Looks like to high resolution on input and color map is not properly distributed (limitation described by paper).
Side to this somehow i start to like color version of movies (weird as i was against colorization process).
Looks like adding third layer of neural network to improve temporal stability may give quite robust movie plugin (but perhaps this is too naive expectation).
+ Reply to Thread
Results 31 to 37 of 37
In case you are not aware of, the Chaplin sample was created using a different set of tools and training sets. (probably not related to the Wasada team)
The underlining idea is still machine-learning however.Stopping development until someone save me from poverty or get me out of Hong Kong...
What is the ->
Here is a trained TensorFlow model to play around with:
This model containes the VGG16 model from Karen Simonyan and Andrew Zisserman (that I converted to TensorFlow). It is available for non-commercial use only.
For what is the 492M download good ? Is it possible to compile it ?
Sorry I am noob...
I don't think you can compile it... like the waifu2x model data, they are not the actual executable.Stopping development until someone save me from poverty or get me out of Hong Kong...
I don't think you can compile it... like the waifu2x model data, they are not the actual executable.
Mecab added flavor option on his page.
city, sky, architecture, night and sunset or no flavor