def cluster_faces(name, img_list = 'all-scores-faces-list-new'):
root = root_all + 'face_recognition/'+ '@'.join(name.split('-'))
cnn_root = root_all + 'face_recognition_CNN/'+name + '/'
f = open(cnn_root + 'waldo_normalized_combined.cPickle','r')
combined_matrix = cPickle.load(f)
f.close()
diag = np.diag(combined_matrix)
diag = diag[:, np.newaxis]
normalize_matrix = np.dot(diag, np.transpose(diag))
normalize_matrix = np.sqrt(normalize_matrix)
affinity_matrix = np.divide(combined_matrix, normalize_matrix)
min_ = np.min(affinity_matrix); max_ = np.max(affinity_matrix)
affinity_matrix = (affinity_matrix - min_) / (max_ - min_)
f = SpectralClustering(affinity='precomputed', n_clusters=min(8, affinity_matrix.shape[0] - 1), eigen_solver = 'arpack', n_neighbors=min(5, affinity_matrix.shape[0]))
a = f.fit_predict(affinity_matrix)
groups = {}
temp = zip(a, xrange(len(a)))
for i in temp:
if i[0] not in groups:
groups[i[0]] = [i[1]]
else:
groups[i[0]].append(i[1])
unique_person_id = []
for kk in groups:
min_similarity = np.Inf
max_similarity = -np.Inf
mean_similarity = 0
this_group_ids = groups[kk]
for j in xrange(len(this_group_ids)):
for i in xrange(j+1, len(this_group_ids)):
temp = combined_matrix[this_group_ids[i],this_group_ids[j]]
if temp < min_similarity:
min_similarity = temp
if temp > max_similarity:
max_similarity = temp
mean_similarity += temp
mean_similarity /= max(1, len(this_group_ids)*(len(this_group_ids) - 1) / 2)
print len(this_group_ids), mean_similarity, max_similarity, min_similarity
print mean_similarity
if mean_similarity > 0.4 and len(this_group_ids) > 1:
unique_person_id.append(kk)
important_person = []
for i in unique_person_id:
important_person.append([i, len(groups[i])])
important_person.sort(key = lambda x:x[1], reverse=True)
in_path = root + '-dir/' + img_list
imgs_list = []
with open(in_path, 'r') as data:
for line in data:
line = line[:-1]
imgs_list.append(line.split('/')[-1])
temp = zip(a, imgs_list)
face_groups = {}
for i in temp:
if i[0] not in face_groups:
face_groups[i[0]] = [i[1]]
else:
face_groups[i[0]].append(i[1])
create_face_group_html(name, face_groups, important_person)
f = open(cnn_root + 'waldo_group_combined.cPickle','w')
cPickle.dump([face_groups, important_person], f)
f.close()
def cluster_faces_new(name = '9_68821308@N00', img_list = 'all-scores-faces-list'):
#cnn_root = root_all + 'face_recognition_CNN/'+('-').join(name.split('@')) + '/'
in_path = root + name + '-dir/all-scores-faces-list-new-pw.mat'
try:
temp = sio.loadmat(in_path)
except:
in_path = root + name + '-dir/all-scores-faces-list-pw.mat'
temp = sio.loadmat(in_path)
matrix = temp['matrix']
if len(matrix) == 0:
out_root = root + name + '-dir/'
f = open(out_root + '_20_group.cPickle','wb')
cPickle.dump([{}, []], f)
f.close()
return
#print matrix
'''1st method: exponential'''
#a_std = np.std(matrix)
#beta = 1.0
#affinity_matrix = np.exp(beta * matrix / a_std)
'''2nd method: sigmoid'''
#affinity_matrix = 1 / (1 + np.exp(-matrix))
'''3rd method: normalize'''
if len(matrix) == 1:
imgs_list = []
with open(in_path, 'r') as data:
for line in data:
line = line[:-1]
imgs_list.append(line.split('/')[-1])
out_root = root + name + '-dir/'
f = open(out_root + '_20_group.cPickle','wb')
cPickle.dump([{img_list[0]:1}, []], f)
f.close()
return
matrix_ori = matrix
min_ = np.min(matrix)
matrix = matrix - min_
diag = np.diag(matrix)
diag = diag[:, np.newaxis]
normalize_matrix = np.dot(diag, np.transpose(diag))
normalize_matrix = np.sqrt(normalize_matrix)
affinity_matrix = np.divide(matrix, normalize_matrix)
min_ = np.min(affinity_matrix); max_ = np.max(affinity_matrix)
affinity_matrix = (affinity_matrix - min_) / (max_ - min_)
f = SpectralClustering(affinity='precomputed', n_clusters=min(30, affinity_matrix.shape[0]/2), eigen_solver = 'arpack', n_neighbors=min(10, affinity_matrix.shape[0]))
#b = f.fit(affinity_matrix)
a = f.fit_predict(affinity_matrix)
mean_similarities = {}
groups_notyet = {}
temp = zip(a, xrange(len(a)))
for i in temp:
if i[0] not in groups_notyet:
groups_notyet[i[0]] = [i[1]]
else:
groups_notyet[i[0]].append(i[1])
groups_already = {}
dump_low_mean_(matrix_ori, groups_already, groups_notyet)
while len(groups_notyet) > 1:
keys = groups_notyet.keys()
max_ = [-1,-1]
max_median = -np.Inf
for i in xrange(len(keys)):
for j in xrange(i + 1, len(keys)):
group_i = groups_notyet[keys[i]]
group_j = groups_notyet[keys[j]]
temp = cal_median_distance(matrix_ori, group_i, group_j)
#print temp
if temp > max_median:
max_median = temp
#print temp
max_ = [keys[i],keys[j]]
#print
#if max_[0] == -1:
# break
#print matrix_ori[np.ix_(groups_notyet[max_[0]], groups_notyet[max_[1]])]
temp = cal_median_distance_ingroup(matrix_ori, groups_notyet[max_[0]] + groups_notyet[max_[1]])
#print temp
#if cal_median_distance_ingroup(matrix_ori, groups_notyet[max_[0]] + groups_notyet[max_[1]]) > -10:
if cal_median_distance_ingroup(matrix_ori, groups_notyet[max_[0]] + groups_notyet[max_[1]]) > -10:
temp = groups_notyet[max_[0]] + groups_notyet[max_[1]]
groups_notyet.pop(max_[0], None)
groups_notyet.pop(max_[1], None)
groups_notyet[max_[0]] = temp
else:
groups_already[max_[0]] = groups_notyet[max_[0]]
groups_already[max_[1]] = groups_notyet[max_[1]]
groups_notyet.pop(max_[0], None)
groups_notyet.pop(max_[1], None)
#print len(groups_notyet)
for i in groups_notyet:
groups_already[i] = groups_notyet[i]
#print len(groups_already), groups_already
unique_person_id = []
for kk in groups_already:
min_similarity = np.Inf
max_similarity = -np.Inf
mean_similarity = 0
#median_similarity = []
this_group_ids = groups_already[kk]
for j in xrange(len(this_group_ids)):
for i in xrange(j+1, len(this_group_ids)):
temp = matrix_ori[this_group_ids[i],this_group_ids[j]]
if temp < min_similarity:
min_similarity = temp
if temp > max_similarity:
max_similarity = temp
#mean_similarity += np.log10(temp)
mean_similarity += temp
#median_similarity.append(temp)
mean_similarity /= max(1, len(this_group_ids)*(len(this_group_ids) - 1) / 2)
mean_similarities[kk] = mean_similarity
#if len(median_similarity) >= 1:
# median_ = np.median(np.array(median_similarity))
#else:
# median_ = 0
#mean_similarities[kk] = median_
#print len(this_group_ids), mean_similarity, max_similarity, min_similarity
if mean_similarity > 0 and len(this_group_ids) > 1:
#if median_ > 0 and len(this_group_ids) > 1:
unique_person_id.append(kk)
important_person = []
for i in unique_person_id:
important_person.append([i, len(groups_already[i])])
important_person.sort(key = lambda x:x[1], reverse=True)
in_path = root + name + '-dir/' + img_list
imgs_list = []
with open(in_path, 'r') as data:
for line in data:
line = line[:-1]
imgs_list.append(line.split('/')[-1])
a = np.zeros(len(imgs_list))
for i in groups_already:
for j in groups_already[i]:
a[j] = i
temp = zip(a, imgs_list)
face_groups = {}
for i in temp:
if i[0] not in face_groups:
face_groups[i[0]] = [i[1]]
else:
face_groups[i[0]].append(i[1])
create_retrieval_image(name, matrix)
create_face_group_html(name, face_groups, important_person, mean_similarities)
out_root = root + name + '-dir/'
f = open(out_root + '_20_group.cPickle','wb')
cPickle.dump([face_groups, important_person], f)
f.close()
