def create_keras_model_dense():
mc = MeasureCollection()
m = Measurement(1, 1111111111, 48, 14, 4,
GroundTruth(1111, GroundTruthClass.FREE_SPACE))
mc.add_measure(m)
dataset = DataSet.get_raw_sensor_dataset([mc])
model = Sequential()
model.add(Dense(64, activation='relu', input_dim=len(dataset.x[0])))
model.add(Dropout(0.1))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.1))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.1))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.1))
model.add(Dense(len(dataset.class_labels), activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
return model
base_path = 'C:\\sw\\master\\collected data\\'
options = {
'mc_min_speed': 1.0,
'mc_merge': True,
'mc_separation_threshold': 1.0,
'mc_min_measure_count': 2,
# 'mc_surrounding_times_s': [2.0, 5.0],
'outlier_threshold_distance': 1.0,
'outlier_threshold_diff': 0.5,
# 'replacement_values': {0.01: 10.01},
'min_measurement_value': 0.06,
}
dataset = None
measure_collections_files_dir = MeasureCollection.read_directory(
base_path, options=options)
measure_collections_dir = {}
for file_name, measure_collections in measure_collections_files_dir.items():
print(file_name)
dataset = DataSet.get_raw_sensor_dataset_per_10cm(measure_collections,
dataset=dataset,
is_softmax_y=True)
measure_collections_dir.update(
MeasureCollection.mc_list_to_dict(measure_collections))
# Generate dummy data
x_train = [x_t for i, x_t in enumerate(dataset.x) if i < len(dataset.x) * 0.8]
y_train = [
x_t for i, x_t in enumerate(dataset.y_true) if i < len(dataset.x) * 0.8
]
x_test = [x_t for i, x_t in enumerate(dataset.x) if i >= len(dataset.x) * 0.8]
'outlier_threshold_diff': 0.5,
'replacement_values': {
0.01: 10.01
},
'min_measurement_value': 0.06,
}
# measurements = Measurement.read('C:\\sw\\master\\collected data\\data_20170718_tunnel\\raw_20170718_074348_696382.dat',
# 'C:\\sw\\master\\collected data\\data_20170718_tunnel\\raw_20170718_074348_696382.dat_images_Camera\\00gt1500721683.81.dat',
# options)
#
# visualization.show_distance_signal(measurements, plt.figure(1))
# visualization.show_distance_signal_scatter(measurements, plt.figure(2))
#free_space_measure_collections = []
measure_collections_dir = MeasureCollection.read_directory(base_path,
options=options)
#gt25 = 0
i = 1
for file_name, measure_collection in measure_collections_dir.items():
#visualization.show_2d_scatter(measure_collection, fig=plt.figure(1))
#visualization.show_distances_plus_segmentation(measure_collection, fig=plt.figure(i))
#visualization.show_distance_for_class(measure_collection, [GroundTruthClass.OVERTAKEN_BICYCLE], fig=plt.figure(i))
#gt25 += len([mc for mc in measure_collection if mc.get_probable_ground_truth() == GroundTruthClass.FREE_SPACE and mc.length >= 5])
#free_space_measure_collections.extend([mc for mc in measure_collection if mc.get_probable_ground_truth() == GroundTruthClass.FREE_SPACE]);
i += 1
#
# print gt25
# visualization.show_distance_histogram_length(free_space_measure_collections, fig=plt.figure(i))
#measure_collections = MeasureCollection.read_from_file('C:\\sw\\master\\collected data\\data_20170707\\tagged_mc_20170705_065613_869794.dat')
#visualization.show_distances_plus_segmentation(measure_collections)
#visualization.show_distance_signal(measurements)
os.path.join(
camera_folder,
gt_files[0]),
options=options)
cnt_measurements += len(measurements)
total_seconds += measurements[len(
measurements) - 1].timestamp - measurements[0].timestamp
return cnt_measurements, total_seconds
if __name__ == '__main__':
base_path = 'C:\\sw\\master\\collected data\\'
options = {}
measure_collections = {}
excluded_mcs = options.get('exclude_mcs', [])
print('')
raw_size = get_raw_dataset_size(base_path, options)
print('cnt_measurements, total_seconds')
print(raw_size)
print('')
measure_collections_dir = MeasureCollection.read_directory(base_path,
options=options)
print('')
print('cnt_measure_collections, cnt_measurements, total_seconds')
print(MeasureCollection.get_size(measure_collections_dir))
'outlier_threshold_distance': 1.0,
'outlier_threshold_diff': 0.5,
'max_measure_value': 10.0,
# 'replacement_values': {0.01: 10.01},
'min_measurement_value': 0.06
}
camera_folder = scenario_path + '_images_Camera\\'
ground_truth_file = [
os.path.join(camera_folder, f) for f in os.listdir(camera_folder) if
os.path.isfile(os.path.join(camera_folder, f)) and f.startswith('00gt')
][0]
measurements_scenario = Measurement.read(scenario_path,
ground_truth_file,
options=options)
measure_collections_scenario = MeasureCollection.create_measure_collections(
measurements_scenario, options=options)
dataset_scenario = DataSet.get_dataset(measure_collections_scenario)
options['exclude_mcs'] = measure_collections_scenario
dataset = None
measure_collections_files_dir = MeasureCollection.read_directory(
base_path, options=options)
for file_name, measure_collections in measure_collections_files_dir.items(
):
dataset = DataSet.get_dataset(measure_collections, dataset=dataset)
clf = RandomForestClassifier(n_estimators=1000, n_jobs=-1, random_state=42)
clf.fit(dataset.x, dataset.y_true)
predictions = clf.predict(np.array(dataset_scenario.x)).reshape(1, -1)[0]
'mc_merge': True,
'mc_separation_threshold': 1.0,
'mc_min_measure_count': 2,
# 'mc_surrounding_times_s': [2.0, 5.0],
'outlier_threshold_distance': 1.0,
'outlier_threshold_diff': 0.5,
# 'replacement_values': {0.01: 10.01},
'min_measurement_value': 0.06,
}
dataset_raw = None
dataset_10cm = None
dataset_10cm_surrounding = None
dataset_parking = None
#write_to_file(base_path, ml_file_path)
measure_collections_files_dir = MeasureCollection.read_directory(
base_path, options=options)
parking_space_map_clusters, _ = create_parking_space_map(
measure_collections_files_dir)
measure_collections_files_dir = filter_parking_space_map_mcs(
measure_collections_files_dir, parking_space_map_clusters)
print(MeasureCollection.get_size(measure_collections_files_dir))
measure_collections_dir = {}
for file_name, measure_collections in measure_collections_files_dir.items(
):
print(file_name)
#print(len(measure_collection))
#measure_collection = filter_acceleration_situations(measure_collection)
#print('filtered', len(measure_collection))
#MeasureCollection.write_arff_file(measure_collections1, ml_file_path)