Argument Outline

It looks like there are a lot of arguments. However, most of them are for developers or alrealy set automatically in cluster submitting environment and users do not need to care about them. Here, we divide these arguments into serveral classes according to the scenario that they are used in. For example, the arguments in common can be used in all scenes. Some arguments can be only used in certain layers. Some are needed by multi machines training in cluster, etc.

√

	args	local train	cluster train	local test	cluster test
common	job	√	√	√	√
	use_gpu	√	√	√	√
	local	√	√	√	√
	config	√	√	√	√
	config_args	√	√	√	√
	num_passes	√	√	√	√
	trainer_count	√	√	√	√
	version	√	√	√	√
	show_layer_stat	√	√	√	√
train	dot_period	√	√
	test_period	√	√
	saving_period	√	√
	show_parameter_stats_period	√	√
	init_model_path	√	√	√
	load_missing_parameter_strategy	√	√
	saving_period_by_batches	√	√
	use_old_updater	√	√
	enable_grad_share	√	√
	grad_share_block_num	√	√
	log_error_clipping	√	√
	log_clipping	√	√
	save_only_one	√	√
	allow_inefficient_sparse_update	√	√
	start_pass	√	√
train/test	save_dir	√	√	√	√
testing during training	test_all_data_in_one_period	√	√
	average_test_period	√	√
test	model_list			√	√
	test_wait			√	√
	test_pass			√	√
	predict_output_dir			√	√
	distribute_test			√	√
Auc/PnpairValidation	predict_file				√
GPU	gpu_id	√	√	√	√
	parallel_nn	√	√	√	√
	allow_only_one_model_on_one_gpu	√	√	√	√
	cudnn_dir	√	√	√	√
	cuda_dir	√	√	√	√
	cudnn_conv_workspace_limit_in_mb	√	√	√	√
RNN	beam_size			√	√
	rnn_use_batch	√	√	√	√
	prev_batch_state	√	√
	diy_beam_search_prob_so			√	√
metric learning	external	√	√	√	√
	data_server_port		√		√
PServer	start_pserver		√		√
	pservers		√		√
	port		√		√
	port_num		√		√
	ports_num_for_sparse		√		√
	nics		√		√
	rdma_tcp		√		√
	small_messages		√
	loadsave_parameters_in_pserver		√		√
	log_period_server		√
	pserver_num_threads		√
	sock_send_buf_size		√
	sock_recv_buf_size		√
	num_gradient_servers		√
	parameter_block_size		√
	parameter_block_size_for_sparse		√
Async SGD	async_count		√
	async_lagged_ratio_min		√
	async_lagged_ratio_default		√
Performance Tuning	log_barrier_abstract		√
	log_barrier_lowest_nodes		√
	log_barrier_show_log		√
	check_sparse_distribution_batches		√
	check_sparse_distribution_ratio		√
	check_sparse_distribution_unbalance_degree		√
	check_sparse_distribution_in_pserver		√
	show_check_sparse_distribution_log		√
Data Provider	memory_threshold_on_load_data	√	√
RandomNumber	seed	√	√
	thread_local_rand_use_global_seed	√	√
UnitTest	checkgrad_eps
Matrix/Vector	enable_parallel_vector	√	√	√	√