Closed wangyuyy closed 1 year ago
I think the easiest way would be to use (part of) the training set as validation set, so you can get plots for the training images. Basically change the data-loading to load the training set twice instead of train+test
I have a problem. How to output a rendered image instead of a video using a trained model. How to set it up while testing.
I found that in videodataset, train dataset returns a batchsize of rays while test dataset returns rays of a whole image. But I want to check out the reconstruction quality of the training views(not just mse or PSNR informations), when the training was done. I tried to modify the
__getitem__
method of the videodataset by ignoring theif self.split == 'train'
, but the output is still not correct. So I wonder if there is an easy way to achieve it.