Zhipeng Zhou

A question about code

1

In _get_64_anchor(self,gtbox), can you explain why the x of anchor is 14+28*a in the 'anchor = [14+28*a, 14+28*b, self.anchor_shape[c][0], self.anchor_shape[c][1]]', I can not understand since the whole network stride is...

Hi Seongmin, great work! I have run your code, it performs well. But diving into the training details, I found that each episode you just sample a task while in...

Are customized loss functions supported?

9

Hi! Thanks for the contributions, I would like to know if customized loss functions are supported. Currently, it seems that only those defined in PyTorch are supported. Best

Are customized loss functions/layers supported?

2

Hi! Thanks for the great work. I'm trying to use the Laplace approximation in my work, but your package only supports MSE and CE, and the corresponding layers only support...