Training with Vimeo90K

[jhkjames1110]

Hello, I am trying to train a new model to take advantage of your great color propagation algorithm.

I have the following questions:

1. I keep getting the following assertion error when trying to train the model with Vimeo90K (the same data as you have used).
   Given groups=1, weight of size [64, 196, 3, 3], expected input[4, 136, 68, 68] to have 196 channels, but got 136 channels instead
   I am sending vimeo frames as input for the lr_set with the upscale_factor changed to 1 from params.json.

Could you please provide me with a reason for this error? Were any changes made to the code for training for the Vimeo90K dataset?

2. How did you change the directory structure for Vimeo90K? Seems like the preferred directory structure is very different to that of the dataset provided from the link you've provided in one of the closed issues.

Thank you in advance!

[jhkjames1110]

1. Fix: I changed the path_size from 64 to 256 to allow the crop size to be the desired size (256 x 256). Still get the following error: Given groups=1, weight of size [64, 196, 3, 3], expected input[1, 136, 260, 260] to have 196 channels, but got 136 channels instead