airsplay / lxmert

PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".
MIT License
935 stars 158 forks source link

How to build 'all_ans.json' #43

Closed sileod closed 4 years ago

sileod commented 4 years ago

Hi and thank you for sharing your code in such an actually usable way ! The pretraining instructions mention a file name 'all_ans.json', which is required for launching the pretraining instruction, but I coulnd't find out how to download or build it, and when I run bash run/lxmert_pretrain.bash 0,1,2,3 --multiGPU --tiny I get FileNotFoundError: [Errno 2] No such file or directory: 'data/lxmert/all_ans.json' Could anyone tell me how to get all_ans ? Many thanks

airsplay commented 4 years ago

Thanks. The file is contained in the repo here: https://github.com/airsplay/lxmert/blob/master/data/lxmert/all_ans.json.