Baseline model for nocaps benchmark, a re-implementation based on the UpDown image captioning model trained on the COCO dataset (only), and with added support of decoding using Constrained Beam Search.

If you find this code useful, please consider citing our paper, the paper which proposed original model, and EvalAI — the platform which hosts our evaluation server. All bibtex available in CITATION.md.

1. How to setup this codebase?
2. How to train your captioner?
3. How to evaluate or run inference?

Extensive documentation available at nocaps.org/updown-baseline. Use it as an API reference to navigate through and build on top of our code.

Pre-trained checkpoints with the provided configs in (configs directory) are available to download:

• Checkpoint (.pth file): updown.pth
• Predictions on nocaps val: updown_nocaps_val.json

Note: While CBS is inference-only technique, it cannot be used on this checkpoint. CBS requires models to have 300-dimensional froze GloVe embeddings, this checkpoint has 1000- dimensional word embeddings which are learned during training.

• Checkpoint (.pth file): updown_plus_cbs.pth

Note: Since CBS is inference-only technique, this particular checkpoint can be used without CBS decoding. It yields similar results to the UpDown Captioner trained using learned word embeddings during training.

• Predictions on nocaps val: updown_plus_cbs_nocaps_val_with_cbs.json

• Predictions on nocaps val: updown_plus_cbs_nocaps_val_without_cbs.json