def get_save_depth_params():
parser = get_initial_parser()
params = parser.parse_args()
params.net_model = 'all'
params.proceed_step = RunSteps.COLORIZED_DEPTH_SAVE
params = init_save_dirs(params)
return params
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 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 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)
help="Pre-trained network model to be employed as the feature extractor"
)
parser.add_argument("--log-dir",
dest="log_dir",
default="../logs",
help="Log directory")
parser.add_argument("--data-type",
dest="data_type",
default="rgbd",
choices=["rgb", "depth", "rgbd"])
parser.add_argument("--debug-mode",
dest="debug_mode",
default=0,
type=int,
choices=[0, 1])
params = parser.parse_args()
params.proceed_step = RunSteps.OVERALL_RUN
params.load_features = 1
return params
if __name__ == '__main__':
params = get_params()
params = init_save_dirs(params)
if params.task == "object":
wrgbd_main(params)
else:
sunrgbd_main(params)
