Error executing training step 3

[GregorioFornetti]

In the README of the repository, the third command to execute to train the model is the following:

python train.py --cfg_file ./cfgs/predictor_masked_bn_tune.yaml --extra_tag predictor_tune --ckpt ../output/cfgs/predictor/default/ckpt/latest_model.pth --hard_drop

I tried to execute it, but this error occurred:

usage: train.py [-h] [--cfg_file CFG_FILE] [--batch_size BATCH_SIZE] [--epochs EPOCHS] [--workers WORKERS] [--extra_tag EXTRA_TAG] [--ckpt CKPT]
                [--pretrained_model PRETRAINED_MODEL] [--launcher {none,pytorch,slurm}] [--tcp_port TCP_PORT] [--sync_bn] [--fix_random_seed]
                [--ckpt_save_interval CKPT_SAVE_INTERVAL] [--local_rank LOCAL_RANK] [--max_ckpt_save_num MAX_CKPT_SAVE_NUM] [--merge_all_iters_to_one_epoch]
                [--set ...] [--max_waiting_mins MAX_WAITING_MINS] [--start_epoch START_EPOCH] [--num_epochs_to_eval NUM_EPOCHS_TO_EVAL] [--save_to_file]
                [--use_tqdm_to_record] [--logger_iter_interval LOGGER_ITER_INTERVAL] [--ckpt_save_time_interval CKPT_SAVE_TIME_INTERVAL] [--wo_gpu_stat WO_GPU_STAT]
                [--use_amp]
train.py: error: unrecognized arguments: --hard_drop

The train.py file I used was the one given in the repository. Is there another version of this file with the parameter --hard_drop available? What should I do to train the model?