06.03.2024, 00:00
(05.03.2024, 20:06)zspeciman Wrote: Great work to the both of you. I've got it working as well.
I've run a video comparison between regular Deoldify and the Hybrid Deoldify. For some reason the Hybrid version is a little brighter, not as dark.
Where is the setting to fix that?
I published in https://github.com/dan64/vs-deoldify
a Model Comparison section, where you can find the Hybrid setup used and the test images.
Dan
(03.03.2024, 19:14)zspeciman Wrote: Around 15-20% faster, that's always good news. Any thoughts about this Google Colorization Transformer?
https://github.com/google-research/googl...er/coltran
There is an article comparing it to Deoldify
https://habr.com/en/companies/ruvds/articles/568426/
I published in https://github.com/dan64/vs-deoldify
a Model Comparison section, using as reference images the ones published in the Habr article. Instead of using a subjective measure to evaluate the color differences I used a quantitative method using the CIEDE2000 color similarity metric. In the test the ColTran + TensorFlow 2.4.1 was the model that performed worse.
Dan