rubenvillegas / iclr2017mcnet

Tensorflow implementation of the ICLR 2017 paper: Decomposing Motion and Content for Natural Video Sequence Prediction
https://sites.google.com/a/umich.edu/rubenevillegas/iclr2017
MIT License
109 stars 34 forks source link

Could you suggest me an approach for working with MCNet on a Custom Data #13

Closed sharathyadav1993 closed 5 years ago

sharathyadav1993 commented 5 years ago

Hi Ruben,

Thank you for the MCNet code. I want to use your MCNet for video frame extrapolation task for my custom dataset. It would be great if you suggest me some approach in doing it, or share me some generalized code to work for my dataset.

Regards Sharath

rubenvillegas commented 5 years ago

Hi Sharath,

If you look at the file ./src/utils.py, there are functions to load each dataset (e.g., load_kth_data). You should add another function to load your specific dataset, and follow the same input/output scheme. Hope this helps.

Regards, Ruben