def process(options, testCollection, trainCollection, trainAnnotationName, feature, modelName):
if modelName.startswith('fik'):
from fiksvm.fiksvm import fiksvm_load_model as load_model
else:
from fastlinear.fastlinear import fastlinear_load_model as load_model
rootpath = options.rootpath
overwrite = options.overwrite
prob_output = options.prob_output
numjobs = options.numjobs
job = options.job
#blocksize = options.blocksize
topk = options.topk
outputName = '%s,%s' % (feature,modelName)
if prob_output:
outputName += ',prob'
resultfile = os.path.join(rootpath, testCollection, 'autotagging', testCollection, trainCollection, trainAnnotationName, outputName, 'id.tagvotes.txt')
if numjobs>1:
resultfile += '.%d.%d' % (numjobs, job)
if checkToSkip(resultfile, overwrite):
return 0
concepts = readConcepts(trainCollection,trainAnnotationName, rootpath=rootpath)
nr_of_concepts = len(concepts)
test_imset = readImageSet(testCollection, testCollection, rootpath)
test_imset = [test_imset[i] for i in range(len(test_imset)) if i%numjobs+1 == job]
test_imset = set(test_imset)
nr_of_test_images = len(test_imset)
printStatus(INFO, "working on %d-%d, %d test images -> %s" % (numjobs,job,nr_of_test_images,resultfile))
models = [None] * nr_of_concepts
for c in range(nr_of_concepts):
model_file_name = os.path.join(rootpath,trainCollection,'Models',trainAnnotationName,feature, modelName, '%s.model'%concepts[c])
models[c] = load_model(model_file_name)
if models[c] is None:
return 0
#(pA,pB) = model.get_probAB()
feat_file = StreamFile(os.path.join(rootpath, testCollection, "FeatureData", feature))
makedirsforfile(resultfile)
fw = open(resultfile, "w")
done = 0
feat_file.open()
for _id, _vec in feat_file:
if _id not in test_imset:
continue
if prob_output:
scores = [models[c].predict_probability(_vec) for c in range(nr_of_concepts)]
else:
scores = [models[c].predict(_vec) for c in range(nr_of_concepts)]
tagvotes = sorted(zip(concepts, scores), key=lambda v:v[1], reverse=True)
if topk>0:
tagvotes = tagvotes[:topk]
newline = '%s %s\n' % (_id, " ".join(["%s %s" % (tag, niceNumber(vote,6)) for (tag,vote) in tagvotes]))
fw.write(newline)
done += 1
if done % 1e4 == 0:
printStatus(INFO, "%d done" % done)
feat_file.close()
fw.close()
printStatus(INFO, "%d done" % (done))
return done
from fiksvm.fiksvm import fiksvm_load_model as load_model
else:
from fastlinear.fastlinear import fastlinear_load_model as load_model
test_imset = readImageSet(testCollection, testCollection, rootpath=rootpath)
test_feat_file = BigFile(os.path.join(rootpath,testCollection,'FeatureData',feature))
test_renamed, test_vectors = test_feat_file.read(test_imset)
concepts = readConcepts(testCollection, testAnnotationName, rootpath=rootpath)
print ('### %s' % os.path.join(trainCollection, 'Models', trainAnnotationName, feature, modelName))
results = []
for concept in concepts:
model_file_name = os.path.join(rootpath, trainCollection, 'Models', trainAnnotationName, feature, modelName, '%s.model' % concept)
model = load_model(model_file_name)
ranklist = [(test_renamed[i], model.predict(test_vectors[i])) for i in range(len(test_renamed))]
ranklist.sort(key=lambda v:v[1], reverse=True)
names,labels = readAnnotationsFrom(testCollection, testAnnotationName, concept, skip_0=True, rootpath=rootpath)
test_name2label = dict(zip(names,labels))
sorted_labels = [test_name2label[x[0]] for x in ranklist if x[0] in test_name2label]
perf = scorer.score(sorted_labels)
print ('%s %g' % (concept, perf))
results.append((concept, perf))
mean_perf = sum([x[1] for x in results]) / len(concepts)
print ('mean%s %g' % (metric, mean_perf))
def process(options, testCollection, trainCollection, trainAnnotationName,
feature, modelName):
if modelName.startswith('fik'):
from fiksvm.fiksvm import fiksvm_load_model as load_model
else:
from fastlinear.fastlinear import fastlinear_load_model as load_model
rootpath = options.rootpath
overwrite = options.overwrite
prob_output = options.prob_output
numjobs = options.numjobs
job = options.job
blocksize = options.blocksize
outputName = '%s,%s' % (feature, modelName)
if prob_output:
outputName += ',prob'
resultfile = os.path.join(rootpath, testCollection, 'autotagging',
testCollection, trainCollection,
trainAnnotationName, outputName,
'id.tagvotes.txt')
if numjobs > 1:
resultfile += '.%d.%d' % (numjobs, job)
if checkToSkip(resultfile, overwrite):
return 0
concepts = readConcepts(trainCollection,
trainAnnotationName,
rootpath=rootpath)
nr_of_concepts = len(concepts)
test_imset = readImageSet(testCollection, testCollection, rootpath)
test_imset = [
test_imset[i] for i in range(len(test_imset)) if i % numjobs + 1 == job
]
nr_of_test_images = len(test_imset)
printStatus(
INFO, "working on %d-%d, %d test images -> %s" %
(numjobs, job, nr_of_test_images, resultfile))
models = [None] * nr_of_concepts
for c in range(nr_of_concepts):
model_file_name = os.path.join(rootpath, trainCollection, 'Models',
trainAnnotationName, feature, modelName,
'%s.model' % concepts[c])
models[c] = load_model(model_file_name)
if models[c] is None:
return 0
#(pA,pB) = model.get_probAB()
feat_file = BigFile(
os.path.join(rootpath, testCollection, "FeatureData", feature))
makedirsforfile(resultfile)
fw = open(resultfile, "w")
read_time = 0
test_time = 0
start = 0
done = 0
while start < nr_of_test_images:
end = min(nr_of_test_images, start + blocksize)
printStatus(INFO, 'processing images from %d to %d' % (start, end - 1))
s_time = time.time()
renamed, test_X = feat_file.read(test_imset[start:end])
read_time += time.time() - s_time
s_time = time.time()
output = [None] * len(renamed)
for i in xrange(len(renamed)):
if prob_output:
scores = [
models[c].predict_probability(test_X[i])
for c in range(nr_of_concepts)
]
else:
scores = [
models[c].predict(test_X[i]) for c in range(nr_of_concepts)
]
#dec_value = sigmoid_predict(dec_value, A=pA, B=pB)
tagvotes = sorted(zip(concepts, scores),
key=lambda v: v[1],
reverse=True)
output[i] = '%s %s\n' % (renamed[i], " ".join([
"%s %s" % (tag, niceNumber(vote, 6))
for (tag, vote) in tagvotes
]))
test_time += time.time() - s_time
start = end
fw.write(''.join(output))
fw.flush()
done += len(output)
# done
printStatus(
INFO, "%d done. read time %g seconds, test_time %g seconds" %
(done, read_time, test_time))
fw.close()
return done
def process(options, testCollection, trainCollection, trainAnnotationName, feature, modelName):
if modelName.startswith('fik'):
from fiksvm.fiksvm import fiksvm_load_model as load_model
else:
from fastlinear.fastlinear import fastlinear_load_model as load_model
rootpath = options.rootpath
overwrite = options.overwrite
prob_output = options.prob_output
numjobs = options.numjobs
job = options.job
blocksize = options.blocksize
outputName = '%s,%s' % (feature,modelName)
if prob_output:
outputName += ',prob'
resultfile = os.path.join(rootpath, testCollection, 'autotagging', testCollection, trainCollection, trainAnnotationName, outputName, 'id.tagvotes.txt')
if numjobs>1:
resultfile += '.%d.%d' % (numjobs, job)
if checkToSkip(resultfile, overwrite):
return 0
concepts = readConcepts(trainCollection,trainAnnotationName, rootpath=rootpath)
nr_of_concepts = len(concepts)
test_imset = readImageSet(testCollection, testCollection, rootpath)
test_imset = [test_imset[i] for i in range(len(test_imset)) if i%numjobs+1 == job]
nr_of_test_images = len(test_imset)
printStatus(INFO, "working on %d-%d, %d test images -> %s" % (numjobs,job,nr_of_test_images,resultfile))
models = [None] * nr_of_concepts
for c in range(nr_of_concepts):
model_file_name = os.path.join(rootpath,trainCollection,'Models',trainAnnotationName,feature, modelName, '%s.model'%concepts[c])
models[c] = load_model(model_file_name)
if models[c] is None:
return 0
#(pA,pB) = model.get_probAB()
feat_file = BigFile(os.path.join(rootpath, testCollection, "FeatureData", feature))
makedirsforfile(resultfile)
fw = open(resultfile, "w")
read_time = 0
test_time = 0
start = 0
done = 0
while start < nr_of_test_images:
end = min(nr_of_test_images, start + blocksize)
printStatus(INFO, 'processing images from %d to %d' % (start, end-1))
s_time = time.time()
renamed, test_X = feat_file.read(test_imset[start:end])
read_time += time.time() - s_time
s_time = time.time()
output = [None] * len(renamed)
for i in xrange(len(renamed)):
if prob_output:
scores = [models[c].predict_probability(test_X[i]) for c in range(nr_of_concepts)]
else:
scores = [models[c].predict(test_X[i]) for c in range(nr_of_concepts)]
#dec_value = sigmoid_predict(dec_value, A=pA, B=pB)
tagvotes = sorted(zip(concepts, scores), key=lambda v:v[1], reverse=True)
output[i] = '%s %s\n' % (renamed[i], " ".join(["%s %s" % (tag, niceNumber(vote,6)) for (tag,vote) in tagvotes]))
test_time += time.time() - s_time
start = end
fw.write(''.join(output))
fw.flush()
done += len(output)
# done
printStatus(INFO, "%d done. read time %g seconds, test_time %g seconds" % (done, read_time, test_time))
fw.close()
return done
os.path.join(rootpath, testCollection, 'FeatureData', feature))
test_renamed, test_vectors = test_feat_file.read(test_imset)
concepts = readConcepts(testCollection,
testAnnotationName,
rootpath=rootpath)
print('### %s' % os.path.join(trainCollection, 'Models',
trainAnnotationName, feature, modelName))
results = []
for concept in concepts:
model_file_name = os.path.join(rootpath, trainCollection, 'Models',
trainAnnotationName, feature, modelName,
'%s.model' % concept)
model = load_model(model_file_name)
ranklist = [(test_renamed[i], model.predict(test_vectors[i]))
for i in range(len(test_renamed))]
ranklist.sort(key=lambda v: v[1], reverse=True)
names, labels = readAnnotationsFrom(testCollection,
testAnnotationName,
concept,
skip_0=True,
rootpath=rootpath)
test_name2label = dict(zip(names, labels))
sorted_labels = [
test_name2label[x[0]] for x in ranklist if x[0] in test_name2label
]
perf = scorer.score(sorted_labels)
def process(options, testCollection, trainCollection, trainAnnotationName, feature, modelName):
if modelName.startswith('fik'):
from fiksvm.fiksvm import fiksvm_load_model as load_model
else:
from fastlinear.fastlinear import fastlinear_load_model as load_model
rootpath = options.rootpath
overwrite = options.overwrite
prob_output = options.prob_output
numjobs = options.numjobs
job = options.job
#blocksize = options.blocksize
topk = options.topk
outputName = '%s,%s' % (feature,modelName)
if prob_output:
outputName += ',prob'
resultfile = os.path.join(rootpath, testCollection, 'autotagging', testCollection, trainCollection, trainAnnotationName, outputName, 'id.tagvotes.txt')
if numjobs>1:
resultfile += '.%d.%d' % (numjobs, job)
if checkToSkip(resultfile, overwrite):
return 0
concepts = readConcepts(trainCollection,trainAnnotationName, rootpath=rootpath)
nr_of_concepts = len(concepts)
test_imset = readImageSet(testCollection, testCollection, rootpath)
test_imset = [test_imset[i] for i in range(len(test_imset)) if i%numjobs+1 == job]
test_imset = set(test_imset)
nr_of_test_images = len(test_imset)
printStatus(INFO, "working on %d-%d, %d test images -> %s" % (numjobs,job,nr_of_test_images,resultfile))
models = [None] * nr_of_concepts
for c in range(nr_of_concepts):
model_file_name = os.path.join(rootpath,trainCollection,'Models',trainAnnotationName,feature, modelName, '%s.model'%concepts[c])
models[c] = load_model(model_file_name)
if models[c] is None:
return 0
#(pA,pB) = model.get_probAB()
feat_file = StreamFile(os.path.join(rootpath, testCollection, "FeatureData", feature))
makedirsforfile(resultfile)
fw = open(resultfile, "w")
done = 0
feat_file.open()
for _id, _vec in feat_file:
if _id not in test_imset:
continue
if prob_output:
scores = [models[c].predict_probability(_vec) for c in range(nr_of_concepts)]
else:
scores = [models[c].predict(_vec) for c in range(nr_of_concepts)]
tagvotes = sorted(zip(concepts, scores), key=lambda v:v[1], reverse=True)
if topk>0:
tagvotes = tagvotes[:topk]
newline = '%s %s\n' % (_id, " ".join(["%s %s" % (tag, niceNumber(vote,6)) for (tag,vote) in tagvotes]))
fw.write(newline)
done += 1
if done % 1e4 == 0:
printStatus(INFO, "%d done" % done)
feat_file.close()
fw.close()
printStatus(INFO, "%d done" % (done))
return done