lavis/projects/blip/eval/vqav2_eval.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_vqa
  model_type: vqav2
  image_size: 480

datasets:
  coco_vqa: # name of the dataset builder
    type: eval
    vis_processor:
        eval:
          name: "blip_image_eval"
          image_size: 480
    text_processor:
        eval:
          name: "blip_question"

run:
  task: vqa
  # optimization-specific
  batch_size_train: 16
  batch_size_eval: 64
  num_workers: 4

  # inference-specific
  max_len: 10
  min_len: 1
  num_beams: 3
  num_ans_candidates: 128
  inference_method: "rank"

  seed: 42
  output_dir: "output/BLIP/VQA"

  evaluate: True
  test_splits: ["val"]

  # distribution-specific
  device: "cuda"
  world_size: 1
  dist_url: "env://"
  distributed: True