def process(options, collection, annotationName):
rootpath = options.rootpath
overwrite = options.overwrite
concepts = readConcepts(collection,annotationName,rootpath)
resultdir = os.path.join(rootpath, collection, "SimilarityIndex", "ngd")
todo = [x for x in concepts if not os.path.exists(os.path.join(resultdir,x+'.txt')) or overwrite]
if not todo:
printStatus(INFO, 'nothing to do')
return
fcs = FlickrContextSim(collection, rootpath=rootpath)
vob = fcs.vob
resultdir = os.path.join(rootpath, collection, "SimilarityIndex", "ngd")
printStatus(INFO, 'expanding tags for %s-%s -> %s' % (collection, annotationName, resultdir))
for concept in todo:
resultfile = os.path.join(resultdir, concept + '.txt')
vals = []
for tag in vob:
dist = fcs.computeNGD(concept, tag, img=1)
if dist < 10:
vals.append((tag,dist))
vals.sort(key=lambda v:v[1])
printStatus(INFO, '%s -> %s' % (concept, ' '.join([x[0] for x in vals[:3]])))
writeRankingResults(vals, resultfile)
def process(options, collection, annotationName):
rootpath = options.rootpath
overwrite = options.overwrite
concepts = readConcepts(collection, annotationName, rootpath)
resultdir = os.path.join(rootpath, collection, "SimilarityIndex", "ngd")
todo = [
x for x in concepts
if not os.path.exists(os.path.join(resultdir, x + '.txt')) or overwrite
]
if not todo:
printStatus(INFO, 'nothing to do')
return
fcs = FlickrContextSim(collection, rootpath=rootpath)
vob = fcs.vob
resultdir = os.path.join(rootpath, collection, "SimilarityIndex", "ngd")
printStatus(
INFO, 'expanding tags for %s-%s -> %s' %
(collection, annotationName, resultdir))
for concept in todo:
resultfile = os.path.join(resultdir, concept + '.txt')
vals = []
for tag in vob:
dist = fcs.computeNGD(concept, tag, img=1)
if dist < 10:
vals.append((tag, dist))
vals.sort(key=lambda v: v[1])
printStatus(INFO,
'%s -> %s' % (concept, ' '.join([x[0] for x in vals[:3]])))
writeRankingResults(vals, resultfile)
def submit(searchers, collection,annotationName, rootpath=ROOT_PATH, overwrite=0):
concepts = readConcepts(collection, annotationName, rootpath=rootpath)
nr_of_runs = len(searchers)
for concept in concepts:
for j in range(nr_of_runs):
resultfile = os.path.join(searchers[j].getOutputdir(), concept + ".txt")
if checkToSkip(resultfile, overwrite):
continue
searchresults = searchers[j].scoreCollection(concept)
print ("%s: %s %d -> %s" % (searchers[j].name, concept, len(searchresults), resultfile))
writeRankingResults(searchresults, resultfile)
printStatus('%s.submit'%os.path.basename(__file__), "done")
def process(options, testCollection, annotationName, tagvotefile):
rootpath = options.rootpath
tpp = options.tpp
tagged = options.tagged
overwrite = options.overwrite
resultdir = generate_result_dir(options, testCollection, tagvotefile)
concepts = readConcepts(testCollection, annotationName, rootpath)
todo = []
for concept in concepts:
resfile = os.path.join(resultdir, '%s.txt'%concept)
if checkToSkip(resfile, overwrite):
continue
todo.append(concept)
if not todo:
print ('nothing to do')
return 0
nr_of_concepts = len(todo)
labeled_set = [None] * nr_of_concepts
if tagged:
for i in range(nr_of_concepts):
labeled_set[i] = set(readLabeledImageSet(testCollection, todo[i], tpp, rootpath))
concept2index = dict(zip(todo, range(nr_of_concepts)))
ranklists = [[] for i in range(nr_of_concepts)]
for line in open(tagvotefile):
elems = line.strip().split()
imageid = elems[0]
del elems[0]
assert(len(elems)%2==0)
for i in range(0, len(elems), 2):
tag = elems[i]
c = concept2index.get(tag, -1)
if c >= 0:
if tagged and imageid not in labeled_set[c]:
continue
score = float(elems[i+1])
ranklists[c].append((imageid,score))
for i in range(nr_of_concepts):
concept = todo[i]
resfile = os.path.join(resultdir, '%s.txt'%concept)
ranklist = sorted(ranklists[i], key=lambda v:v[1], reverse=True)
print ('%s %d -> %s' % (concept, len(ranklist), resfile))
writeRankingResults(ranklist, resfile)
def process(options, collection, annotationName, runfile, newRunName):
rootpath = options.rootpath
overwrite = options.overwrite
dataset = options.testset if options.testset else collection
concepts = readConcepts(collection, annotationName, rootpath)
simdir = os.path.join(rootpath, collection, "SimilarityIndex", dataset)
data = [x.strip() for x in open(runfile).readlines() if x.strip() and not x.strip().startswith("#")]
models = []
for line in data:
weight, run = str.split(line)
models.append((run, float(weight), 1))
for concept in concepts:
resultfile = os.path.join(simdir, newRunName, concept + ".txt")
if checkToSkip(resultfile, overwrite):
continue
scorefile = os.path.join(simdir, models[0][0], concept + ".txt")
if not os.path.exists(scorefile):
print("%s does not exist. skip" % scorefile)
continue
ranklist = readRankingResults(scorefile)
names = sorted([x[0] for x in ranklist])
nr_of_images = len(names)
name2index = dict(zip(names, range(nr_of_images)))
print("%s %d" % (concept, nr_of_images))
scoreTable = readImageScoreTable(concept, name2index, simdir, models, torank=options.torank)
assert scoreTable.shape[1] == nr_of_images
weights = [model[1] for model in models]
scores = np.matrix(weights) * scoreTable
scores = [float(scores[0, k]) for k in range(nr_of_images)]
newranklist = [(names[i], scores[i]) for i in range(nr_of_images)]
newranklist.sort(key=lambda v: (v[1], v[0]), reverse=True)
writeRankingResults(newranklist, resultfile)
def process(options, collection, annotationName, runfile, newRunName):
rootpath = options.rootpath
overwrite = options.overwrite
dataset = options.testset if options.testset else collection
concepts = readConcepts(collection, annotationName, rootpath)
simdir = os.path.join(rootpath, collection, "SimilarityIndex", dataset)
data = [x.strip() for x in open(runfile).readlines() if x.strip() and not x.strip().startswith("#")]
models = []
for line in data:
weight,run = str.split(line)
models.append((run, float(weight), 1))
for concept in concepts:
resultfile = os.path.join(simdir, newRunName, concept + ".txt")
if checkToSkip(resultfile, overwrite):
continue
scorefile = os.path.join(simdir, models[0][0], concept + ".txt")
if not os.path.exists(scorefile):
print ("%s does not exist. skip" % scorefile)
continue
ranklist = readRankingResults(scorefile)
names = sorted([x[0] for x in ranklist])
nr_of_images = len(names)
name2index = dict(zip(names, range(nr_of_images)))
print ('%s %d' % (concept, nr_of_images))
scoreTable = readImageScoreTable(concept, name2index, simdir, models, torank=options.torank)
assert(scoreTable.shape[1] == nr_of_images)
weights = [model[1] for model in models]
scores = np.matrix(weights) * scoreTable
scores = [float(scores[0,k]) for k in range(nr_of_images)]
newranklist = [(names[i], scores[i]) for i in range(nr_of_images)]
newranklist.sort(key=lambda v:(v[1],v[0]), reverse=True)
writeRankingResults(newranklist, resultfile)
def submit(searchers,
collection,
annotationName,
rootpath=ROOT_PATH,
overwrite=0):
concepts = readConcepts(collection, annotationName, rootpath=rootpath)
nr_of_runs = len(searchers)
for concept in concepts:
for j in range(nr_of_runs):
resultfile = os.path.join(searchers[j].getOutputdir(),
concept + ".txt")
if checkToSkip(resultfile, overwrite):
continue
searchresults = searchers[j].scoreCollection(concept)
print("%s: %s %d -> %s" %
(searchers[j].name, concept, len(searchresults), resultfile))
writeRankingResults(searchresults, resultfile)
printStatus('%s.submit' % os.path.basename(__file__), "done")
def process(options, collection, annotationName, runfile):
rootpath = options.rootpath
overwrite = options.overwrite
resultdir = os.path.join(rootpath, collection, 'SimilarityIndex',
collection)
apscorer = getScorer('AP')
datafiles = [
x.strip() for x in open(runfile).readlines()
if x.strip() and not x.strip().startswith('#')
]
nr_of_runs = len(datafiles)
concepts = readConcepts(collection, annotationName, rootpath=rootpath)
nr_of_concepts = len(concepts)
printStatus(INFO, 'read annotations from files')
name2label = [{} for i in range(nr_of_concepts)]
hit_imgset = [[] for i in range(nr_of_concepts)]
for i in range(nr_of_concepts):
names, labels = readAnnotationsFrom(collection,
annotationName,
concepts[i],
skip_0=False,
rootpath=rootpath)
names = map(int, names)
name2label[i] = dict(zip(names, labels))
label_file = os.path.join(rootpath, collection, 'tagged,lemm',
'%s.txt' % concepts[i])
try:
hit_imgset[i] = set(map(int, open(label_file).readlines()))
except:
hit_imgset[i] = set()
printStatus(
INFO, 'readLabeledImageSet for %s-%s -> %d hits' %
(collection, concepts[i], len(hit_imgset[i])))
ap_table = np.zeros((nr_of_runs, nr_of_concepts))
ap2_table = np.zeros((nr_of_runs, nr_of_concepts))
for run_idx in range(nr_of_runs):
runName = os.path.splitext(os.path.basename(datafiles[run_idx]))[0]
data = pickle.load(open(datafiles[run_idx], 'rb'))
scores = data['scores']
assert (scores.shape[1] == nr_of_concepts)
imset = data['id_images']
nr_of_images = len(imset)
#print datafiles[run_idx], imset[:5], imset[-5:]
for c_idx in range(nr_of_concepts):
ground_truth = name2label[c_idx]
ranklist = zip(imset, scores[:, c_idx])
ranklist.sort(key=lambda v: (v[1], str(v[0])), reverse=True)
ranklist = [x for x in ranklist if x[0] in ground_truth]
resfile = os.path.join(resultdir, runName,
'%s.txt' % concepts[c_idx])
if not checkToSkip(resfile, overwrite):
writeRankingResults(ranklist, resfile)
sorted_labels = [ground_truth[x[0]] for x in ranklist]
assert (len(sorted_labels) > 0)
#print concepts[c_idx], ranklist[:5], sorted_labels[:5]
ap_table[run_idx, c_idx] = apscorer.score(sorted_labels)
resfile = os.path.join(resultdir, 'tagged,lemm', runName,
'%s.txt' % concepts[c_idx])
if not checkToSkip(resfile, overwrite):
writeRankingResults(
[x for x in ranklist if x[0] in hit_imgset[c_idx]],
resfile)
sorted_labels = [
ground_truth[x[0]] for x in ranklist
if x[0] in hit_imgset[c_idx]
]
ap2_table[run_idx, c_idx] = apscorer.score(sorted_labels)
print '#' * 100
print '# untagged-concept', ' '.join(
[os.path.basename(x) for x in datafiles])
print '#' * 100
for c_idx in range(nr_of_concepts):
print concepts[c_idx], ' '.join(
['%.3f' % x for x in ap_table[:, c_idx]])
print 'meanAP', ' '.join(['%.3f' % x for x in ap_table.mean(axis=1)])
print '#' * 100
print '# tagged-concept'
print '#' * 100
for c_idx in range(nr_of_concepts):
print concepts[c_idx], ' '.join(
['%.3f' % x for x in ap2_table[:, c_idx]])
print 'meanAP2', ' '.join(['%.3f' % x for x in ap2_table.mean(axis=1)])
def process(options, collection, annotationName, runfile):
rootpath = options.rootpath
overwrite = options.overwrite
resultdir = os.path.join(rootpath, collection, 'SimilarityIndex', collection)
apscorer = getScorer('AP')
datafiles = [x.strip() for x in open(runfile).readlines() if x.strip() and not x.strip().startswith('#')]
nr_of_runs = len(datafiles)
concepts = readConcepts(collection, annotationName, rootpath=rootpath)
nr_of_concepts = len(concepts)
printStatus(INFO, 'read annotations from files')
name2label = [{} for i in range(nr_of_concepts)]
hit_imgset = [[] for i in range(nr_of_concepts)]
for i in range(nr_of_concepts):
names,labels = readAnnotationsFrom(collection, annotationName, concepts[i], skip_0=False, rootpath=rootpath)
names = map(int, names)
name2label[i] = dict(zip(names,labels))
label_file = os.path.join(rootpath, collection, 'tagged,lemm', '%s.txt'% concepts[i])
try:
hit_imgset[i] = set(map(int, open(label_file).readlines()))
except:
hit_imgset[i] = set()
printStatus(INFO, 'readLabeledImageSet for %s-%s -> %d hits' % (collection, concepts[i], len(hit_imgset[i])))
ap_table = np.zeros((nr_of_runs, nr_of_concepts))
ap2_table = np.zeros((nr_of_runs, nr_of_concepts))
for run_idx in range(nr_of_runs):
runName = os.path.splitext(os.path.basename(datafiles[run_idx]))[0]
data = pickle.load(open(datafiles[run_idx],'rb'))
scores = data['scores']
assert(scores.shape[1] == nr_of_concepts)
imset = data['id_images']
nr_of_images = len(imset)
#print datafiles[run_idx], imset[:5], imset[-5:]
for c_idx in range(nr_of_concepts):
ground_truth = name2label[c_idx]
ranklist = zip(imset, scores[:,c_idx])
ranklist.sort(key=lambda v:(v[1], str(v[0])), reverse=True)
ranklist = [x for x in ranklist if x[0] in ground_truth]
resfile = os.path.join(resultdir, runName, '%s.txt' % concepts[c_idx])
if not checkToSkip(resfile, overwrite):
writeRankingResults(ranklist, resfile)
sorted_labels = [ground_truth[x[0]] for x in ranklist]
assert(len(sorted_labels)>0)
#print concepts[c_idx], ranklist[:5], sorted_labels[:5]
ap_table[run_idx, c_idx] = apscorer.score(sorted_labels)
resfile = os.path.join(resultdir, 'tagged,lemm', runName, '%s.txt' % concepts[c_idx])
if not checkToSkip(resfile, overwrite):
writeRankingResults([x for x in ranklist if x[0] in hit_imgset[c_idx]], resfile)
sorted_labels = [ground_truth[x[0]] for x in ranklist if x[0] in hit_imgset[c_idx]]
ap2_table[run_idx, c_idx] = apscorer.score(sorted_labels)
print '#'*100
print '# untagged-concept', ' '.join([os.path.basename(x) for x in datafiles])
print '#'*100
for c_idx in range(nr_of_concepts):
print concepts[c_idx], ' '.join(['%.3f' % x for x in ap_table[:,c_idx]])
print 'meanAP', ' '.join(['%.3f' % x for x in ap_table.mean(axis=1)])
print '#'*100
print '# tagged-concept'
print '#'*100
for c_idx in range(nr_of_concepts):
print concepts[c_idx], ' '.join(['%.3f' % x for x in ap2_table[:,c_idx]])
print 'meanAP2', ' '.join(['%.3f' % x for x in ap2_table.mean(axis=1)])
print 'training %s' % tag
from model_based.svms.fastlinear.liblinear193.python.liblinearutil import train
from model_based.svms.fastlinear.fastlinear import liblinear_to_fastlinear
svm_params = '-s 2 -B -1 -q'
model = train(y, vectors, svm_params)
fastmodel = liblinear_to_fastlinear([model], [1.0], feat_dim)
# optionally save the learned model to disk
from model_based.svms.fastlinear.fastlinear import fastlinear_save_model
model_dir = os.path.join(rootpath, trainCollection, 'Models',
trainAnnotationName, feature, 'fastlinear')
model_filename = os.path.join(model_dir, '%s.model' % tag)
from basic.common import makedirsforfile
makedirsforfile(model_filename)
fastlinear_save_model(model_filename, fastmodel)
print 'applying %s' % tag
from model_based.svms.mlengine_util import classify_large_data
ranklist = classify_large_data(fastmodel, test_imset, test_feat_file)
#predict_scores = [fastmodel.predict(x) for x in test_vectors]
#ranklist = sorted(zip(test_renamed, predict_scores), key=lambda v:(v[1],v[0]), reverse=True)
from basic.common import writeRankingResults
simdir = os.path.join(rootpath, testCollection, 'SimilarityIndex',
testCollection, trainCollection,
'conceptsmm15tut.txt', '%s,fastlinear' % feature)
resultfile = os.path.join(simdir, '%s.txt' % tag)
writeRankingResults(ranklist, resultfile)
def process(options, trainCollection, testCollection, feature):
rootpath = options.rootpath
k = options.k
distance = options.distance
blocksize = options.blocksize
uniqueUser = options.uu
numjobs = options.numjobs
job = options.job
overwrite = options.overwrite
testset = options.testset
if not testset:
testset = testCollection
searchMethod = distance + 'knn'
if uniqueUser:
searchMethod += ",uu"
tagfile = os.path.join(rootpath, trainCollection, 'TextData', 'id.userid.lemmtags.txt')
im2user = {}
for line in open(tagfile):
im,userid,tags = line.split('\t')
im2user[im] = userid
resultdir = os.path.join(rootpath, testCollection, "SimilarityIndex", testset, trainCollection, "%s,%s,%d" % (feature,searchMethod,k))
feat_dir = os.path.join(rootpath, trainCollection, 'FeatureData', feature)
id_file = os.path.join(feat_dir, 'id.txt')
shape_file = os.path.join(feat_dir, 'shape.txt')
nr_of_images, feat_dim = map(int, open(shape_file).readline().split())
nr_of_images = len(open(id_file).readline().strip().split())
searcher = imagesearch.load_model(os.path.join(feat_dir, 'feature.bin'), feat_dim, nr_of_images, id_file)
searcher.set_distance(distance)
workingSet = readImageSet(testCollection, testset, rootpath=rootpath)
workingSet = [workingSet[i] for i in range(len(workingSet)) if (i%numjobs+1) == job]
printStatus(INFO, "working on %d-%d, %d test images -> %s" % (numjobs,job,len(workingSet),resultdir))
test_feat_dir = os.path.join(rootpath, testCollection, 'FeatureData', feature)
test_feat_file = BigFile(test_feat_dir)
read_time = 0
knn_time = 0
start = 0
done = 0
filtered = 0
while start < len(workingSet):
end = min(len(workingSet), start + blocksize)
printStatus(INFO, 'processing images from %d to %d' % (start, end-1))
s_time = time.time()
renamed,vectors = test_feat_file.read(workingSet[start:end])
read_time += time.time() - s_time
nr_images = len(renamed)
s_time = time.time()
for i in range(nr_images):
resultfile = os.path.join(resultdir, renamed[i][-2:], '%s.txt' % renamed[i])
if checkToSkip(resultfile, overwrite):
continue
knn = searcher.search_knn(vectors[i], max_hits=max(3000,k*3))
if uniqueUser:
removed, newknn = unique_user_constraint(knn, im2user, k)
filtered += removed
knn = newknn
else:
knn = knn[:k]
assert(len(knn) >= k)
writeRankingResults(knn, resultfile)
done += 1
printStatus(INFO, 'job %d-%d: %d done, filtered neighbors %d' % (numjobs, job, done, filtered))
start = end
printStatus(INFO, 'job %d-%d: %d done, filtered neighbors %d' % (numjobs, job, done, filtered))
(renamed, vectors) = train_feat_file.read(names)
y = [name2label[x] for x in renamed]
print 'training %s' % tag
from model_based.svms.fastlinear.liblinear193.python.liblinearutil import train
from model_based.svms.fastlinear.fastlinear import liblinear_to_fastlinear
svm_params = '-s 2 -B -1 -q'
model = train(y, vectors, svm_params)
fastmodel = liblinear_to_fastlinear([model], [1.0], feat_dim)
# optionally save the learned model to disk
from model_based.svms.fastlinear.fastlinear import fastlinear_save_model
model_dir = os.path.join(rootpath, trainCollection, 'Models', trainAnnotationName, feature, 'fastlinear')
model_filename = os.path.join(model_dir, '%s.model' % tag)
from basic.common import makedirsforfile
makedirsforfile(model_filename)
fastlinear_save_model(model_filename, fastmodel)
print 'applying %s' % tag
from model_based.svms.mlengine_util import classify_large_data
ranklist = classify_large_data(fastmodel, test_imset, test_feat_file)
#predict_scores = [fastmodel.predict(x) for x in test_vectors]
#ranklist = sorted(zip(test_renamed, predict_scores), key=lambda v:(v[1],v[0]), reverse=True)
from basic.common import writeRankingResults
simdir = os.path.join(rootpath, testCollection, 'SimilarityIndex', testCollection, trainCollection, 'conceptsmm15tut.txt', '%s,fastlinear'%feature)
resultfile = os.path.join(simdir, '%s.txt' % tag)
writeRankingResults(ranklist, resultfile)
