search

X-PLUG / mPLUG

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections. (EMNLP 2022)
https://arxiv.org/abs/2205.12005
81 stars 6 forks source link

Cannot reproduce VQA finetuning, please upload checkpoints #4

Open simon-ging opened 1 year ago

simon-ging commented 1 year ago

Dear authors,

I finetuned mPLUG Base on VQAv2 but only get around 75% accuracy instead of the around 80% reported in the readme.

Could you kindly upload the finetuned checkpoints for VQA? I am benchmarking your model and would prefer to benchmark the strongest possible version.

Best,

erjpc commented 1 month ago

Dear authors,

I finetuned mPLUG Base on VQAv2 but only get around 75% accuracy instead of the around 80% reported in the readme.

Could you kindly upload the finetuned checkpoints for VQA? I am benchmarking your model and would prefer to benchmark the strongest possible version.

Best,

Hello, there is something wrong with my code. Can you help me look at it