search

airsplay / lxmert

PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".
MIT License
923 stars 157 forks source link

finetun VQA #100

Open 1144181135 opened 3 years ago

1144181135 commented 3 years ago

Hi, can you provide your finetun model weight file (i.e., the weight of VQA_model.py) on VQA2.0 dataset ? I have some difficulty to download the pretrained features as the bannd http.