Generating scene-graphs from custom images using a pre-trained model

NVIDIA / ContrastiveLosses4VRD

Implementation for the CVPR2019 paper "Graphical Contrastive Losses for Scene Graph Generation"

Other

200 stars 41 forks source link

Generating scene-graphs from custom images using a pre-trained model #21

Open mrfarazi opened 4 years ago

mrfarazi commented 4 years ago

Hello, I was wondering if there was a way to run inference on custom image(s) without gt annotations. For example, if I wanted to generate scene-graph using your pre-trained models from a custom image not in visual genome/VRD dataset, would I be able to do that.

Thanks!

sak-18 commented 4 years ago

@mrfarazi could you find something?

Muhammaddany commented 1 year ago

could you find something...??? kindly tell the pre-trained model name.

ZhongQiyu commented 1 month ago

https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch This might be a good one to check, as nowadays we apply instruction following and tuning to work on the iterations.