image_root: '/home/notebook/data/group/projects/tagging/caption/datasets/public/coco/'

ann_root: 'dataset/caption_dataset'
coco_gt_root: 'dataset/caption_dataset'

pretrained: '/home/notebook/code/personal/S9049611/BLIP/output/pretrain_caption_tagtotext_v2_bert_asl'

# size of vit model; base or large
vit: 'swin_b'
vit_grad_ckpt: False
vit_ckpt_layer: 0

batch_size: 35
init_lr: 5e-6 

image_size: 384

# generation configs
max_length: 20  
min_length: 5
num_beams: 3
prompt: 'a picture of '

# optimizer
weight_decay: 0.05
min_lr: 0
max_epoch: 10

text_pretrain: 'bert'

class_num: 3429
threshold: 0.7