Home Artists Posts Import Register

Content

I am releasing a Git to help people to train their own Models to be used with Dain-App.

I tried my best to make the script user friendly, but it still require some knowledge in the model training area to be used. A little or python knowledge won't hurt either.


A Model is what do the "interpolation" magic in a the software, training it from scratch can take thousands of images as input and weeks of processing.


Here is the link to the Training Colab File:

https://colab.research.google.com/github/BurguerJohn/DAIN/blob/master/DainModelTraining.ipynb

It support creating Models from scratch or continue training on top of existing models.


If you want to test your new models, just replace the model_weights/best.pth inside DainApp

Files

BurguerJohn/DAIN

Train your model in Colab Wenbo Bao, Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CVPR 2019 This work is developed based on our TPAMI work MEMC-Net, where we propose the adaptive warping layer. Please also consider referring to it.

Comments

Anonymous

thank you for this.