Skip to content

Latest commit

 

History

History
11 lines (8 loc) · 744 Bytes

README.md

File metadata and controls

11 lines (8 loc) · 744 Bytes

The code of 'Local Context Attention Learning for Fine-Grained Scene Graph Generation'.

Install commond: torch==2.0.1 torchvision==0.15.2. python setup.py build develop. More details on datasets and installations can be found in Scene-Graph-Benchmark.pytorch.

You can evaluate the trained model with the commond: sh scripts/test.sh. The webpath of the pre-trained model is: 'https://drive.google.com/drive/folders/1lOnfl0iHAxYHeW9PJIzTyfqnl8RxNfLg?usp=drive_link'

Acknowledgement

The code is built on Scene-Graph-Benchmark.pytorch, and RUNet Thanks for their excellent codes.