line = line[:-2]
data = line.split("\t")
assert (len(data) == 3)
id_image = data[0]
tags = [x.lower() for x in data[2].split(" ")]
final_tags = [t for t in tags if t in vocab]
id_tags[id_image] = final_tags
N_images = len(id_tags)
print "N images: ", N_images
# build tag matrix
tagmatrix = np.zeros((N_images, N_tags), dtype=np.int8)
for i, id_im in enumerate(id_images):
tags = id_tags[id_im]
if len(tags) > 0:
idx = [bisect_index(vocab, t) for t in tags]
tagmatrix[i, idx] = True
# save output
fout = h5py.File(resultfile, 'w')
fout['tagmatrix'] = tagmatrix
fout['vocab'] = vocab
fout['id_images'] = id_images
fout.close()
def process(options, testCollection, trainCollection, annotationName, feature):
rootpath = options.rootpath
k = options.k
distance = options.distance
overwrite = options.overwrite
testset = testCollection
onlytest = options.onlytest
nnName = distance + "knn"
resultfile_train = os.path.join(rootpath, trainCollection, 'TagProp-data', trainCollection, '%s,%s,%d'%(feature,nnName,k), 'nn_train.h5')
resultfile_test = os.path.join(rootpath, testCollection, 'TagProp-data', testset, trainCollection, annotationName, '%s,%s,%d'%(feature,nnName,k), 'nn_test.h5')
if (not onlytest and checkToSkip(resultfile_train, overwrite)) or checkToSkip(resultfile_test, overwrite):
return 0
testSet = readImageSet(testCollection, testset, rootpath)
trainSet = readImageSet(trainCollection, trainCollection, rootpath)
testSet.sort()
trainSet.sort()
#train_feat_dir = os.path.join(rootpath, trainCollection, 'FeatureData', feature)
#train_feat_file = BigFile(train_feat_dir)
tagger = NAME_TO_TAGGER["preknn"](trainCollection, annotationName, feature, distance, rootpath=rootpath, k=1001)
printStatus(INFO, '%d test images, %d train images' % (len(testSet), len(trainSet)))
# allocate train -> train nearest neighbors
if not onlytest:
printStatus(INFO, 'Allocating NN, NND matrices')
NN = np.zeros((len(trainSet), k+1), dtype=np.int32)
NND = np.zeros((len(trainSet), k+1))
printStatus(INFO, 'Filling NN, NND matrices')
for i,id_img in enumerate(trainSet):
neighbors = tagger._get_neighbors(content=None, context='%s,%s' % (trainCollection, id_img))
if len(neighbors) < k+1:
printStatus(INFO, 'ERROR: id_img %s has %d < %d neighbors!' % (id_img, len(neighbors), k+1))
sys.exit(1)
NNrow = np.array([bisect_index(trainSet, x[0]) for x in neighbors])
NNDrow = np.array([x[1] for x in neighbors])
NN[i,:] = NNrow[0:k+1]
NND[i,:] = NNDrow[0:k+1]
if i % 1000 == 0:
printStatus(INFO, '%d / %d images' % (i, len(trainSet)))
printStatus(INFO, 'Saving train matrices to file %s' % (resultfile_train))
makedirsforfile(resultfile_train)
fout = h5py.File(resultfile_train, 'w')
fout['NN'] = NN
fout['NND'] = NND
fout['trainSet'] = trainSet
fout['concepts'] = tagger.concepts
fout.close()
del NN
del NND
# allocate test -> train nearest neighbors
printStatus(INFO, 'Allocating NNT, NNDT matrices')
NNT = np.zeros((len(testSet), k), dtype=np.int32)
NNDT = np.zeros((len(testSet), k))
printStatus(INFO, 'Filling NNT, NNDT matrices')
for i,id_img in enumerate(testSet):
neighbors = tagger._get_neighbors(content=None, context='%s,%s' % (testCollection, id_img))
if len(neighbors) < k:
printStatus(INFO, 'ERROR: id_img %s has %d < %d neighbors!' % (id_img, len(neighbors), k))
sys.exit(1)
NNrow = np.array([bisect_index(trainSet, x[0]) for x in neighbors])
NNDrow = np.array([x[1] for x in neighbors])
NNT[i,:] = NNrow[0:k]
NNDT[i,:] = NNDrow[0:k]
if i % 1000 == 0:
printStatus(INFO, '%d / %d images' % (i, len(testSet)))
printStatus(INFO, 'Saving test matrices to file %s' % (resultfile_test))
makedirsforfile(resultfile_test)
fout = h5py.File(resultfile_test, 'w')
fout['NNT'] = NNT
fout['NNDT'] = NNDT
fout['trainSet'] = trainSet
fout['testSet'] = testSet
fout['concepts'] = tagger.concepts
fout.close()
def process(options, testCollection, trainCollection, annotationName, feature):
rootpath = options.rootpath
k = options.k
distance = options.distance
overwrite = options.overwrite
testset = testCollection
onlytest = options.onlytest
nnName = distance + "knn"
resultfile_train = os.path.join(rootpath, trainCollection, 'TagProp-data',
trainCollection,
'%s,%s,%d' % (feature, nnName, k),
'nn_train.h5')
resultfile_test = os.path.join(rootpath, testCollection, 'TagProp-data',
testset, trainCollection, annotationName,
'%s,%s,%d' % (feature, nnName, k),
'nn_test.h5')
if (not onlytest
and checkToSkip(resultfile_train, overwrite)) or checkToSkip(
resultfile_test, overwrite):
return 0
testSet = readImageSet(testCollection, testset, rootpath)
trainSet = readImageSet(trainCollection, trainCollection, rootpath)
testSet.sort()
trainSet.sort()
#train_feat_dir = os.path.join(rootpath, trainCollection, 'FeatureData', feature)
#train_feat_file = BigFile(train_feat_dir)
tagger = NAME_TO_TAGGER["preknn"](trainCollection,
annotationName,
feature,
distance,
rootpath=rootpath,
k=1001)
printStatus(
INFO,
'%d test images, %d train images' % (len(testSet), len(trainSet)))
# allocate train -> train nearest neighbors
if not onlytest:
printStatus(INFO, 'Allocating NN, NND matrices')
NN = np.zeros((len(trainSet), k + 1), dtype=np.int32)
NND = np.zeros((len(trainSet), k + 1))
printStatus(INFO, 'Filling NN, NND matrices')
for i, id_img in enumerate(trainSet):
neighbors = tagger._get_neighbors(content=None,
context='%s,%s' %
(trainCollection, id_img))
if len(neighbors) < k + 1:
printStatus(
INFO, 'ERROR: id_img %s has %d < %d neighbors!' %
(id_img, len(neighbors), k + 1))
sys.exit(1)
NNrow = np.array([bisect_index(trainSet, x[0]) for x in neighbors])
NNDrow = np.array([x[1] for x in neighbors])
NN[i, :] = NNrow[0:k + 1]
NND[i, :] = NNDrow[0:k + 1]
if i % 1000 == 0:
printStatus(INFO, '%d / %d images' % (i, len(trainSet)))
printStatus(INFO,
'Saving train matrices to file %s' % (resultfile_train))
makedirsforfile(resultfile_train)
fout = h5py.File(resultfile_train, 'w')
fout['NN'] = NN
fout['NND'] = NND
fout['trainSet'] = trainSet
fout['concepts'] = tagger.concepts
fout.close()
del NN
del NND
# allocate test -> train nearest neighbors
printStatus(INFO, 'Allocating NNT, NNDT matrices')
NNT = np.zeros((len(testSet), k), dtype=np.int32)
NNDT = np.zeros((len(testSet), k))
printStatus(INFO, 'Filling NNT, NNDT matrices')
for i, id_img in enumerate(testSet):
neighbors = tagger._get_neighbors(content=None,
context='%s,%s' %
(testCollection, id_img))
if len(neighbors) < k:
printStatus(
INFO, 'ERROR: id_img %s has %d < %d neighbors!' %
(id_img, len(neighbors), k))
sys.exit(1)
NNrow = np.array([bisect_index(trainSet, x[0]) for x in neighbors])
NNDrow = np.array([x[1] for x in neighbors])
NNT[i, :] = NNrow[0:k]
NNDT[i, :] = NNDrow[0:k]
if i % 1000 == 0:
printStatus(INFO, '%d / %d images' % (i, len(testSet)))
printStatus(INFO, 'Saving test matrices to file %s' % (resultfile_test))
makedirsforfile(resultfile_test)
fout = h5py.File(resultfile_test, 'w')
fout['NNT'] = NNT
fout['NNDT'] = NNDT
fout['trainSet'] = trainSet
fout['testSet'] = testSet
fout['concepts'] = tagger.concepts
fout.close()
def process(options, workingCollection, feature):
rootpath = options.rootpath
k_ratio = options.kratio
distance = options.distance
overwrite = options.overwrite
nnName = distance + "knn"
resultfile = os.path.join(rootpath, workingCollection, 'LaplacianI', workingCollection, '%s,%s,%f'%(feature,nnName,k_ratio), 'laplacianI.mat')
if checkToSkip(resultfile, overwrite):
return 0
workingSet = readImageSet(workingCollection, workingCollection, rootpath)
workingSet.sort()
tot_images = len(workingSet)
printStatus(INFO, '%d images' % (tot_images))
K_neighs = int(math.floor(len(workingSet) * k_ratio))
printStatus(INFO, '%d nearest neighbor per image (ratio = %f)' % (K_neighs, k_ratio))
printStatus(INFO, 'Allocating I,J,V arrays')
I = np.zeros((K_neighs * tot_images * 2))
J = np.zeros((K_neighs * tot_images * 2))
V = np.zeros((K_neighs * tot_images * 2))
n_entries = 0
# distances
printStatus(INFO, 'Starting to fill I,J,V arrays')
for i in xrange(tot_images):
try:
neighbors = _get_neighbors('%s,%s' % (workingCollection, workingSet[i]), rootpath, K_neighs*2, feature, distance)
# remove images with features but not in the working set
NNrow = []
NNDrow = []
new_neighs = []
for x in neighbors:
try:
NNrow.append(bisect_index(workingSet, x[0]))
NNDrow.append(x[1])
new_neighs.append(x)
except ValueError:
pass
#NNrow = np.array([bisect_index(workingSet, x[0]) for x in neighbors])
#NNDrow = np.array([x[1] for x in neighbors])
NNrow = np.array(NNrow)
NNDrow = np.array(NNDrow)
neighbors = new_neighs[0:K_neighs]
except ValueError:
printStatus(INFO, 'ERROR: id_img %s has non-standard format!' % (workingSet[i]))
sys.exit(1)
if len(neighbors) < K_neighs:
printStatus(INFO, 'ERROR: id_img %s has %d < %d neighbors!' % (workingSet[i], len(neighbors), K_neighs))
sys.exit(1)
if (i+1) % 1000 == 0:
printStatus(INFO, '%d / %d done' % (i+1, tot_images))
for k in xrange(K_neighs):
if i != int(NNrow[k]): # -1 zero on the diagonal for a later step
I[n_entries] = i
J[n_entries] = int(NNrow[k]) # -1
V[n_entries] = NNDrow[k]
n_entries += 1
I[n_entries] = int(NNrow[k]) # -1
J[n_entries] = i
V[n_entries] = NNDrow[k]
n_entries += 1
I = I[0:n_entries]
J = J[0:n_entries]
V = V[0:n_entries]
printStatus(INFO, 'Removing duplicates')
ind = np.lexsort((V,J,I))
I = I[ind]
J = J[ind]
V = V[ind]
a = np.concatenate([I.reshape(1, len(I)), J.reshape(1, len(J))], axis=0).T
b = np.ascontiguousarray(a).view(np.dtype((np.void, a.dtype.itemsize * a.shape[1])))
del a
_, idx = np.unique(b, return_index=True)
del b
I = I[idx]
J = J[idx]
V = V[idx]
printStatus(INFO, 'Computing the final laplacian matrix')
sigma = np.median(V) ** 2.;
printStatus(INFO, 'Estimated sigma^2 = %f' % sigma)
V = np.exp(-V / sigma)
matrix = coo_matrix((V, (I, J)), shape=(tot_images, tot_images)).tocsr()
new_diag = matrix.sum(axis=0).T
V = -V
I_add = np.zeros((tot_images))
J_add = np.zeros((tot_images))
V_add = np.zeros((tot_images))
for i,v in enumerate(new_diag):
I_add[i] = i
J_add[i] = i
V_add[i] = v
I = np.append(I, I_add)
J = np.append(J, J_add)
V = np.append(V, V_add)
matrix = coo_matrix((V, (I, J)), shape=(tot_images, tot_images)).tolil()
printStatus(INFO, 'Saving laplacian matrix to %s' % resultfile)
makedirsforfile(resultfile)
scipy.io.savemat(resultfile, {'im_similarity' : matrix, 'sigma' : sigma})
def process(options, workingCollection, annotationName, feature, outputpkl):
rootpath = options.rootpath
distance = options.distance
overwrite = options.overwrite
k_ratio = options.kratio
ratio_cs = options.ratiocs
lambda1 = options.lambda1
lambda2 = options.lambda2
outputonlytest = options.outputonlytest
rawtagmatrix = options.rawtagmatrix
modelName = "robustpca"
nnName = distance + "knn"
printStatus(INFO, "Starting RobustPCA %s,%s,%s,%s,%f,%f,%f" % (workingCollection, annotationName, feature, nnName, k_ratio, lambda1, lambda2))
if rawtagmatrix:
printStatus(INFO, "Using raw tag matrix.")
else:
printStatus(INFO, "Using preprocessed tag matrix.")
resultfile = os.path.join(outputpkl)
resultfile_robustpca = os.path.join(rootpath, workingCollection, 'RobustPCA-Prediction', '%s,%s,%f,%f,%f,%d'%(feature,nnName,lambda1,lambda2,k_ratio,rawtagmatrix), 'prediction.mat')
if checkToSkip(resultfile_robustpca, overwrite):
only_dump = True
else:
only_dump = False
if not rawtagmatrix:
tagmatrix_file = os.path.join(rootpath, workingCollection, 'RobustPCA', '%s,%s,%f'%(feature,nnName,DEFAULT_K_PROP), 'tagmatrix.h5')
if not os.path.exists(tagmatrix_file):
printStatus(INFO, "Tag matrix file not found at %s Did you run robustpca_preprocessing.py?" % (tagmatrix_file))
sys.exit(1)
else:
tagmatrix_file = os.path.join(rootpath, workingCollection, 'TextData', "lemm_wordnet_freq_tags.h5")
if not os.path.exists(tagmatrix_file):
printStatus(INFO, 'Tag matrix file not found in %s Did you run wordnet_frequency_tags.py?' % (tagmatrix_file))
sys.exit(1)
laplacianI_file = os.path.join(rootpath, workingCollection, 'LaplacianI', workingCollection, '%s,%s,%f'%(feature,nnName,k_ratio), 'laplacianI.mat')
if not os.path.exists(laplacianI_file):
printStatus(INFO, "LaplacianI file not found at %s Did you run laplacian_images.py?" % (laplacianI_file))
sys.exit(1)
laplacianT_file = os.path.join(rootpath, workingCollection, 'LaplacianT', '%f'%(ratio_cs), 'laplacianT.mat')
if not os.path.exists(laplacianT_file):
printStatus(INFO, "LaplacianT file not found at %s Did you run laplacian_tags.py?" % (laplacianT_file))
sys.exit(1)
# being learning
script = """
rpca_path = 'transduction_based/robustpca/';
addpath(rpca_path);
addpath([rpca_path, 'fast_svd/']);
tagmatrix = sparse(double(h5read('%s', '/tagmatrix')));
load('%s');
load('%s');
lambda1 = %f;
lambda2 = %f;
maxIters = 50;
precision = 1e-4;
mu_start = 1.;
parpool('local', 4);
[P,E]=robustpca(tagmatrix, lambda1, lambda2, tag_similarity, im_similarity, maxIters, precision, mu_start);
""" % (tagmatrix_file, laplacianI_file, laplacianT_file, lambda1, lambda2)
script += """
delete(gcp);
save('%s', 'P', 'E', 'lambda1', 'lambda2', '-v7.3');
exit;
""" % resultfile_robustpca
if not only_dump:
printStatus(INFO, "starting learning")
makedirsforfile(resultfile_robustpca)
call_matlab(script)
if checkToSkip(resultfile, overwrite):
return 0
# save results in pkl format
printStatus(INFO, "Dump results in pkl format at %s" % resultfile)
concepts = readConcepts(workingCollection, annotationName, rootpath)
if outputonlytest:
testset_id_images = readImageSet(workingCollection.split('+')[1], workingCollection.split('+')[1], rootpath)
testset_id_images.sort()
id_images = readImageSet(workingCollection, workingCollection, rootpath)
id_images.sort()
# concepts mapping
robustpca_output = h5py.File(resultfile_robustpca, 'r')
tagprop_input = h5py.File(tagmatrix_file, 'r')
mapping = getVocabMap(list(tagprop_input['vocab'][:]),concepts)
predicted_tagmatrix = robustpca_output['P'][:,mapping]
if outputonlytest:
idx = np.array([bisect_index(id_images, x) for x in testset_id_images])
final_tagmatrix = predicted_tagmatrix[idx, :]
assert(final_tagmatrix.shape[0] == idx.shape[0])
id_images = testset_id_images
else:
final_tagmatrix = predicted_tagmatrix
makedirsforfile(resultfile)
with open(resultfile, 'w') as f:
pickle.dump({'concepts':concepts, 'id_images': id_images, 'scores':final_tagmatrix}, f, pickle.HIGHEST_PROTOCOL)
def process(options, workingCollection, annotationName, feature, outputpkl):
rootpath = options.rootpath
distance = options.distance
overwrite = options.overwrite
k_ratio = options.kratio
ratio_cs = options.ratiocs
lambda1 = options.lambda1
lambda2 = options.lambda2
outputonlytest = options.outputonlytest
rawtagmatrix = options.rawtagmatrix
modelName = "robustpca"
nnName = distance + "knn"
printStatus(
INFO, "Starting RobustPCA %s,%s,%s,%s,%f,%f,%f" %
(workingCollection, annotationName, feature, nnName, k_ratio, lambda1,
lambda2))
if rawtagmatrix:
printStatus(INFO, "Using raw tag matrix.")
else:
printStatus(INFO, "Using preprocessed tag matrix.")
resultfile = os.path.join(outputpkl)
resultfile_robustpca = os.path.join(
rootpath, workingCollection, 'RobustPCA-Prediction',
'%s,%s,%f,%f,%f,%d' %
(feature, nnName, lambda1, lambda2, k_ratio, rawtagmatrix),
'prediction.mat')
if checkToSkip(resultfile_robustpca, overwrite):
only_dump = True
else:
only_dump = False
if not rawtagmatrix:
tagmatrix_file = os.path.join(
rootpath, workingCollection, 'RobustPCA',
'%s,%s,%f' % (feature, nnName, DEFAULT_K_PROP), 'tagmatrix.h5')
if not os.path.exists(tagmatrix_file):
printStatus(
INFO,
"Tag matrix file not found at %s Did you run robustpca_preprocessing.py?"
% (tagmatrix_file))
sys.exit(1)
else:
tagmatrix_file = os.path.join(rootpath, workingCollection, 'TextData',
"lemm_wordnet_freq_tags.h5")
if not os.path.exists(tagmatrix_file):
printStatus(
INFO,
'Tag matrix file not found in %s Did you run wordnet_frequency_tags.py?'
% (tagmatrix_file))
sys.exit(1)
laplacianI_file = os.path.join(rootpath, workingCollection, 'LaplacianI',
workingCollection,
'%s,%s,%f' % (feature, nnName, k_ratio),
'laplacianI.mat')
if not os.path.exists(laplacianI_file):
printStatus(
INFO,
"LaplacianI file not found at %s Did you run laplacian_images.py?"
% (laplacianI_file))
sys.exit(1)
laplacianT_file = os.path.join(rootpath, workingCollection, 'LaplacianT',
'%f' % (ratio_cs), 'laplacianT.mat')
if not os.path.exists(laplacianT_file):
printStatus(
INFO,
"LaplacianT file not found at %s Did you run laplacian_tags.py?" %
(laplacianT_file))
sys.exit(1)
# being learning
script = """
rpca_path = 'transduction_based/robustpca/';
addpath(rpca_path);
addpath([rpca_path, 'fast_svd/']);
tagmatrix = sparse(double(h5read('%s', '/tagmatrix')));
load('%s');
load('%s');
lambda1 = %f;
lambda2 = %f;
maxIters = 50;
precision = 1e-4;
mu_start = 1.;
parpool('local', 4);
[P,E]=robustpca(tagmatrix, lambda1, lambda2, tag_similarity, im_similarity, maxIters, precision, mu_start);
""" % (tagmatrix_file, laplacianI_file, laplacianT_file, lambda1,
lambda2)
script += """
delete(gcp);
save('%s', 'P', 'E', 'lambda1', 'lambda2', '-v7.3');
exit;
""" % resultfile_robustpca
if not only_dump:
printStatus(INFO, "starting learning")
makedirsforfile(resultfile_robustpca)
call_matlab(script)
if checkToSkip(resultfile, overwrite):
return 0
# save results in pkl format
printStatus(INFO, "Dump results in pkl format at %s" % resultfile)
concepts = readConcepts(workingCollection, annotationName, rootpath)
if outputonlytest:
testset_id_images = readImageSet(
workingCollection.split('+')[1],
workingCollection.split('+')[1], rootpath)
testset_id_images.sort()
id_images = readImageSet(workingCollection, workingCollection, rootpath)
id_images.sort()
# concepts mapping
robustpca_output = h5py.File(resultfile_robustpca, 'r')
tagprop_input = h5py.File(tagmatrix_file, 'r')
mapping = getVocabMap(list(tagprop_input['vocab'][:]), concepts)
predicted_tagmatrix = robustpca_output['P'][:, mapping]
if outputonlytest:
idx = np.array([bisect_index(id_images, x) for x in testset_id_images])
final_tagmatrix = predicted_tagmatrix[idx, :]
assert (final_tagmatrix.shape[0] == idx.shape[0])
id_images = testset_id_images
else:
final_tagmatrix = predicted_tagmatrix
makedirsforfile(resultfile)
with open(resultfile, 'w') as f:
pickle.dump(
{
'concepts': concepts,
'id_images': id_images,
'scores': final_tagmatrix
}, f, pickle.HIGHEST_PROTOCOL)
def process(options, workingCollection, feature):
rootpath = options.rootpath
k_ratio = options.kratio
distance = options.distance
overwrite = options.overwrite
laplaciankratio = options.laplaciankratio
nnName = distance + "knn"
resultfile = os.path.join(rootpath, workingCollection, 'RobustPCA', '%s,%s,%f'%(feature,nnName,k_ratio), 'tagmatrix.h5')
if checkToSkip(resultfile, overwrite):
return 0
tagmatrix_file = os.path.join(rootpath, workingCollection, 'TextData', "lemm_wordnet_freq_tags.h5")
if not os.path.exists(tagmatrix_file):
printStatus(INFO, 'Tagmatrix file not found in %s Did you run wordnet_frequency_tags.py?' % (tagmatrix_file))
sys.exit(1)
laplacianI_file = os.path.join(rootpath, workingCollection, 'LaplacianI', workingCollection, '%s,%s,%f'%(feature,nnName,laplaciankratio), 'laplacianI.mat')
if not os.path.exists(laplacianI_file):
printStatus(INFO, 'LaplacianI file not found in %s Did you run laplacian_images.py?' % (laplacianI_file))
sys.exit(1)
tagmatrix_data = h5py.File(tagmatrix_file, 'r')
tagmatrix = tagmatrix_data['tagmatrix'][:]
printStatus(INFO, 'tagmatrix.shape = %s' % (str(tagmatrix.shape)))
laplacian_data = scipy.io.loadmat(laplacianI_file)
sigma = laplacian_data['sigma']
printStatus(INFO, 'Sigma^2 = %f' % (sigma))
workingSet = readImageSet(workingCollection, workingCollection, rootpath)
workingSet.sort()
#print map(int, workingSet)[0:10], map(int, list(tagmatrix_data['id_images'][:])[0:10])
#assert(np.all(map(int, workingSet) == list(tagmatrix_data['id_images'][:])))
assert(np.all(workingSet == list(tagmatrix_data['id_images'][:])))
tot_images = len(workingSet)
printStatus(INFO, '%d images in %s' % (tot_images, workingCollection))
printStatus(INFO, 'Mean images per tag = %f' % (np.mean(tagmatrix.sum(axis=0))))
K_neighs = int(math.floor(np.mean(tagmatrix.sum(axis=0)) * k_ratio))
printStatus(INFO, '%d nearest neighbor per image (ratio = %f)' % (K_neighs, k_ratio))
printStatus(INFO, 'Starting the propagation pre-processing')
tagmatrix_new = np.zeros(tagmatrix.shape)
for i in xrange(tot_images):
neighbors = _get_neighbors('%s,%s' % (workingCollection, workingSet[i]), rootpath, K_neighs * 2, feature, distance)
#NNrow = np.array([bisect_index(workingSet, x[0]) for x in neighbors])
#NNDrow = np.array([x[1] for x in neighbors])
# remove images with features but not in the working set
NNrow = []
NNDrow = []
new_neighs = []
for x in neighbors:
try:
NNrow.append(bisect_index(workingSet, x[0]))
NNDrow.append(x[1])
new_neighs.append(x)
except ValueError:
pass
#NNrow = np.array([bisect_index(workingSet, x[0]) for x in neighbors])
#NNDrow = np.array([x[1] for x in neighbors])
NNrow = np.array(NNrow)
NNDrow = np.array(NNDrow)
neighbors = new_neighs[0:K_neighs]
C = np.sum(np.exp(-(NNDrow)/sigma))
tagmatrix_new[i,:] = np.sum((np.exp(-(NNDrow)/sigma).T * tagmatrix[NNrow]) / C, axis=0);
if (i+1) % 1000 == 0:
printStatus(INFO, '%d / %d done' % (i+1, tot_images))
# save output
printStatus(INFO, 'Saving propagated tagmatrix to %s' % resultfile)
makedirsforfile(resultfile)
fout = h5py.File(resultfile, 'w')
fout['tagmatrix'] = tagmatrix_new
fout['vocab'] = tagmatrix_data['vocab'][:]
fout['id_images'] = workingSet
fout.close()
def process(options, workingCollection, feature):
rootpath = options.rootpath
k_ratio = options.kratio
distance = options.distance
overwrite = options.overwrite
laplaciankratio = options.laplaciankratio
nnName = distance + "knn"
resultfile = os.path.join(rootpath, workingCollection, 'RobustPCA',
'%s,%s,%f' % (feature, nnName, k_ratio),
'tagmatrix.h5')
if checkToSkip(resultfile, overwrite):
return 0
tagmatrix_file = os.path.join(rootpath, workingCollection, 'TextData',
"lemm_wordnet_freq_tags.h5")
if not os.path.exists(tagmatrix_file):
printStatus(
INFO,
'Tagmatrix file not found in %s Did you run wordnet_frequency_tags.py?'
% (tagmatrix_file))
sys.exit(1)
laplacianI_file = os.path.join(
rootpath, workingCollection, 'LaplacianI', workingCollection,
'%s,%s,%f' % (feature, nnName, laplaciankratio), 'laplacianI.mat')
if not os.path.exists(laplacianI_file):
printStatus(
INFO,
'LaplacianI file not found in %s Did you run laplacian_images.py?'
% (laplacianI_file))
sys.exit(1)
tagmatrix_data = h5py.File(tagmatrix_file, 'r')
tagmatrix = tagmatrix_data['tagmatrix'][:]
printStatus(INFO, 'tagmatrix.shape = %s' % (str(tagmatrix.shape)))
laplacian_data = scipy.io.loadmat(laplacianI_file)
sigma = laplacian_data['sigma']
printStatus(INFO, 'Sigma^2 = %f' % (sigma))
workingSet = readImageSet(workingCollection, workingCollection, rootpath)
workingSet.sort()
#print map(int, workingSet)[0:10], map(int, list(tagmatrix_data['id_images'][:])[0:10])
#assert(np.all(map(int, workingSet) == list(tagmatrix_data['id_images'][:])))
assert (np.all(workingSet == list(tagmatrix_data['id_images'][:])))
tot_images = len(workingSet)
printStatus(INFO, '%d images in %s' % (tot_images, workingCollection))
printStatus(INFO,
'Mean images per tag = %f' % (np.mean(tagmatrix.sum(axis=0))))
K_neighs = int(math.floor(np.mean(tagmatrix.sum(axis=0)) * k_ratio))
printStatus(
INFO,
'%d nearest neighbor per image (ratio = %f)' % (K_neighs, k_ratio))
printStatus(INFO, 'Starting the propagation pre-processing')
tagmatrix_new = np.zeros(tagmatrix.shape)
for i in xrange(tot_images):
neighbors = _get_neighbors(
'%s,%s' % (workingCollection, workingSet[i]), rootpath,
K_neighs * 2, feature, distance)
#NNrow = np.array([bisect_index(workingSet, x[0]) for x in neighbors])
#NNDrow = np.array([x[1] for x in neighbors])
# remove images with features but not in the working set
NNrow = []
NNDrow = []
new_neighs = []
for x in neighbors:
try:
NNrow.append(bisect_index(workingSet, x[0]))
NNDrow.append(x[1])
new_neighs.append(x)
except ValueError:
pass
#NNrow = np.array([bisect_index(workingSet, x[0]) for x in neighbors])
#NNDrow = np.array([x[1] for x in neighbors])
NNrow = np.array(NNrow)
NNDrow = np.array(NNDrow)
neighbors = new_neighs[0:K_neighs]
C = np.sum(np.exp(-(NNDrow) / sigma))
tagmatrix_new[i, :] = np.sum(
(np.exp(-(NNDrow) / sigma).T * tagmatrix[NNrow]) / C, axis=0)
if (i + 1) % 1000 == 0:
printStatus(INFO, '%d / %d done' % (i + 1, tot_images))
# save output
printStatus(INFO, 'Saving propagated tagmatrix to %s' % resultfile)
makedirsforfile(resultfile)
fout = h5py.File(resultfile, 'w')
fout['tagmatrix'] = tagmatrix_new
fout['vocab'] = tagmatrix_data['vocab'][:]
fout['id_images'] = workingSet
fout.close()
line = line[:-2]
data = line.split("\t")
assert len(data) == 3
id_image = data[0]
tags = [x.lower() for x in data[2].split(" ")]
final_tags = [t for t in tags if t in vocab]
id_tags[id_image] = final_tags
N_images = len(id_tags)
print "N images: ", N_images
# build tag matrix
tagmatrix = np.zeros((N_images, N_tags), dtype=np.int8)
for i, id_im in enumerate(id_images):
tags = id_tags[id_im]
if len(tags) > 0:
idx = [bisect_index(vocab, t) for t in tags]
tagmatrix[i, idx] = True
# save output
fout = h5py.File(resultfile, "w")
fout["tagmatrix"] = tagmatrix
fout["vocab"] = vocab
fout["id_images"] = id_images
fout.close()
pkl_file = open(sys.argv[2], 'w')
workingCollection = sys.argv[3]
annotationName = sys.argv[4]
rootpath = ROOT_PATH
id_images = tagmatrix_file['id_images']
concepts = readConcepts(workingCollection, annotationName, rootpath)
testset_id_images = readImageSet(workingCollection.split('+')[1], workingCollection.split('+')[1], rootpath)
testset_id_images.sort()
if not type(id_images[0]) is str:
id_images = map(str, id_images)
if not type(testset_id_images[0]) is str:
testset_id_images = map(str, testset_id_images)
mapping = getVocabMap(list(tagmatrix_file['vocab'][:]),concepts)
predicted_tagmatrix = tagmatrix_file['tagmatrix'][:,mapping]
print "predicted_tagmatrix.shape = ", predicted_tagmatrix.shape
print "len(id_images) = ", len(id_images)
print "len(testset_id_images) = ", len(testset_id_images)
idx = np.array([bisect_index(id_images, x) for x in testset_id_images])
final_tagmatrix = predicted_tagmatrix[idx, :]
id_images = testset_id_images
print "dumping %d elements..." % len(id_images)
pickle.dump({'concepts':concepts, 'id_images':map(int, id_images), 'scores':final_tagmatrix}, pkl_file, pickle.HIGHEST_PROTOCOL)
def process(options, workingCollection, feature):
rootpath = options.rootpath
k_ratio = options.kratio
distance = options.distance
overwrite = options.overwrite
nnName = distance + "knn"
resultfile = os.path.join(rootpath, workingCollection, 'LaplacianI',
workingCollection,
'%s,%s,%f' % (feature, nnName, k_ratio),
'laplacianI.mat')
if checkToSkip(resultfile, overwrite):
return 0
workingSet = readImageSet(workingCollection, workingCollection, rootpath)
workingSet.sort()
tot_images = len(workingSet)
printStatus(INFO, '%d images' % (tot_images))
K_neighs = int(math.floor(len(workingSet) * k_ratio))
printStatus(
INFO,
'%d nearest neighbor per image (ratio = %f)' % (K_neighs, k_ratio))
printStatus(INFO, 'Allocating I,J,V arrays')
I = np.zeros((K_neighs * tot_images * 2))
J = np.zeros((K_neighs * tot_images * 2))
V = np.zeros((K_neighs * tot_images * 2))
n_entries = 0
# distances
printStatus(INFO, 'Starting to fill I,J,V arrays')
for i in xrange(tot_images):
try:
neighbors = _get_neighbors(
'%s,%s' % (workingCollection, workingSet[i]), rootpath,
K_neighs * 2, feature, distance)
# remove images with features but not in the working set
NNrow = []
NNDrow = []
new_neighs = []
for x in neighbors:
try:
NNrow.append(bisect_index(workingSet, x[0]))
NNDrow.append(x[1])
new_neighs.append(x)
except ValueError:
pass
#NNrow = np.array([bisect_index(workingSet, x[0]) for x in neighbors])
#NNDrow = np.array([x[1] for x in neighbors])
NNrow = np.array(NNrow)
NNDrow = np.array(NNDrow)
neighbors = new_neighs[0:K_neighs]
except ValueError:
printStatus(
INFO,
'ERROR: id_img %s has non-standard format!' % (workingSet[i]))
sys.exit(1)
if len(neighbors) < K_neighs:
printStatus(
INFO, 'ERROR: id_img %s has %d < %d neighbors!' %
(workingSet[i], len(neighbors), K_neighs))
sys.exit(1)
if (i + 1) % 1000 == 0:
printStatus(INFO, '%d / %d done' % (i + 1, tot_images))
for k in xrange(K_neighs):
if i != int(NNrow[k]): # -1 zero on the diagonal for a later step
I[n_entries] = i
J[n_entries] = int(NNrow[k]) # -1
V[n_entries] = NNDrow[k]
n_entries += 1
I[n_entries] = int(NNrow[k]) # -1
J[n_entries] = i
V[n_entries] = NNDrow[k]
n_entries += 1
I = I[0:n_entries]
J = J[0:n_entries]
V = V[0:n_entries]
printStatus(INFO, 'Removing duplicates')
ind = np.lexsort((V, J, I))
I = I[ind]
J = J[ind]
V = V[ind]
a = np.concatenate([I.reshape(1, len(I)), J.reshape(1, len(J))], axis=0).T
b = np.ascontiguousarray(a).view(
np.dtype((np.void, a.dtype.itemsize * a.shape[1])))
del a
_, idx = np.unique(b, return_index=True)
del b
I = I[idx]
J = J[idx]
V = V[idx]
printStatus(INFO, 'Computing the final laplacian matrix')
sigma = np.median(V)**2.
printStatus(INFO, 'Estimated sigma^2 = %f' % sigma)
V = np.exp(-V / sigma)
matrix = coo_matrix((V, (I, J)), shape=(tot_images, tot_images)).tocsr()
new_diag = matrix.sum(axis=0).T
V = -V
I_add = np.zeros((tot_images))
J_add = np.zeros((tot_images))
V_add = np.zeros((tot_images))
for i, v in enumerate(new_diag):
I_add[i] = i
J_add[i] = i
V_add[i] = v
I = np.append(I, I_add)
J = np.append(J, J_add)
V = np.append(V, V_add)
matrix = coo_matrix((V, (I, J)), shape=(tot_images, tot_images)).tolil()
printStatus(INFO, 'Saving laplacian matrix to %s' % resultfile)
makedirsforfile(resultfile)
scipy.io.savemat(resultfile, {'im_similarity': matrix, 'sigma': sigma})
