search

linjieli222 / VQA_ReGAT

Research Code for ICCV 2019 paper "Relation-aware Graph Attention Network for Visual Question Answering"
https://arxiv.org/abs/1903.12314
MIT License
180 stars 38 forks source link

Test with new images #3

Closed pqviet closed 5 years ago

pqviet commented 5 years ago

Can you provide the pretrained model for generating visual features, so that I can test with new images?

linjieli222 commented 5 years ago

The visual features are extracted using bottom-up-attention model .

You should be able to directly test with implicit relation.

For spatial relation, look into build_graph function to extract spatial relations.

For semantic relation, we are not releasing the semantic relation classifier at this moment.

Thanks!