aoyanl

Results 6 comments of aoyanl

> > Hi, do you got any problems in visualizing the masked labels? > > my visualized labels: ![image](https://user-images.githubusercontent.com/64065947/153202928-cfc936bf-7c2d-4aab-8142-98bec7a14669.png) > > visualized labels in this paper: ![image](https://user-images.githubusercontent.com/64065947/153203390-a08be52b-3823-4e80-b12b-8379a730ee4c.png) > > It...

I also have a question about signal scaling, the codes below are added after the combination of signal and noise, x = torch.clamp(x, min=-1 * self.scale, max=self.scale) x = ((x...

Hi, I also want to know whether the code of TD2-bise34 and TD4-bise18 will be released?

> Hey @bradyz , thanks! > > Just got finished on a smaller scale training (150 scenes, 5 epochs) and here are the results. Working on using a larger subset...

Will the visible mask be used in the training/validation phase later?

@happycoding1996 hello, I can't even get a harmonic mean of 28.18 . How many gpus did you use? What is the batch size? and can you provide the init model...