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

question on faster r-cnn feature extraction #97

Open theaitetus opened 3 years ago

theaitetus commented 3 years ago

hello thanks for sharing your great work on public.

I have a question on feature for you model.

Which model did you use for feature extraction, faster r-cnn trained on ms-coco or visual genome?

thank you in advance