Closed trungpx closed 2 years ago
Hi, we fixed the issue yesterday. Can you pull and try again?
I'm trying and will get back soon.
Thanks for the fixing. It's correct now. Due to this issue, all other baselines using momentum I ran 2 days ago are wrong. I'm running again all of them with the fixed one.
To summarize issue and code fixed, the change in base.py as follows:
Yesterdays (wrong): self.momentum_updater.update_tau(cur_step=cur_step, max_steps=self.num_training_steps) Today (fixed --> worked): self.momentum_updater.update_tau(cur_step=cur_step, max_steps=self.max_epochs * self.num_training_steps)
Hello,
I used this library before. Today I just clone the latest one from this website. But when running the baseline of BYOL, I found its tau seems to be incorrect as picture below. Am I correct or this is just an intended update from you, Vturrisi?
Figure1. It looks not correct since previously it increases from 0.99 to one as in Fig. 2 I ran before.![image](https://user-images.githubusercontent.com/37993448/171784664-92dce5c7-7065-4fbd-bc85-3f819e6657ab.png)
Below I looked up again the previous runs. Figure 2. A reference to BYOL ran 1 month ago.![image](https://user-images.githubusercontent.com/37993448/171785163-51662391-7238-4533-8a44-bf4757149805.png)