def add_frames(self,E,edge_feature_row_breaks,
edge_orientations,abst_threshold):
new_E = E.copy()
esp.threshold_edgemap(new_E,.30,edge_feature_row_breaks,abst_threshold=abst_threshold)
esp.spread_edgemap(new_E,edge_feature_row_breaks,edge_orientations,spread_length=3)
if not self.processed_frames:
self.E = np.mean(new_E,axis=1)
self.processed_frames = True
else:
self.E = (self.E * self.num_frames + np.sum(new_E,axis=1))/(self.num_frames+new_E.shape[1])
self.num_frames += new_E.shape[1]
def get_detections(neg_E,mean_template,bg_len,mean_bgd,
edge_feature_row_breaks,edge_orientations,
spread_length=3,abst_threshold = .0001*np.ones(8)):
num_detections = neg_E.shape[1] - mean_template.shape[1]
detections = []
for d in xrange(num_detections):
E_segment = neg_E[:,d:d+mean_template.shape[1]].copy()
esp.threshold_edgemap(E_segment,.30,edge_feature_row_breaks,abst_threshold=abst_threshold)
esp.spread_edgemap(E_segment,edge_feature_row_breaks,edge_orientations,spread_length=spread_length)
if d > bg_len:
bg = np.maximum(np.minimum(np.mean(neg_E[:,d-bg_len:d],
axis=1),
.4),
.01)
else:
bg = mean_bgd.copy()
P,C = tt.score_template_background_section(mean_template,
bg,E_segment)
detections.append((P+C,d))
return detections
def get_training_template(train_data_iter):
patterns = []
train_data_iter.reset_exp()
for datum_id in xrange(train_data_iter.num_data):
if datum_id % 10 == 0:
print datum_id
if train_data_iter.next(wait_for_positive_example=True,
compute_patterns=True,
max_template_length=40):
# the context length is 11
for p in train_data_iter.patterns:
pattern = p.copy()
esp.threshold_edgemap(pattern,.30,edge_feature_row_breaks,report_level=False,abst_threshold=abst_threshold)
esp.spread_edgemap(pattern,edge_feature_row_breaks,edge_orientations,spread_length=5)
patterns.append(pattern)
else:
break
_,_ ,\
registered_examples,template \
= et.simple_estimate_template(patterns)
return registered_examples, template
# important to think about the consequences of the
# comparison
mean_template_match = np.empty((quantile_level.shape[0],
len(all_patterns)))
for i in xrange(len(all_patterns)):
# get the background signal processing done
if all_bgds[i].shape[1] > 0:
# process the edges for each of the different thresholds
for j in xrange(quantile_levels.shape[0]):
a,tau_alpha_vals[i] = esp.threshold_edgemap(all_patterns[i],.30,edge_feature_row_breaks,
abst_threshold=)
esp.spread_edgemap(a,edge_feature_row_breaks,edge_orientations)
for i in xrange(len(all_patterns)):
a,tau_alpha_vals[i] = esp.threshold_edgemap(p,.30,edge_feature_row_breaks,report_level=True)
# threshold pattern edges
for i in xrange(len(patterns)):
esp.threshold_edgemap(patterns[i],.30,edge_feature_row_breaks)
esp.spread_edgemap(patterns[i],edge_feature_row_breaks,edge_orientations)
if bgds[i].shape[1] > 0:
esp.threshold_edgemap(bgds[i],.30,edge_feature_row_breaks)
esp.spread_edgemap(bgds[i],edge_feature_row_breaks,edge_orientations)
# compute background mean
bgds[i] = np.mean(bgds[i],axis=1)
all_def_templates = np.empty((def_range.shape[0],
tpm.def_template.shape[0],
tpm.def_template.shape[1]))
for d in xrange(def_range.shape[0]):
tpm.get_def_template(def_range[d])
all_def_templates[d] = tpm.def_template.copy()
optimal_detection_scores = -np.inf * np.ones((len(tuning_patterns_context),def_range.shape[0]))
optimal_detection_idx = np.zeros((len(tuning_patterns_context),def_range.shape[0]))
for c_id in xrange(len(tuning_patterns_context)):
print c_id
cur_context = tuning_patterns_context[c_id]
num_detections = cur_context.shape[1] - tpm.length_range[1]
win_length = tpm.length_range[1]
for d in xrange(num_detections):
E_window = cur_context[:,d:d+win_length].copy()
esp.threshold_edgemap(E_window,.30,edge_feature_row_breaks,report_level=False,abst_threshold=abst_threshold)
esp.spread_edgemap(E_window,edge_feature_row_breaks,edge_orientations,spread_length=3)
# base detection
for deformation in def_range:
def_template = all_def_templates[10+deformation]
P,C = tt.score_template_background_section(def_template,tpm.bg,E_window)
score = P+C
if score > optimal_detection_scores[c_id,deformation]:
optimal_detection_scores[c_id,deformation] = score
optimal_detection_idx[c_id,deformation] = d
#E
template=mean_template
bgd_length=26
mean_background=mean_bgd
#edge_feature_row_breaks
#edge_orientations
abst_threshold=abst_threshold
spread_length=3
pbgd = E[:,pattern_times[0][0]-bg_len:pattern_times[0][0]].copy()
pbgd2 = pbgd.copy()
esp.threshold_edgemap(pbgd2,.30,edge_feature_row_breaks,
abst_threshold=abst_threshold)
esp.spread_edgemap(pbgd2,edge_feature_row_breaks,edge_orientations,
spread_length=spread_length)
pbgd2 = np.mean(pbgd2,axis=1)
pbgd2 = np.maximum(np.minimum(pbgd2,.4),.1)
template_height,template_length = template.shape
num_detections = E.shape[1]-template_length+1
E_background, estimated_background_idx = self._get_E_background(E,num_detections,bgd_length, mean_background,
edge_feature_row_breaks,
edge_orientations,
abst_threshold=abst_threshold,
spread_length=spread_length)
# found that
for frame_id in xrange(bg_len,E_background.shape[1]):
bg_seg = E[:,frame_id-bg_len:frame_id].copy()
cPickle.dump(tune_data_iter,output)
output.close()
aar_patterns = []
train_data_iter.reset_exp()
for datum_id in xrange(train_data_iter.num_data):
if datum_id % 10 == 0:
print datum_id
if train_data_iter.next(wait_for_positive_example=True,
compute_patterns=True,
max_template_length=40):
# the context length is 11
for p in train_data_iter.patterns:
pattern = p.copy()
esp.threshold_edgemap(pattern,.30,edge_feature_row_breaks,report_level=False,abst_threshold=abst_threshold)
esp.spread_edgemap(pattern,edge_feature_row_breaks,edge_orientations,spread_length=2)
aar_patterns.append(pattern)
else:
break
_,_ ,\
registered_examples,template \
= et.simple_estimate_template(aar_patterns)
np.save('aar_template053112',template)
np.save('registered_examples_aar053112',registered_examples)
mean_background = np.load(root_path+'Experiments/050812/mean_background_liy051012.npy')
data_iter = tune_data_iter
import template_speech_rec.classification as cl
def get_roc_coarse(data_iter, classifier,
allowed_overlap = .2,
edge_feature_row_breaks= np.array([ 0.,
45.,
90.,
138.,
186.,
231.,
276.,
321.,
366.]),
edge_orientations=np.array([[ 1., 0.],
[-1., 0.],
[ 0., 1.],
[ 0., -1.],
[ 1., 1.],
[-1., -1.],
[ 1., -1.],
[-1., 1.]]),
abst_threshold=np.array([.025,.025,.015,.015,
.02,.02,.02,.02]),
spread_radius=3):
"""
Find the appropriate threshold for the coarse classifier, this
should be run on tuning data, and then we can get a level for the
tradeoff between false positives and false negatives the first
pair is the roc curve for the count test and the second is for the
coarse likelihood test
The way this works is that we find the scores for each window and
then we rank them and remove overlapping windows that are lower
rank if the overlap is below a certain percentage
We are assuming that the classifier has been implemented and initialized properly
"""
num_frames = 0
all_positive_counts = []
all_positive_likes = []
all_negative_counts = []
all_negative_likes = []
data_iter.reset_exp()
for datum_id in xrange(data_iter.num_data):
if datum_id % 10 == 0:
print "working on example", datum_id
if data_iter.next(compute_pattern_times=True,
max_template_length=classifier.window[1]):
pattern_times = data_iter.pattern_times
num_detections = data_iter.E.shape[1] - classifier.window[1]
num_frames += data_iter.E.shape[1]
coarse_count_scores = -np.inf * np.ones(num_detections)
coarse_like_scores = -np.inf * np.ones(num_detections)
for d in xrange(num_detections):
E_segment = data_iter.E[:,d:d+classifier.window[1]].copy()
esp.threshold_edgemap(E_segment,.30,edge_feature_row_breaks,report_level=False,abst_threshold=abst_threshold)
esp.spread_edgemap(E_segment,edge_feature_row_breaks,edge_orientations,spread_length=3)
coarse_count_scores[d] = classifier.coarse_score_count(E_segment)
coarse_like_scores[d] = classifier.coarse_score_like_no_bg(E_segment)
# now we get the indices sorted
count_indices = remove_overlapping_examples(np.argsort(coarse_count_scores),
classifier.coarse_length,
int(allowed_overlap*classifier.coarse_length))
like_indices = remove_overlapping_examples(np.argsort(coarse_like_scores),
classifier.coarse_length,
int(allowed_overlap*classifier.coarse_length))
positive_counts, negative_counts = get_pos_neg_scores(count_indices,pattern_times,
coarse_count_scores)
positive_likes, negative_likes = get_pos_neg_scores(like_indices,pattern_times,
coarse_like_scores)
all_positive_counts.extend(positive_counts)
all_negative_counts.extend(negative_counts)
all_positive_likes.extend(positive_likes)
all_negative_likes.extend(negative_likes)
count_roc = get_roc(np.sort(all_positive_counts)[::-1],
np.sort(all_negative_counts)[::-1],
num_frames)
like_roc = get_roc(np.sort(all_positive_likes)[::-1],
np.sort(all_negative_likes)[::-1],
num_frames)
return count_roc, like_roc
patterns = exp.get_patterns(E,phns,phn_times,s)
patterns_context = exp.get_patterns(E,phns,phn_times,s,context=True,template_length=33)
bgds = exp.get_pattern_bgds(E,phns,phn_times,s,bg_len)
fronts_backs = exp.get_pattern_fronts_backs(E,phns,phn_times,s,bg_len)
E_avg.add_frames(E,edge_feature_row_breaks,
edge_orientations,abst_threshold)
# threshold pattern edges
for i in xrange(len(patterns)):
all_raw_patterns_context.append(patterns_context[i].copy())
all_raw_bgds.append(bgds[i].copy())
_, edge_thresholds = esp.threshold_edgemap(patterns[i],.30,edge_feature_row_breaks,report_level=True,abst_threshold=abst_threshold)
# we record both the thresholds
# and the length to see if there is a relationship
pattern_edge_thresholds.append(edge_thresholds)
pattern_lengths.append(patterns[i].shape[1])
esp.spread_edgemap(patterns[i],edge_feature_row_breaks,edge_orientations,spread_length=5)
if bgds[i].shape[1] > 0:
_,edge_thresholds = esp.threshold_edgemap(bgds[i],.30,edge_feature_row_breaks,report_level=True,abst_threshold=abst_threshold)
bgd_edge_thresholds.append(edge_thresholds)
esp.spread_edgemap(bgds[i],edge_feature_row_breaks,edge_orientations,spread_length=5)
# compute background mean
bgds[i] = np.mean(bgds[i],axis=1)
# impose floor and ceiling constraints on values
bgds[i] = np.maximum(np.minimum(bgds[i],.4),.05)
else:
bgds[i] = np.random.rand(patterns[i].shape[0]).reshape(patterns[i].shape[0],1)
bgds[i] = np.mean(bgds[i],axis=1)
bgds[i] = np.maximum(np.minimum(bgds[i],.4),.05)
empty_bgds.append(pattern_num)
pattern_num += len(patterns)
all_patterns.extend(patterns)
mean_background = E_avg.E.copy()
mean_background = np.maximum(np.minimum(mean_background,.4),.05)
for pattern in xrange(len(all_patterns)):
# do the thresholding
esp.threshold_edgemap(all_patterns[pattern],.30,
train_data_iter.edge_feature_row_breaks,
report_level=False,
abst_threshold=train_data_iter.abst_threshold)
esp.spread_edgemap(all_patterns[pattern],
train_data_iter.edge_feature_row_breaks,
train_data_iter.edge_orientations,spread_length=5)
template_height, template_length, \
registered_templates,mean_template \
= et.simple_estimate_template(all_patterns,
template_length=33)
template_shape = np.array([template_height,template_length])
np.save('mean_template050612',mean_template)
np.save('template_shape050612',template_shape)
#########################################
#
num_detections = data_iter.E.shape[1] - classifier.window[1]
num_frames += data_iter.E.shape[1]
scores_adapt_bg = -np.inf * np.ones(num_detections)
scores_mel = -np.inf * np.ones(num_detections)
bg = mean_background.copy()
E_mel,e_breaks_mel,\
e_orientations_mel= esp.get_edgemap_no_threshold(train_data_iter.s,
train_data_iter.sample_rate,
train_data_iter.num_window_samples,
train_data_iter.num_window_step_samples,
train_data_iter.fft_length,8000,7,
use_mel = True)
for d in xrange(num_detections):
E_segment = data_iter.E[:,d:d+classifier.window[1]].copy()
esp.threshold_edgemap(E_segment,.30,edge_feature_row_breaks,report_level=False,abst_threshold=abst_threshold)
esp.spread_edgemap(E_segment,edge_feature_row_breaks,edge_orientations,spread_length=3)
E_segment_mel = E_mel[:,d:d+classifier.window[1]].copy()
esp.threshold_edgemap(E_segment_mel,.30,e_breaks_mel,report_level=False,abst_threshold=abst_threshold)
esp.spread_edgemap(E_segment_mel,e_breaks_mel,e_orientations_mel,spread_length=3)
bg = np.minimum(.4,
np.maximum(np.mean(E_segment,axis=1),
.1))
scores_adapt_bg[d] = classifier.score(E_segment,bg)
scores_mel[d] = classifier.score_no_bg(E_segment_mel)
# now we get the indices sorted
indices_adapt_bg = cl.remove_overlapping_examples(np.argsort(scores_adapt_bg)[::-1],
classifier.window[1],
int(allowed_overlap*classifier.window[1]))
indices_mel = cl.remove_overlapping_examples(np.argsort(scores_mel)[::-1],
classifier.window[1],
int(allowed_overlap*classifier.window[1]))
E,edge_feature_row_breaks,\
edge_orientations= texp.get_edgemap_no_threshold(train_data_iter.s)
abst_threshold = np.array([0.025,0.025,0.015,0.015,
0.02,0.02,0.02,0.02])
del(E)
del(s)
for p in all_patterns[1:]:
esp.threshold_edgemap(p,.30,edge_feature_row_breaks,report_level=False,abst_threshold=abst_threshold)
esp.spread_edgemap(p,edge_feature_row_breaks,edge_orientations,spread_length=5)
template_height, template_length, \
registered_templates,mean_template \
= et.simple_estimate_template(all_patterns)
template_shape = np.array([template_height,template_length])
np.save('mean_template_piy050912',mean_template)
np.save('template_shape_piy050912',template_shape)
np.save('registered_templates_piy050912',registered_templates)
mean_template = np.load('mean_template_piy050912.npy')
template_shape = np.load('template_shape_piy050912.npy')
# time to get a baseline for how well the pattern applies to examples