during training of VQA, validation is too slow. I guess it's due to trie search. how to speed up?

[HiSultryMan]

No description provided.

[yangapku]

Hi, in the current code we use all-candidate evaluation for validation during training, which is much slower than beam-search evaluation (as mentioned in the readme). You can try to disable (use a large --validate-interval) automatic validation during training and manually use evaluate.py to evaluate the checkpoint on the validation set using beam-search evaluation, which is much faster. Or moving further, you can try to move the beam-search evaluation code from eval_utils.py to replace the automatic validation code during training in the valid_step method of vqa_gen.py, which we haven't done yet.

[yangapku]

@HiSultryMan Hi, we have updated the code to support beam-search validation during VQA fine-tuning, which will be much faster than the previous all-candidate validation. For more information, please refer to this PR #79 and pull the latest codebase.