def eval_models(proceed_step):
params = get_recursive_params(proceed_step)
params = init_save_dirs(params)
if not is_initial_params_suitable(params):
return
if params.fusion_levels and not is_suitable_level_fusion(params):
return
if params.load_features and not is_cnn_rnn_features_available(params, cnn=0):
return
if params.data_type != DataTypes.RGBD and not is_cnn_rnn_features_available(params, cnn=1):
return
logfile_name = params.log_dir + proceed_step + '/' + get_timestamp() + '_' + str(params.trial) + '-' + \
params.net_model + '_' + params.data_type + '_split_' + str(params.split_no) + '.log'
init_logger(logfile_name, params)
if params.net_model == Models.AlexNet:
model = AlexNet(params)
elif params.net_model == Models.VGGNet16:
model = VGG16Net(params)
elif params.net_model == Models.ResNet50 or params.net_model == Models.ResNet101:
model = ResNet(params)
elif params.net_model == Models.DenseNet121:
model = DenseNet(params)
else:
print('{}{}Unsupported model selection! Please check your model choice in arguments!{}'
.format(PrForm.BOLD, PrForm.RED, PrForm.END_FORMAT))
return
model.eval()
def test_automatic_timestamp(self):
timestamp = main.get_timestamp()
app_id = 'test-application'
data = json.dumps({'test-type': 'test-data'})
event = main.create_event_ds(app_id, 'test-event', data)
self.assertEqual(event.name, 'test-event')
self.assertAlmostEqual(event.ts, timestamp)
self.assertEqual(event.data, data)
def test_timestamped_events(self):
timestamp = main.get_timestamp()
data = json.dumps({'test-type': 'test-data', 'creation-time': timestamp})
app_id = 'test-application'
event = main.create_event_ds(app_id, 'test-event', data)
self.assertEqual(event.name, 'test-event')
self.assertEqual(event.ts, timestamp)
self.assertEqual(event.data, data)
def extract_fixed_features():
params = get_extraction_params()
params = init_save_dirs(params)
if not is_initial_params_suitable(params):
return
logfile_name = params.log_dir + params.proceed_step + '/' + get_timestamp() + '_' + params.net_model + '_' + \
params.data_type + '_cnn_extraction.log'
init_logger(logfile_name, params)
fixed_extraction(params)
def save_depth():
params = get_save_depth_params()
if params.data_type != DataTypes.Depth:
print('{}{}The parameter {}--data-type{} should be {}depth{}!{}'.
format(PrForm.BOLD, PrForm.RED, PrForm.BLUE, PrForm.RED, PrForm.GREEN, PrForm.RED, PrForm.END_FORMAT))
return
logfile_name = params.log_dir + params.proceed_step + '/' + get_timestamp() + '_' + params.data_type + \
'_colorized_save.log'
init_logger(logfile_name, params)
process_depth_save(params)
def finetune_model():
params = get_finetune_params()
params = init_save_dirs(params)
if not is_initial_params_suitable(params):
return
logfile_name = params.log_dir + params.proceed_step + '/' + get_timestamp() + '_' + str(params.trial) + '-' + \
params.net_model + '_' + params.data_type + '_split_' + str(params.split_no) + '.log'
init_logger(logfile_name, params)
process_finetuning(params)
