Training on art images, hyper-parameter tuning

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

1.03k stars 228 forks source link

Training on art images, hyper-parameter tuning #102

Open ChrisAlthaus opened 3 years ago

ChrisAlthaus commented 3 years ago

Hi, I would like to train the network on art images (paintings, ...). Do you have any suggestions for the hyper-parameters w.r. to this kind of input images? I realized that the architecture has quite a lot of knobs for tuning, so I'm a bit confused if there's a special parameters for increasing performance.

Greetings, Christian

BlockchainRev commented 3 years ago

Hey @ChrisAlthaus! How did you manage to create the dataset for the art images?