How to measure and display the metric values for evaluating

LJOVO / TranSalNet

TranSalNet: Towards perceptually relevant visual saliency prediction. Neurocomputing (2022)

https://doi.org/10.1016/j.neucom.2022.04.080

MIT License

53 stars 10 forks source link

How to measure and display the metric values for evaluating #8

Open fadhfaiz opened 4 months ago

fadhfaiz commented 4 months ago

Hi,

I would like to retrain the model and am interested in understanding how to measure and display the metric values such as Correlation Coefficient (CC), Structural Similarity Index (SIM), Normalized Scanpath Saliency (NSS), and Kullback-Leibler divergence (KL). Could you please provide a step-by-step guide on how to achieve and show the metrics?

Thank you!

LJOVO commented 4 months ago

Hi,

Please find the evaluation code in this repo: https://github.com/cvzoya/saliency

Best