What is the effect of Cache?
raywzy opened this issue · 2 comments
Very impressive work! While checking the dataset file, I found you utilize the cache to ensure no repeat calculation for each source image. But it will lead to one-to-one matching during training, rather than selecting the target view randomly. Is it right?
You made a very good point that I probably ignore it myself!
The cache is only aiming for acceleration, but I did not find that it leads to one-to-one matching -- It is a bug when I refactor my code for release.
You are free to turn it off, and it probably gives similar or even better result.
You made a very good point that I probably ignore it myself!
The cache is only aiming for acceleration, but I did not find that it leads to one-to-one matching -- It is a bug when I refactor my code for release.
You are free to turn it off, and it probably gives similar or even better result.
Thanks for your reply :)