def run_opf_supervised(self):
le = preprocessing.LabelEncoder()
le.fit(self.result_classes)
cross_result_classes = le.transform(self.result_classes)
cross_result_classes = cross_result_classes.astype(numpy.int32)
self.log("Result data size: " + str(len(self.result_data)))
self.log("Cross classes size: " + str(len(cross_result_classes)))
self.log("Training OPF")
self.opf_sup_cls = libopf_py.OPF()
t_opf_start = time.time()
self.opf_sup_cls.fit(self.result_data,
cross_result_classes,
metric=self.distance_function)
t_opf_end = time.time() - t_opf_start
self.params_output['time_classificator_fit'] = t_opf_end
images_info = filesprocess.get_files(self.test_path)
labels_test = []
labels_hist_array = []
#bins = range(self.bins_size)
pool = multiprocessing.Pool()
preds_data = []
preds_data = pool.map(
func_star_extract_descriptors_predict_test,
itertools.izip(images_info, itertools.repeat(self)))
for data in preds_data:
labels_hist_array.extend(data[0])
labels_test.extend(data[1])
labels_hist_array = numpy.asarray(labels_hist_array, numpy.float64)
self.log("Generating predictions")
prediction = self.opf_sup_cls.predict(labels_hist_array)
labels_predicted = le.inverse_transform(prediction)
pool.close()
pool.terminate()
accuracy = metrics.accuracy_score(labels_test, labels_predicted)
precision = metrics.precision_score(labels_test, labels_predicted)
recall = metrics.recall_score(labels_test, labels_predicted)
f1 = metrics.f1_score(labels_test, labels_predicted)
self.params_output['accuracy'] = accuracy
self.params_output['precision'] = precision
self.params_output['recall'] = recall
self.params_output['F1'] = f1
self.log("Accuracy: " + str(accuracy))
self.log("Precision: " + str(precision))
self.log("Recall: " + str(recall))
self.log("F1: " + str(f1))
return accuracy, precision, recall, f1
def run_test(self):
le = preprocessing.LabelEncoder()
le.fit(self.result_classes)
#list(le.classes_)
cross_result_classes = le.transform(self.result_classes)
cross_result_classes = cross_result_classes.astype(numpy.int32)
result_data_array = numpy.asarray(self.result_data, numpy.float64)
self.log("Creating OPF")
self.opf_cls = libopf_py.OPF()
t_opf_start = time.time()
#self.svm_cls.fit(self.result_data, self.result_classes)
self.opf_cls.fit(result_data_array,
cross_result_classes,
metric=self.distance_function)
t_opf_end = time.time() - t_opf_start
self.params_output['time_classificator_fit'] = t_opf_end
labels_test = []
labels_predicted = []
images_info = filesprocess.get_files(self.test_path)
for idx, image_info in enumerate(images_info):
self.log("Generating hist " + str(idx) + " of " +
str(len(images_info)))
img_path = image_info[0]
img_folder = image_info[1]
features, descriptors = featureextractor.extract_descriptor(
img_path, None, "OVERFEAT", "OVERFEAT")
if (descriptors != None):
descriptors = numpy.asarray(descriptors, numpy.float64)
prediction = self.opf_cls.predict(descriptors)
labels_predicted.append(prediction[0])
label_trans = le.transform([img_folder])
labels_test.append(label_trans[0])
print labels_predicted
accuracy = metrics.accuracy_score(labels_test, labels_predicted)
self.log("Accuracy: " + str(accuracy))
precision = metrics.precision_score(labels_test, labels_predicted)
self.log("Precision: " + str(precision))
recall = metrics.recall_score(labels_test, labels_predicted)
self.log("Recall: " + str(recall))
f1 = metrics.f1_score(labels_test, labels_predicted)
self.log("F1: " + str(f1))
self.params_output['accuracy'] = accuracy
self.params_output['precision'] = precision
self.params_output['recall'] = recall
self.params_output['F1'] = f1
return accuracy, precision, recall, f1
def run_opf_supervised(self):
le = preprocessing.LabelEncoder()
le.fit(self.result_classes)
cross_result_classes = le.transform(self.result_classes)
cross_result_classes = cross_result_classes.astype(numpy.int32)
self.log("Result data size: " + str(len(self.result_data)))
self.log("Cross classes size: " + str(len(cross_result_classes)))
self.log("Training OPF")
self.opf_sup_cls = libopf_py.OPF()
t_opf_start = time.time()
self.opf_sup_cls.fit(self.result_data, cross_result_classes,metric=self.distance_function)
t_opf_end = time.time() - t_opf_start
self.params_output['time_classificator_fit'] = t_opf_end
images_info = filesprocess.get_files(self.test_path)
labels_test = []
labels_hist_array = []
#bins = range(self.bins_size)
for idx, image_info in enumerate(images_info):
self.log("Generating hist test " + str(idx) + " of " + str(len(images_info)))
img_path = image_info[0]
img_folder = image_info[1]
features, descriptors = featureextractor.extract_descriptor(img_path, self.thumbnail_size,self.feature_type,self.descriptor_type)
if (descriptors != None):
label_hist = self.opf_predict(descriptors, self.n_clusters)
labels_hist_array.append(label_hist)
labels_test.append(img_folder)
labels_hist_array = numpy.asarray(labels_hist_array, numpy.float64)
self.log("Generating predictions")
prediction = self.opf_sup_cls.predict(labels_hist_array)
labels_predicted = le.inverse_transform(prediction)
accuracy = metrics.accuracy_score(labels_test, labels_predicted)
precision = metrics.precision_score(labels_test, labels_predicted)
recall = metrics.recall_score(labels_test, labels_predicted)
f1 = metrics.f1_score(labels_test, labels_predicted)
self.params_output['accuracy'] = accuracy
self.params_output['precision'] = precision
self.params_output['recall'] = recall
self.params_output['F1'] = f1
self.log("Accuracy: " + str(accuracy))
self.log("Precision: " + str(precision))
self.log("Recall: " + str(recall))
self.log("F1: " + str(f1))
return accuracy, precision, recall, f1
def _opf():
label_train_32 = label_train.astype(np.int32)
label_test_32 = label_test.astype(np.int32)
O = libopf_py.OPF()
t = time()
O.fit(data_train, label_train_32)
opf_results[i, 3] = time() - t
t = time()
predicted = O.predict(data_test)
opf_results[i, 0] = precision_score(label_test_32, predicted)
opf_results[i, 1] = recall_score(label_test_32, predicted)
opf_results[i, 2] = f1_score(label_test_32, predicted)
gc.collect()
def opf():
# OPF only supports 32 bits labels at the moment
label_train_32 = label_train.astype(numpy.int32)
label_test_32 = label_test.astype(numpy.int32)
O = libopf_py.OPF()
t = time.time()
O.fit(dist_train, label_train_32, precomputed_distance=True)
# O.fit(dist_train, label_train_32, precomputed_distance=True, learning="agglomerative", split=0.8)
print("OPF: time elapsed in fitting: %f secs" % (time.time() - t))
t = time.time()
predicted = O.predict(dist_test)
print("OPF: time elapsed in predicting: %f secs" % (time.time() - t))
print("Classification report for OPF:\n%s\n" %
(classification_report(label_test_32, predicted)))
print("Confusion matrix:\n%s" %
confusion_matrix(label_test_32, predicted))
def run_opf_supervised(self):
le = preprocessing.LabelEncoder()
le.fit(self.result_classes)
#list(le.classes_)
cross_result_classes = le.transform(self.result_classes)
cross_result_classes = cross_result_classes.astype(numpy.int32)
# unique_classes = numpy.asarray(self.result_classes)
# unique_classes = numpy.unique(unique_classes)
# unique_classes = numpy.sort(unique_classes)
# num_samples = len(self.result_data)
# num_classes = len(unique_classes)
# num_features = len(self.result_data[0])
O = libopf_py.OPF()
result_data_array = numpy.array(self.result_data)
self.log("Training OPF")
t_opf_start = time.time()
O.fit(result_data_array, cross_result_classes,metric=self.distance_function)
t_opf_end = time.time() - t_opf_start
self.params_output['time_classificator_fit'] = t_opf_end
images_info = filesprocess.get_files(self.test_path)
bins = range(self.kmeans_k)
labels_test = []
labels_hist_array = []
for idx, image_info in enumerate(images_info):
self.log("Generating hist " + str(idx) + " of " + str(len(images_info)))
img_path = image_info[0]
img_folder = image_info[1]
label_test = le.transform([img_folder])
features, descriptors = featureextractor.extract_descriptor(img_path, self.thumbnail_size,self.feature_type,self.descriptor_type)
if (descriptors != None):
labels = self.kmeans_cls.predict(descriptors)
labels_hist = numpy.histogram(labels, bins=bins, density=True)[0]
labels_hist_array.append(labels_hist)
labels_test.append(label_test)
#labels_hist_array = numpy.array([labels_hist])
labels_hist_array = numpy.asarray(labels_hist_array, numpy.float64)
labels_predicted = O.predict(labels_hist_array)
#labels_predicted = le.inverse_transform(prediction)
#self.log("Prediction: " + str(pridicted_label[0]))
#self.log("Real: " + str(img_folder))
accuracy = metrics.accuracy_score(labels_test, labels_predicted)
precision = metrics.precision_score(labels_test, labels_predicted)
recall = metrics.recall_score(labels_test, labels_predicted)
f1 = metrics.f1_score(labels_test, labels_predicted)
self.params_output['accuracy'] = accuracy
self.params_output['precision'] = precision
self.params_output['recall'] = recall
self.params_output['F1'] = f1
self.log("Accuracy: " + str(accuracy))
self.log("Precision: " + str(precision))
self.log("Recall: " + str(recall))
self.log("F1: " + str(f1))
return accuracy, precision, recall, f1