lavis/projects/blip2/eval/caption_coco_opt2.7b_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

# Bleu_1: 0.832
# Bleu_2: 0.691
# Bleu_3: 0.556
# Bleu_4: 0.438
# METEOR: 0.317
# ROUGE_L: 0.620
# CIDEr: 1.461
# SPICE: 0.252

model:
  arch: blip2_opt
  model_type: caption_coco_opt2.7b
  use_grad_checkpoint: False

datasets:
  coco_caption: # name of the dataset builder
    vis_processor:
        eval:
          name: "blip_image_eval"
          image_size: 364
    text_processor:
        eval:
          name: "blip_caption"
#     build_info:
#         images:
#             storage: '/export/share/datasets/vision/coco/images/'

run:
  task: captioning
  # optimizer
  batch_size_train: 32
  batch_size_eval: 16
  num_workers: 4

  max_len: 30
  min_len: 8
  num_beams: 5

  seed: 42
  output_dir: "output/BLIP2/Caption_coco_opt2.7b"

  evaluate: True
  test_splits: ["test"]

  device: "cuda"
  world_size: 1
  dist_url: "env://"
  distributed: True