Giters

lliuz / ARFlow

The official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

how to inference your given model on a set of consecutive images?

TengFeiHan0 opened this issue · comments

commented

I 'd like to test your models on my own images, but each time it only accepts three images. will you support this option?

commented

Hi, @TengFeiHan0
It is quite easy to implement it by yourself, here are some suggestions:

You can refer to inference.py to implement it, just traverse your image samples and feed to the model to run repeatedly.

Besides, if you have a large number of consequent images, you can modify the model file to keep a buffer to save the feature pyramid of the previous image to save some inference time.