search

MILVLG / mcan-vqa

Deep Modular Co-Attention Networks for Visual Question Answering
Apache License 2.0
438 stars 88 forks source link

pretrained frcnn and network #2

Closed nithinraok closed 5 years ago

nithinraok commented 5 years ago

Hi, Thanks for your project and great work. I am looking to run it on new images but using other pretrained faster-rcnn features like COCO giving wrong answer. Can you please provide pretrained faster-rcnn model and network to replicate.

Thanks

MIL-VLG commented 5 years ago

hi，the pre-trained Faster RCNN model are provided at here. We use the model with K\in[10,100] to extract visual features from the image.

nithinraok commented 5 years ago

Thanks for your swift response. I was guessing you used other pytorch model instead of caffe to get Visual Genome features.