Questions about "--adj_aug_infonce"

[HalbertCH]

Dear authors, I have some questions about the "--adj_aug_infonce":
I used the provided "chair_dog" dataset to train the model, and the specific command is:
python main.py --base configs/latent-diffusion/txt2img-1p4B-finetune.yaml -t --actual_resume models/ldm/text2img-large/model.ckpt -n "dog_chair" --gpus 0, --data_root dataset/natural_2_concepts/chair_dog/unmasked/0 --init_word 'dog' --placeholder_string 'a black # with a white *' --presudo_words '#,*' --attn_words 'black,white,#,*' --presudo_words_softmax '#,*' --presudo_words_infonce '#,*' --infonce_temperature 0.3 --infonce_scale 0.00075 --adj_aug_infonce 'black,white'

But got the following error:
File "/opt/data/private/CHB/MCPL/ldm/models/diffusion/ddpm.py", line 1674, in p_losses
[rank0]: cond_presudo_words = torch.cat([cond_presudo_words,cond_adj_aug],dim=0)
[rank0]: RuntimeError: Sizes of tensors must match except in dimension 0. Expected size 2 but got size 1 for tensor number 1 in the list.

Is there something wrong with my command? Thanks for your help in advance!