lavis/configs/models/blip_feature_extractor_base.yaml

 # Copyright (c) 2022, salesforce.com, inc.
 # All rights reserved.
 # SPDX-License-Identifier: BSD-3-Clause
 # For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause

model:
  arch: blip_pretrain
  pretrained: "https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base_capfilt_large.pth"

  # vit encoder
  vit_type: "base"
  vit_grad_ckpt: False
  vit_ckpt_layer: 0

  image_size: 224

  # bert config
  med_config_path: "configs/models/med_config.json"

  embed_dim: 256

preprocess:
  vis_processor:
      eval:
        name: "blip_image_eval"
        image_size: 224
  text_processor:
      eval:
        name: "blip_caption"