airsplay / lxmert

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

img_root #4

Closed joey1993 closed 5 years ago

joey1993 commented 5 years ago

https://github.com/airsplay/lxmert/blob/fc1b287cce280f717a3b1b076c2c23dfd492b880/data/mscoco_imgfeat/extract_coco_image.py#L62

a small bug: IMG_ROOT --> img_root :)

airsplay commented 5 years ago

Many thanks for pointing it out! I have fixed it.