| image_root: '/export/share/datasets/vision/coco/images/' | |
| ann_root: 'annotation' | |
| coco_gt_root: 'annotation/coco_gt' | |
| # set pretrained as a file path or an url | |
| pretrained: 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base_caption_capfilt_large.pth' | |
| # size of vit model; base or large | |
| vit: 'base' | |
| vit_grad_ckpt: False | |
| vit_ckpt_layer: 0 | |
| batch_size: 32 | |
| init_lr: 1e-5 | |
| # vit: 'large' | |
| # vit_grad_ckpt: True | |
| # vit_ckpt_layer: 5 | |
| # batch_size: 16 | |
| # init_lr: 2e-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: 5 | |