Metrics for RE and IS - Githubissues

alexandre01 / deepsvg

[NeurIPS 2020] Official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Includes a PyTorch library for deep learning with SVG data.

https://www.reshot.ai

MIT License

981 stars 99 forks source link

Metrics for RE and IS #25

Open m43 opened 2 years ago

m43 commented 2 years ago

Hej Alexandre, thanks for the cool work on SVGs!

I am trying to reproduce your table with quantitative measurements, but cannot find the Reconstruction Error (RE) and Interpolation Smoothness (IS) in the codebase. Could you point me to them (or do you mind sharing them)?

idevede commented 2 years ago

Hey Alexandre, I am also wondering how can I access the metrics for RE and IS.