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”
When I use VGG-16 as the backbone, the output dimension of the pre trained model is 512, while the required input dimension of the pre trained RPN is 256, which is not a match.
❓ Questions and Help
When I use VGG-16 as the backbone, the output dimension of the pre trained model is 512, while the required input dimension of the pre trained RPN is 256, which is not a match.