The official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".
If i have my own unlabeled dataset (no ground truth) on which i want to train the ARFlow network.
How can i do it? Is there a rule of thumb of organizing the data in order to train the NN?
If i have my own unlabeled dataset (no ground truth) on which i want to train the ARFlow network. How can i do it? Is there a rule of thumb of organizing the data in order to train the NN?