list, warped_patch2_list = list(zip(*ut.ichunks(data, 2)))
samp_args = (warped_patch1_list, warped_patch2_list, labels)
_sample = functools.partial(draw_results.get_patch_sample_img, *samp_args)
cnn_fp_img = _sample({'fs': cnn_scores}, cnn_indicies.fp)[0]
cnn_fn_img = _sample({'fs': cnn_scores}, cnn_indicies.fn)[0]
cnn_tp_img = _sample({'fs': cnn_scores}, cnn_indicies.tp)[0]
cnn_tn_img = _sample({'fs': cnn_scores}, cnn_indicies.tn)[0]
if SIFT:
sift_fp_img = _sample({'fs': sift_scores}, sift_indicies.fp)[0]
sift_fn_img = _sample({'fs': sift_scores}, sift_indicies.fn)[0]
sift_tp_img = _sample({'fs': sift_scores}, sift_indicies.tp)[0]
sift_tn_img = _sample({'fs': sift_scores}, sift_indicies.tn)[0]
#if ut.show_was_requested():
#def rectify(arr):
# return np.flipud(arr)
SINGLE_FIG = False
if SINGLE_FIG:
def dump_img(img_, lbl, fnum):
fig, ax = pt.imshow(img_, figtitle=dataname + ' ' + lbl, fnum=fnum)
pt.save_figure(fig=fig, dpath=epoch_dpath, dpi=180)
dump_img(cnn_fp_img, 'cnn_fp_img', fnum_gen())
dump_img(cnn_fn_img, 'cnn_fn_img', fnum_gen())
dump_img(cnn_tp_img, 'cnn_tp_img', fnum_gen())
dump_img(cnn_tn_img, 'cnn_tn_img', fnum_gen())
dump_img(sift_fp_img, 'sift_fp_img', fnum_gen())
dump_img(sift_fn_img, 'sift_fn_img', fnum_gen())
dump_img(sift_tp_img, 'sift_tp_img', fnum_gen())
dump_img(sift_tn_img, 'sift_tn_img', fnum_gen())
#vt.imwrite(dataname + '_' + 'cnn_fp_img.png', (cnn_fp_img))
#vt.imwrite(dataname + '_' + 'cnn_fn_img.png', (cnn_fn_img))
#vt.imwrite(dataname + '_' + 'sift_fp_img.png', (sift_fp_img))
#vt.imwrite(dataname + '_' + 'sift_fn_img.png', (sift_fn_img))
else:
print('Drawing TP FP TN FN')
fnum = fnum_gen()
pnum_gen = pt.make_pnum_nextgen(4, 2)
fig = pt.figure(fnum)
pt.imshow(cnn_fp_img, title='CNN FP', fnum=fnum, pnum=pnum_gen())
pt.imshow(sift_fp_img, title='SIFT FP', fnum=fnum, pnum=pnum_gen())
pt.imshow(cnn_fn_img, title='CNN FN', fnum=fnum, pnum=pnum_gen())
pt.imshow(sift_fn_img, title='SIFT FN', fnum=fnum, pnum=pnum_gen())
pt.imshow(cnn_tp_img, title='CNN TP', fnum=fnum, pnum=pnum_gen())
pt.imshow(sift_tp_img, title='SIFT TP', fnum=fnum, pnum=pnum_gen())
pt.imshow(cnn_tn_img, title='CNN TN', fnum=fnum, pnum=pnum_gen())
pt.imshow(sift_tn_img, title='SIFT TN', fnum=fnum, pnum=pnum_gen())
pt.set_figtitle(dataname + ' confusions')
pt.adjust_subplots(left=0, right=1.0, bottom=0., wspace=.01, hspace=.05)
pt.save_figure(fig=fig, dpath=epoch_dpath, dpi=180, figsize=(9, 18))
with_patch_desc = FULL
if with_patch_desc:
ut.colorprint('[siam_perf] Visualize Patch Descriptors', 'white')
fnum = fnum_gen()
fig = pt.figure(fnum=fnum, pnum=(1, 1, 1))
num_rows = 7
pnum_gen = pt.make_pnum_nextgen(num_rows, 3)
# Compare actual output descriptors
for index in ut.random_indexes(len(sift_list), num_rows):
vec_sift = sift_list[index]
vec_cnn = network_output[index]
patch = data[index]
pt.imshow(patch, fnum=fnum, pnum=pnum_gen())
pt.plot_descriptor_signature(vec_cnn, 'cnn vec', fnum=fnum, pnum=pnum_gen())
pt.plot_sift_signature(vec_sift, 'sift vec', fnum=fnum, pnum=pnum_gen())
pt.set_figtitle('Patch Descriptors')
pt.adjust_subplots(left=0, right=0.95, bottom=0., wspace=.1, hspace=.15)
pt.save_figure(fig=fig, dpath=epoch_dpath, dpi=180, figsize=(9, 18))
def add_rows_from_parent(table, parent_rowids, config=None, verbose=True,
return_num_dirty=False):
"""
Lazy addition
"""
try:
# Get requested configuration id
config_rowid = table.get_config_rowid(config)
# Find leaf rowids that need to be computed
initial_rowid_list = table._get_rowid_from_superkey(parent_rowids,
config=config)
# Get corresponding "dirty" parent rowids
isdirty_list = ut.flag_None_items(initial_rowid_list)
dirty_parent_rowids = ut.compress(parent_rowids, isdirty_list)
num_dirty = len(dirty_parent_rowids)
num_total = len(parent_rowids)
if num_dirty > 0:
if verbose:
fmtstr = 'adding %d / %d new props to %r for config_rowid=%r'
print(fmtstr % (num_dirty, num_total, table.tablename,
config_rowid))
args = zip(*dirty_parent_rowids)
if table._asobject:
# Convinience
args = [table.depc.get_obj(parent, rowids)
for parent, rowids in zip(table.parents, args)]
# CALL EXTERNAL PREPROCESSING / GENERATION FUNCTION
proptup_gen = table.preproc_func(table.depc, *args, config=config)
#proptup_gen = list(proptup_gen)
if len(table._nested_idxs) > 0:
# TODO: rewrite
nested_nCols = len(table.data_colnames)
idxs1 = table._nested_idxs
mask1 = ut.index_to_boolmask(idxs1, nested_nCols)
mask2 = ut.not_list(mask1)
idxs2 = ut.where(mask2)
def unnest_data(data):
unnested_cols = list(zip(ut.take(data, idxs2)))
nested_cols = ut.take(data, idxs1)
grouped_items = [nested_cols, unnested_cols]
groupxs = [idxs1, idxs2]
unflat = ut.ungroup(grouped_items, groupxs, nested_nCols - 1)
return tuple(ut.flatten(unflat))
# Hack when a sql schema has tuples defined in it
proptup_gen = (unnest_data(data) for data in proptup_gen)
#proptup_gen = list(proptup_gen)
dirty_params_iter = (
parent_rowids + (config_rowid,) + data_cols
for parent_rowids, data_cols in zip(dirty_parent_rowids, proptup_gen))
#dirty_params_iter = list(dirty_params_iter)
#print('dirty_params_iter = %s' % (ut.repr2(dirty_params_iter, nl=1),))
CHUNKED_ADD = table.chunksize is not None
if CHUNKED_ADD:
for dirty_params_chunk in ut.ichunks(dirty_params_iter,
chunksize=table.chunksize):
table.db._add(table.tablename, table._table_colnames,
dirty_params_chunk,
nInput=len(dirty_params_chunk))
else:
nInput = num_dirty
table.db._add(table.tablename, table._table_colnames,
dirty_params_iter, nInput=nInput)
# Now that the dirty params are added get the correct order of rowids
rowid_list = table._get_rowid_from_superkey(parent_rowids,
config=config)
else:
rowid_list = initial_rowid_list
if return_num_dirty:
return rowid_list, num_dirty
else:
return rowid_list
except Exception as ex:
ut.printex(ex, 'error in add_rowids', keys=[
'table', 'parent_rowids', 'config', 'args',
'dirty_parent_rowids', 'table.preproc_func'])
raise
def get_sift_collection(sift, aff=None, bin_color=BLACK, arm1_color=RED,
arm2_color=BLACK, arm_alpha=1.0, arm1_lw=1.0,
arm2_lw=2.0, circ_alpha=.5, **kwargs):
"""
Creates a collection of SIFT matplotlib patches
get_sift_collection
Args:
sift (?):
aff (None):
bin_color (ndarray):
arm1_color (ndarray):
arm2_color (ndarray):
arm_alpha (float):
arm1_lw (float):
arm2_lw (float):
circ_alpha (float):
Returns:
?: coll_tup
CommandLine:
python -m plottool.mpl_sift --test-get_sift_collection
Example:
>>> from plottool.mpl_sift import * # NOQA
>>> sift = testdata_sifts()[0]
>>> aff = None
>>> bin_color = array([ 0., 0., 0., 1.])
>>> arm1_color = array([ 1., 0., 0., 1.])
>>> arm2_color = array([ 0., 0., 0., 1.])
>>> arm_alpha = 1.0
>>> arm1_lw = 0.5
>>> arm2_lw = 1.0
>>> circ_alpha = 0.5
>>> coll_tup = get_sift_collection(sift, aff, bin_color, arm1_color, arm2_color, arm_alpha, arm1_lw, arm2_lw, circ_alpha)
>>> print(coll_tup)
"""
# global offset scale adjustments
if aff is None:
aff = mpl.transforms.Affine2D()
MULTI_COLORED_ARMS = kwargs.pop('multicolored_arms', False)
_kwarm = kwargs.copy()
_kwarm.update(dict(head_width=1e-10, length_includes_head=False, transform=aff, color=[1, 1, 0]))
_kwcirc = dict(transform=aff)
arm_patches = []
DSCALE = 0.25 # Descriptor scale factor
ARMSCALE = 1.5 # Arm length scale factor
XYSCALE = 0.5 # Position scale factor
XYOFFST = -0.75 # Position offset
NORI, NX, NY = 8, 4, 4 # SIFT BIN CONSTANTS
NBINS = NX * NY
discrete_ori = (np.arange(0, NORI) * (TAU / NORI))
# Arm magnitude and orientations
arm_mag = sift / 255.0
arm_ori = np.tile(discrete_ori, (NBINS, 1)).flatten()
# Arm orientation in dxdy format
arm_dxy = np.array(list(zip(*_cirlce_rad2xy(arm_ori, arm_mag))))
# Arm locations and dxdy index
yxt_gen = iprod(range(NY), range(NX), range(NORI))
# Circle x,y locations
yx_gen = iprod(range(NY), range(NX))
# Draw 8 directional arms in each of the 4x4 grid cells
arm_args_list = []
for y, x, t in yxt_gen:
#print('y=%r, x=%r, t=%r' % (y, x, t))
index = (y * NX * NORI) + (x * NORI) + (t)
(dx, dy) = arm_dxy[index]
arm_x = (x * XYSCALE) + XYOFFST # MULTIPLY BY -1 to invert X axis
arm_y = (y * XYSCALE) + XYOFFST
arm_dy = (dy * DSCALE) * ARMSCALE
arm_dx = (dx * DSCALE) * ARMSCALE
_args = [arm_x, arm_y, arm_dx, arm_dy]
arm_args_list.append(_args)
for _args in arm_args_list:
arm_patch = mpl.patches.FancyArrow(*_args, **_kwarm)
arm_patches.append(arm_patch)
#print('len(arm_patches) = %r' % (len(arm_patches),))
# Draw circles around each of the 4x4 grid cells
circle_patches = []
for y, x in yx_gen:
circ_xy = (x * XYSCALE + XYOFFST, y * XYSCALE + XYOFFST)
circ_radius = DSCALE
circle_patches += [mpl.patches.Circle(circ_xy, circ_radius, **_kwcirc)]
circ_coll = _circl_collection(circle_patches, bin_color, circ_alpha)
arm2_coll = _arm_collection(arm_patches, arm2_color, arm_alpha, arm2_lw)
if MULTI_COLORED_ARMS:
# Hack in same colorscheme for arms as the sift bars
ori_colors = color_fns.distinct_colors(16)
coll_tup = [circ_coll, arm2_coll]
coll_tup += [_arm_collection(_, color, arm_alpha, arm1_lw)
for _, color in zip(ut.ichunks(arm_patches, 8), ori_colors)]
coll_tup = tuple(coll_tup)
else:
# Just use a single color for all the arms
arm1_coll = _arm_collection(arm_patches, arm1_color, arm_alpha, arm1_lw)
coll_tup = (circ_coll, arm2_coll, arm1_coll)
return coll_tup
def clean_tags():
zotero = get_libzotero()
# dict of all zotero items
# items = zotero.index
# get sql cursor
cur = zotero.cur
if False:
sorted(ut.util_sqlite.get_tablenames(cur))
ut.print_database_structure(cur)
# Debug info about tags table in sql
# The `tags` table stores all tags
# The itemTags table stores the association between items and tags
ut.get_table_columninfo_list(cur, 'fields')
# ut.get_table_columninfo_list(cur, 'relations')
ut.get_table_columninfo_list(cur, 'fieldsCombined')
ut.get_table_columninfo_list(cur, 'itemData')
ut.get_table_columninfo_list(cur, 'itemDataValues')
ut.get_table_columninfo_list(cur, 'tags')
ut.get_table_columninfo_list(cur, 'itemTags')
import pandas as pd
pd.options.display.max_colwidth = 40
pd.options.display.max_rows = 20
def pandas_sql(table, columns):
return pd.DataFrame(ut.get_table_rows(cur, table, columns),
columns=columns)
item_df = pandas_sql('items', ('itemID', 'itemTypeID', 'libraryID', 'key')).set_index('itemID', drop=False)
tags_df = pandas_sql('tags', ('tagID', 'name', 'type', 'libraryID', 'key')).set_index('tagID', drop=False)
itemData_df = pandas_sql('itemData', ('itemID', 'fieldID', 'valueID'))
itemTag_df = pandas_sql('itemTags', ('itemID', 'tagID'))
itemDataValues_df = pandas_sql('itemDataValues', ('valueID', 'value')).set_index('valueID')
field_df = pandas_sql('fields', ('fieldID', 'fieldName', 'fieldFormatID')).set_index('fieldID')
itemData_df['value'] = itemDataValues_df['value'].loc[itemData_df['valueID'].values].values
itemData_df['fieldName'] = field_df['fieldName'].loc[itemData_df['fieldID'].values].values
titles = itemData_df[itemData_df['fieldName'] == 'title']
assert len(ut.unique(ut.map_vals(len, titles.groupby('itemID').indices).values())) == 1
# itemTag_df.groupby('itemID').count()
# Find how often each tag is used
tagid_to_count = itemTag_df.groupby('tagID').count()
tagid_to_count = tagid_to_count.rename(columns={'itemID': 'nItems'})
tagid_to_count['name'] = tags_df.loc[tagid_to_count.index]['name']
tagid_to_count = tagid_to_count.sort_values('nItems')
bad_tags = tagid_to_count[tagid_to_count['nItems'] == 1]
tagid_to_count['tag_ncharsize'] = tagid_to_count['name'].apply(len)
tagid_to_count = tagid_to_count.sort_values('tag_ncharsize')
bad_tags = tagid_to_count[tagid_to_count['tag_ncharsize'] > 25]['name'].values.tolist()
def clean_tags2():
api_key = 'fBDBqRPwW9O3mYyNLiksBKZy'
base_url = 'https://api.zotero.org'
library_id = '1279414'
library_type = 'user'
from pyzotero import zotero
zot = zotero.Zotero(library_id, library_type, api_key)
for chunk in ut.ProgChunks(bad_tags, 50):
zot.delete_tags(*chunk)
if False:
api_key = 'fBDBqRPwW9O3mYyNLiksBKZy'
base_url = 'https://api.zotero.org'
user_id = '1279414'
userOrGroupPrefix = '/users/' + user_id
params = {'v': 3, 'key': api_key}
items_resp = requests.get(base_url + userOrGroupPrefix + '/items', params=params)
print(items_resp.content)
print(items_resp)
json_tags = []
get_url = base_url + userOrGroupPrefix + '/tags'
while True:
print('get_url = %r' % (get_url,))
tag_resp = requests.get(get_url, params=params)
if tag_resp.status_code != 200:
break
json_tags.extend(tag_resp.json())
if 'next' in tag_resp.links:
get_url = tag_resp.links['next']['url']
else:
break
version_to_tags = ut.ddict(list)
bad_tags = []
for tag in ut.ProgIter(json_tags, label='parsing tags'):
# x = requests.get(tag['links']['self']['href'], params=params)
if tag['meta']['numItems'] == 1:
import urllib2
try:
bad_tags.append(urllib2.quote(tag['tag']))
except Exception as ex:
print('cant encode tag=%r' % (tag,))
pass
for chunk in ut.ProgIter(ut.ichunks(bad_tags, 50), length=len(bad_tags) / 50):
search_url = base_url + userOrGroupPrefix + '/items?tag=' + ' || '.join(chunk)
r = requests.get(search_url, params=params)
matching_items = r.json()
# assert len(matching_items) == 1
for item in matching_items:
version = item['version']
version_to_tags[item['version']].append(tag['tag'])
# DELETE MULTIPLE TAGS
import requests
for chunk in ut.ichunks(bad_tags['name'], 50):
import urllib2
encoded_chunk = []
for t in chunk:
try:
encoded_chunk.append(urllib2.quote(t))
except Exception:
print(t)
suffix = ' || '.join(encoded_chunk)
delete_url = base_url + userOrGroupPrefix + '/tags?' + suffix
print('delete_url = %r' % (delete_url,))
resp = requests.delete(delete_url, params=params)
bad_tags = tagid_to_count[tagid_to_count['nItems'] == 1]
bad_tags['tagID'] = bad_tags.index
for tagid in bad_tags:
delete from itemTags where tagID in (select tagID from tags where type=1);
pass
for name in k['name'].values.tolist()
item_df['title'] = titles.set_index('itemID')['value']
for idx, item in zotero.index.items():
sql_title = item_df.loc[item.id]['title']
if item.title != sql_title:
if pd.isnull(sql_title) and item.title is not None:
print(item.__dict__)
print(item_df.loc[item.id])
print('item.title = %r' % (item.title,))
print('sql_title = %r' % (sql_title,))
assert False
duplicate_tags = [
(name, idxs) for name, idxs in tags_df.groupby('name', sort=True).indices.items() if len(idxs) > 2
]
tagname_to_tagid = tags_df.groupby('name', sort=True).first()
new_to_oldtags = {}
# Determine which tagi to use for each name
for tagname, idxs in duplicate_tags:
tags_subdf = tags_df.iloc[idxs]
mapping = itemTag_df[itemTag_df['tagID'].isin(tags_subdf['tagID'])]
tag_hist = mapping.groupby('tagID').count()
best_tagid = tag_hist['itemID'].idxmax()
new_to_oldtags[best_tagid] = set(tag_hist['itemID'].values) - {best_tagid}
tagname_to_tagid.loc[tagname] = tags_df.loc[best_tagid]
# for col in tagname_to_tagid.columns:
# tagname_to_tagid.loc[tagname][col] = tags_df.loc[best_tagid][col]
# tags_df.loc[best_tagid]
if False:
# Update tagIds
for newid, oldids in new_to_oldtags.items():
for oldid in oldids:
# cur.execute('SELECT itemID, tagID FROM itemTags WHERE tagID=?', (oldid,))
import sqlite3
try:
cmd = 'UPDATE itemTags SET tagID=? WHERE tagID=?'
args = (newid, oldid)
print('(%s) args = %r' % (cmd, args,))
cur.execute(cmd, args)
print(cur.fetchall())
except sqlite3.IntegrityError:
print('error')
pass
# tags_df.groupby('name', sort=True)
# itemTag_df.groupby('itemID')
# duptags = tags_df.iloc[tags_df.groupby('name', sort=True).indices['animals']]
# duptags['tagID']
# flags = itemTag_df['tagID'].isin(duptags['tagID'])
# dup_rel = itemTag_df[flags]
# item_df['title'].loc[dup_rel['itemID']].values
# tags_df.iloc[tags_df.groupby('name', sort=True).indices['animals']]
# tags_df[tags_df['type'] == 1]
# tags_df[tags_df['type'] == 0]
# tags_df['libraryID'].unique()
# tags_df['type'].unique()
'''
SELECT
SELECT FROM itemTags WHERE name in (animals)
'''
item_tag_pairs = ut.get_table_rows(cur, 'itemTags', ('itemID', 'tagID'))
# Group tags by item
itemid_to_tagids = ut.group_pairs(item_tag_pairs)
# Group items by tags
tagid_to_itemids = ut.group_pairs(map(tuple, map(reversed, item_tag_pairs)))
# mapping from tagid to name
tagid_to_name = dict(ut.get_table_rows(cur, 'tags', ('tagID', 'name')))
tagid_freq = list(ut.sort_dict(ut.map_vals(len, tagid_to_itemids), 'vals').items())
ut.sort_dict(ut.map_vals(sum, ut.group_pairs([(freq, tagid_to_name.get(tagid, tagid)) for tagid, freq in tagid_freq])), 'vals')
tagname_freq = ut.map_keys(lambda k: tagid_to_name.get(k, k), tagid_freq)
def chunks(self, chunksize):
for idxs in ut.ichunks(self, range(len(self))):
yield self.take(idxs)
def add_annot_chips(ibs, aid_list, config2_=None, verbose=not ut.QUIET, return_num_dirty=False):
r"""
annot.chip.add(aid_list)
CRITICAL FUNCTION MUST EXIST FOR ALL DEPENDANTS
Adds / ensures / computes a dependant property
Args:
aid_list
Returns:
returns chip_rowid_list of added (or already existing chips)
TemplateInfo:
python -m ibeis.templates.template_generator --key chip --funcname-filter "\<add_annot_chips\>" --modfname=manual_chip_funcs
python -m ibeis.templates.template_generator --key chip --modfname=manual_chip_funcs --funcname-filter "\<add_annot_chip"
Tadder_pl_dependant
parent = annot
leaf = chip
CommandLine:
python -m ibeis.control.manual_chip_funcs --test-add_annot_chips
RESTful:
Method: POST
URL: /api/annot_chip/
Example0:
>>> # ENABLE_DOCTEST
>>> from ibeis.control.manual_chip_funcs import * # NOQA
>>> ibs, config2_ = testdata_ibs()
>>> aid_list = ibs._get_all_aids()[::3]
>>> chip_rowid_list = ibs.add_annot_chips(aid_list, config2_=config2_)
>>> assert len(chip_rowid_list) == len(aid_list)
>>> ut.assert_all_not_None(chip_rowid_list)
Example1:
>>> # ENABLE_DOCTEST
>>> from ibeis.control.manual_chip_funcs import * # NOQA
>>> ibs, config2_ = testdata_ibs()
>>> aid_list = ibs._get_all_aids()[0:10]
>>> sub_aid_list1 = aid_list[0:6]
>>> sub_aid_list2 = aid_list[5:7]
>>> sub_aid_list3 = aid_list[0:7]
>>> sub_chip_rowid_list1 = ibs.get_annot_chip_rowids(sub_aid_list1, config2_=config2_, ensure=True)
>>> ibs.get_annot_chip_rowids(sub_aid_list1, config2_=config2_, ensure=True)
>>> sub_chip_rowid_list1, num_dirty0 = ibs.add_annot_chips(sub_aid_list1, config2_=config2_, return_num_dirty=True)
>>> assert num_dirty0 == 0
>>> ut.assert_all_not_None(sub_chip_rowid_list1)
>>> ibs.delete_annot_chips(sub_aid_list2)
>>> #ibs.delete_annot_chip(sub_aid_list2)?
>>> sub_chip_rowid_list3 = ibs.get_annot_chip_rowids(sub_aid_list3, config2_=config2_, ensure=False)
>>> # Only the last two should be None
>>> ut.assert_all_not_None(sub_chip_rowid_list3[0:5], 'sub_chip_rowid_list3[0:5])')
>>> assert sub_chip_rowid_list3[5:7] == [None, None]
>>> sub_chip_rowid_list3_ensured, num_dirty1 = ibs.add_annot_chips(sub_aid_list3, config2_=config2_, return_num_dirty=True)
>>> assert num_dirty1 == 2, 'Only two params should have been computed here'
>>> ut.assert_all_not_None(sub_chip_rowid_list3_ensured)
"""
from ibeis.algo.preproc import preproc_chip
ut.assert_all_not_None(aid_list, ' annot_rowid_list')
# Get requested configuration id
config_rowid = ibs.get_chip_config_rowid(config2_=config2_)
# Find leaf rowids that need to be computed
initial_chip_rowid_list = get_annot_chip_rowids_(ibs, aid_list, config2_=config2_)
# Get corresponding "dirty" parent rowids
isdirty_list = ut.flag_None_items(initial_chip_rowid_list)
dirty_aid_list = ut.compress(aid_list, isdirty_list)
num_dirty = len(dirty_aid_list)
num_total = len(aid_list)
if num_dirty > 0:
if verbose:
fmtstr = '[add_annot_chips] adding %d / %d new chip for config_rowid=%r'
print(fmtstr % (num_dirty, num_total, config_rowid))
# Dependant columns do not need true from_superkey getters.
# We can use the Tgetter_pl_dependant_rowids_ instead
get_rowid_from_superkey = functools.partial(
ibs.get_annot_chip_rowids_, config2_=config2_)
proptup_gen = preproc_chip.generate_chip_properties(ibs, dirty_aid_list, config2_=config2_)
dirty_params_iter = (
(aid, config_rowid, chip_uri, chip_width, chip_height)
for aid, (chip_uri, chip_width, chip_height,) in
zip(dirty_aid_list, proptup_gen)
)
colnames = ['annot_rowid', 'config_rowid',
'chip_uri', 'chip_width', 'chip_height']
#chip_rowid_list = ibs.dbcache.add_cleanly(const.CHIP_TABLE, colnames, dirty_params_iter, get_rowid_from_superkey)
CHUNKED_ADD = True
if CHUNKED_ADD:
chunksize = 32 if ut.WIN32 else 128
for dirty_params_chunk in ut.ichunks(dirty_params_iter, chunksize=chunksize):
nInput = len(dirty_params_chunk)
ibs.dbcache._add(
const.CHIP_TABLE, colnames, dirty_params_chunk, nInput=nInput)
else:
nInput = num_dirty
ibs.dbcache._add(
const.CHIP_TABLE, colnames, dirty_params_iter, nInput=nInput)
# Now that the dirty params are added get the correct order of rowids
chip_rowid_list = get_rowid_from_superkey(aid_list)
else:
chip_rowid_list = initial_chip_rowid_list
if return_num_dirty:
return chip_rowid_list, num_dirty
return chip_rowid_list
