search

KaihuaTang / Scene-Graph-Benchmark.pytorch

A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiased Scene Graph Generation from Biased Training CVPR 2020”
MIT License
1.06k stars 228 forks source link

Feature extraction #117

Open digbose92 opened 3 years ago

digbose92 commented 3 years ago

❓ Questions and Help

I am trying to extract features (relational/object/subject) for custom images using the different architectures used here. Is there a starter script for extracting features from custom images? If not, it will be nice to have some pointers on how to proceed. Thanks

tongbaochen commented 2 years ago

Hi, I am also trying to extract features (relational/object/subject) for custom images too, have you figured out how to make it ?

bibekyess commented 1 year ago

Hello @digbose92 and @tongbaochen, did you figure out how to use feature extraction modules with different architecture for SGDET training? It would be great if you could give me some hint. Thank you!